NV Digital Open Operator System (NVoOS)

Version: 1.1.91 Release Date: 2026-10-01

See § Release History for the 12 most recent releases; every older release is in the Previous Releases table. Full detail: CHANGELOG.md.

🆕 v1.1.91 Highlights: FlowHub MCP mode, MCP App OAuth discovery, and OAuth redirect allowlists. FlowHub Connection MCP mode (#6836) — a flowhub_mode selector on FlowHub Remote Sites connections (MCP mode designates the connection as the FlowHub toolkit MCP server backend) with proxy inheritance: MCP-triggered refresh/sync calls route through the explicit-connection path (decrypted credentials + the connection's encrypted proxy via http_api_curl); explicit connection_id always wins and the seam is generic. MCP App OAuth discovery per MCP spec (#6835) — the full discovery chain (RFC 8414 + §3.2 path insertion, RFC 9728 protected-resource metadata, 401 WWW-Authenticate probe, OIDC + WordPress REST fallbacks) with per-attempt diagnostics surfacing real transport errors. OAuth redirect allowlists (#6831/#6832) — LinkedIn, QuickBooks, Mailjet, and Yahoo connect buttons no longer bounce to wp-admin. JSON envelope protection (#6827) — orchestration CCTs gate on the physical table and the new WP_MCP_AI_Db_Output_Guard wraps central tool dispatch. Security-events display + double-render fixed (#6829/#6830). Dependency advisories (#6833/#6834) — nodemailer 10.x + fast-uri floors. Tool count: ~347 base + ~1,301 Pro (~1,648 total; unchanged). Stale 1.1.89 build ZIPs removed (30 files).

MCP Specification: 2026-07-28 (Stateless Core, Full Compliance)
Maintained by NV Digital
License: GPLv3 or later
Requires: WordPress 6.0+, PHP 7.4+
Patent Status: Patent Pending (Application #19/410,504)
Documentation: Grade A (95/100) — 1,617 files across 12 directories, 108 admin screenshots, 100% feature coverage

🔍 For Reviewers & Auditors

New to this repo? Start here → docs/project/FOR_REVIEWERS.md

That document answers every common question in one place: what the project is, current security posture, what's production vs experimental, PHP version requirements, AI development methodology, compliance status, and scoping advice for a limited-budget review.

Quick links for reviewers:

• Addon Inventory — what each of 28 addons does and its status

• Security Posture — current state of all 50 audit findings

• Compliance Traceability — every .org rejection reason → commit → verification command

• AI-Assisted Development — methodology, transparency, and what to scrutinize

• Architecture Overview — component diagram and data flow

Related MCP server: WP MCP Ultimate

📑 Table of Contents

Getting Started

• 🧩 Overview

• 🎯 Our Mission

• 🛡️ Active Security Monitoring

• ⚠️ Warranty & Safe Use

• 🏗 System Architecture

• 🚀 Features

• 📦 Installation

  • 🌱 Try It on Your PC

• 🔌 What You Lose Without Third-Party Plugins

• ⚙️ Configuration Checklist

• 📚 Documentation

Core Functionality

• 🧠 Memory & Tool Stack Overview

• 🛠 Built-in tools & automations

• 🗨️ Front-end chat surfaces

• 💬 Frontend Shortcode

Addons & Extensions

• 🏗 System Architecture (covers addon ecosystem)

Orchestration & AI Features

• 🏗 System Architecture (covers orchestration, harnessing, MCP servers, memory bridge)

AI Providers & Integration

• 🧠 Language Model Providers

• 🧱 ChatKit Integration

• 🌐 Crawl4AI Integration

• 📡 Job Notification System

• 🧊 Elementor Widgets

Performance & Optimization

• ⚡ Message Bundling

• 🎯 Agentic Loop Token Management

• 🔄 Chat Performance Optimizations

• 🌐 Mesh Compute Routing

• 🔗 Federation & Discovery System

Remote MCP Setup

• 🔒 MCP Server Authentication

• 🌐 Connecting Remote MCP Clients

• 🛰 REST API Endpoints

• 🌊 SSE Streaming Support

• 📝 MCP JSON-RPC 2.0 Endpoint

• 🔑 Assistant API Credentials

• 🎫 Token Management UI

Assistant Management

• 🛠 Assistant Editor Overview

• 📊 Assistant Storage: CPT vs CCT

• ⚡ Assistant Tool Shortcuts

• 🧠 Agent Skills

• 👔 Professional & Team Layers

• 🧵 REST Chat Payloads & Attachments

Development

• 🐳 Local Development with Docker

• 🧑‍💻 Development Tooling

• 📦 NPM Packages

• 🧪 Testing & QA

• 🧩 Hooks & Filters

• 🧰 WP-CLI Commands

Reference

• 🔐 JetEngine Capability Reference

• 🛰 JetEngine REST API Reference

• 🧮 Usage Tracking

• 🧷 Attachment MIME Controls

• 🧾 Logging

• 🧾 JetEngine REST Endpoint Report Helper

• 🔌 Optional Tools & Dependencies

• ✅ Manual QA Scenarios

Changelog

• 📜 Release History

• 📋 Previous Releases

🗺 Repository Map

🧩 Overview

Real-time AI Orchestration Toolkit / Harness for Wordpress - NV oOS is a modular AI framework (Object-Oriented System) for WordPress that connects your site's data with 15 language-model providers: OpenAI, Gemini, Anthropic, DeepSeek, OpenRouter, Baseten, Kimi (Moonshot), Z.AI (GLM), DigitalOcean, NVIDIA NIM, Cloudflare Worker AI, Ollama, LM Studio, Hugging Face, and Flowhub. It allows you to create and manage AI Assistants that can interact with users, access WordPress data, and perform custom tool functions.

✨ What's New at a Glance (v1.1.91)

• 🔌 FlowHub Connection MCP mode (PR #6836). FlowHub Remote Sites connections gain a flowhub_mode selector (api default | mcp) — MCP mode designates the connection as the backend for the FlowHub toolkit MCP server. WP_MCP_AI_FlowHub_Connection_Helper::get_mcp_connection_id() resolves the first enabled MCP-mode connection and the toolkit MCP REST controller injects its ID into tool arguments only when the caller passes none — MCP-triggered refresh/sync calls now route through the explicit-connection path so credentials and the connection's encrypted proxy apply via http_api_curl. Explicit connection_id always wins; without an MCP-designated connection, behavior is byte-for-byte unchanged. The seam is generic (WP_MCP_AI_Toolkit_Server_Base::get_mcp_connection_id()).

• 🔐 MCP App OAuth discovery per MCP spec (PR #6835). discover_metadata() now walks the full chain — RFC 8414 metadata (+ §3.2 path insertion for path-scoped servers), RFC 9728 protected-resource metadata (trying every authorization_servers entry), the 401 WWW-Authenticate probe, OIDC fallback for Auth0/Okta/Cognito, and WordPress REST fallback. RFC 8414 docs are accepted only with both endpoints; every attempt is logged and the metabox failure alert surfaces the real transport error; server-advertised default_scope is honored; multi-challenge WWW-Authenticate parsing; 10 s per-probe cap.

• 🔗 OAuth redirect allowlists (PRs #6831, #6832). LinkedIn, QuickBooks, Mailjet, and Yahoo Sports connect buttons no longer silently bounce to wp-admin — each flow now allowlists its consent-page host (www.linkedin.com, appcenter.intuit.com, app.mailjet.com, api.login.yahoo.com) via the allowed_redirect_hosts filter, with matching ports in the Content Graph AI platform.

• 🛡 JSON envelope protection (PR #6827). Orchestration CCT reads gate on the physical table (table_exists() → is_storage_ready(): table + every required column — schema drift trips the gate and falls back to transients); the new WP_MCP_AI_Db_Output_Guard wraps the central tool dispatch (execute_tool() + both REST tool handlers) so no surface can leak $wpdb error HTML into a JSON response again — the 5-second orchestration dashboard poll's parsererror: Unexpected token '<' failure is gone.

• 🐞 Security events display + double-render fixed (PRs #6829, #6830). The Security tab's "Recent Security Events (last 10)" table and the compliance CSV exporter now read the canonical event_type/ip_address keys (with legacy fallbacks), label known event slugs, and show display names; the orchestration dashboard no longer renders twice (a duplicate loader instantiation registered two callbacks on the same page hook).

• 🧩 RF-DETR presets + coverage manifest (PR #6828). rfdetr_catalog_search joins the ecommerce preset; rfdetr_detect stays gated behind the vision-analysis toolkit (matching its siblings); the Pro tool coverage manifest is regenerated — the RF-DETR cluster's CI failures are closed.

• 🔒 Dependency advisories (PRs #6833, #6834). nodemailer ^9.1.1 → ^10.0.9 in addons/pro + addons/media-worker (GHSA-g57g-f23g-4646 — vendor bundle refreshed with the old lib/ removed); fast-uri override floor → >=4.1.5 across the four alert-bearing trees (GHSA-jvvf-x445-j334) — four Dependabot alerts closed each.

• 🌐 Ecosystem port (PR #6825). The RF-DETR vision cluster (Roboflow service, rfdetr_detect, count normalizer, e-commerce catalog search, dHash copy, standalone init) ports byte-identical into nvoos-content-graph-pro — Wave F3 sub-cluster 1 complete, tracker row appended.

• 📦 Versioning — bumped to 1.1.91 across all version-bearing files. Pro addon: 1.1.91. Media Worker: v3.2.0 (unchanged — the nodemailer bump carries no version change). SaaS Controller: 0.3.0 (unchanged). Design System addon: 0.3.0 (unchanged). nvoos-content-graph: 1.0.8 (unchanged). nvoos-content-graph-ai: 1.0.4 (unchanged). nvoos-content-graph-ai-platform: 2.0.0 (unchanged — OAuth ports + build refresh). nvoos-content-graph-pro: 1.0.0 (unchanged — two in-feature ports landed). Checkout API: 0.1.2 (unchanged). Docs Hub: 0.5.1 (unchanged). Comic Reader: 0.5.0 (unchanged). Chat SPA: 0.7.0 + Canvas Toolkit: 0.2.0 (unchanged). Model catalog: v2026.09.22 (unchanged). Tool count: ~347 base + ~1,301 Pro (~1,648 total — unchanged). Provider count: 15 chat providers (unchanged). Addon count: 28 (unchanged). Bundled skills: 75 base + 41 Pro (unchanged). Coding-time agent skills: 61 (unchanged). Stale build ZIPs removed: the 1.1.89 build set (30 files).

🎯 Mission: Modernizing Small to Medium Business Websites

NV oOS is specifically designed to help small to medium-sized businesses fast-track their outdated, stale, or insecure company websites to modern technology standards—without the need to add yet another wrapper around API calls. Instead, we're trying to peel back decades of API wrappers with the help of AI, providing:

• Direct AI Integration - No middleware required. Connect directly to OpenAI, Gemini, Anthropic, Hugging Face, Cloudflare Worker AI, Ollama, LM Studio, OpenRouter, and DeepSeek without custom development

• Security-First Architecture - Built-in protection against nefarious usage with active monitoring and prevention systems

• Enterprise-Grade Features - Access to capabilities typically requiring expensive custom development

• Compliance & Audit Tools - Comprehensive logging, rate limiting, and usage tracking built-in

• Zero Technical Debt - Modern codebase following WordPress standards, ready for current technology stacks

🛡 Active Security Monitoring

NV oOS actively prevents and monitors against nefarious behavior. The plugin includes:

• Nefarious Usage Monitor - Real-time detection of suspicious patterns and automatic emergency shutdown capabilities【F:includes/class-wp-mcp-ai-nefarious-usage-monitor.php†L1-L676】

• Root Security Key - Optional emergency authentication layer to prevent unauthorized reactivation after security incidents【F:docs/features/security/root-security-key.md†L1-L511】

• Granular Capability Controls - Every tool and API endpoint enforces WordPress capabilities to prevent unauthorized access

• Rate Limiting - Built-in protection against abuse with configurable limits per user, model, and time period

• Comprehensive Audit Logging - Track all API calls, tool executions, and security events for compliance and forensic analysis

• Input Sanitization & Output Escaping - All user input sanitized, all output escaped following WordPress security best practices

This is not a tool for circumventing security or promoting bad practices. Every feature is designed with security, transparency, and responsible AI usage as core principles. The plugin actively works to stop and prevent misuse before it happens.

Latest audit: See docs/operations/compliance/SECURITY_AUDIT_2026_04.md — the published summary of the April 2026 security & compliance code review (no Critical findings; 5 High items, 3 Fixed and 2 Partially Fixed). Full deliverables under docs/project/audits/2026-04/.

WordPress.org compliance hardening (May 9, 2026): docs/operations/compliance/WORDPRESS_ORG_COMPLIANCE_2026_05_09.md — findings B3, B8, B10, B13, and production vendor remap all resolved.

⚠ Warranty & Safe Use

We make every effort to keep NV oOS safe and secure — but by design, it can be destructive and resource-intensive when not properly configured.

NV oOS grants AI assistants access to powerful WordPress operations. The same capability that automates real work can cause irreversible harm if misconfigured:

• Destructive tools — bulk content deletion, user management, file writes, mass email, WP-CLI, direct database operations

• API billing exposure — uncapped AI provider calls can exhaust quotas and trigger unexpected charges

• Server resource exhaustion — concurrent agentic loops and SSE streams can saturate CPU/memory on shared hosting

Before going live: test on staging, take verified backups, apply least-privilege tool permissions, enable rate limiting, and review the system prompt of every public-facing assistant.

📄 Full details: WARRANTY.md — security commitment, "AS IS" disclaimer, destructive-operations table, resource-consumption guide, and mitigation checklist aligned with OWASP, NIST SP 800-53, ISO/IEC 27001, and the WordPress Plugin Developer Handbook.

Patent Pending

NV oOS is the subject of a pending patent application for its novel System and Method for Dynamic AI Orchestration Layer with Real-Time Capability Gating and Resource Budgeting.

Application Number: 19/410,504

The patent covers NV oOS's innovative approach to implementing sophisticated AI orchestration in WordPress's request-based PHP architecture—a platform not designed for real-time streaming, asynchronous operations, or persistent state management. This technical achievement enables enterprise-grade AI capabilities on WordPress by recreating event-driven behavior within PHP's synchronous execution model.

Key Innovations Covered:

• Dynamic resource budget allocation during streaming operations

• Capability-based access control for AI tool execution

• Registry-state-based scheduling in stateless environments

• Metrics-driven budget adjustment for real-time optimization

• Persistent-behavior illusion in request-based architectures

The orchestration layer makes NV oOS unique in the WordPress ecosystem by solving fundamental architectural limitations that prevent traditional WordPress plugins from supporting advanced AI features. See the System Architecture section below for technical details on how these innovations work together.

🏗 System Architecture

NV oOS implements a comprehensive orchestration layer for managing AI operations during real-time streaming events. The system architecture comprises:

• 15 language-model providers — OpenAI, Gemini, Anthropic, DeepSeek, OpenRouter, Baseten, Kimi (Moonshot), Z.AI (GLM), DigitalOcean, NVIDIA NIM, Cloudflare Worker AI, Ollama, LM Studio, Hugging Face, Flowhub

• ~1,648 tool classes (~347 base + ~1,301 Pro; live count via WP_MCP_AI_Tool_Registry::get_tools() is authoritative) registered through a singleton Tool Registry

• 36 REST controllers (16 base + 20 pro) under the mcp-ai/v1 namespace

• 64 service classes powering orchestration, budgets, and workflows

• 5 authentication methods — WordPress nonce, assistant credentials, mesh keys, Auth0 JWT, guest tokens

• Toolkit MCP servers — per-toolkit JSON-RPC 2.0 servers exposed under /wp-json/mcp-ai-pro/v1/mcp/{slug}; discoverable at /.well-known/mcp

• 8 inline-async-tick consumers — cooperative tick-lock pattern eliminates WP-Cron startup latency for background jobs (transcript mining, async tool executor, SaaS Apply, Crawl4AI, Docs Hub rebuild, Graphify reindex, Harness eval, Gemini Veo polling)

• 7 LLM Harness layers (+ 1 Pro) — opt-in epistemic layers A–H activated per-assistant via the LLM Harness metabox

• Orchestration Phases 1–7 — HITL approval queue, prompt-injection detector, structured output, OTel exporter, DAG builder, durable runs, triggers/webhooks, sub-agents

📖 For a detailed explanation of how NV oOS extends standard SSE and MCP protocols with novel orchestration features, see ORCHESTRATION-LAYER-ARCHITECTURE.md

Core Orchestration Layer: Overcoming PHP's Limitations

Critical Context: Most real-time AI streaming systems are built with Node.js, Python FastAPI, or Go — platforms designed for asynchronous, event-driven operations. These platforms natively support:

• Long-lived connections and persistent state

• Non-blocking I/O and parallel execution

• Event loops and asynchronous callbacks

• WebSocket protocols and SSE streaming

NV oOS achieves the same capabilities in PHP/WordPress — an environment fundamentally not designed for these patterns — through a sophisticated orchestration layer that creates a "persistent-behavior illusion":

1. Real-Time Budget Enforcement - Monitors token/memory usage during streaming, prevents exhaustion through predictive allocation

2. Capability-Based Tool Gating - WordPress role-based access control for AI tool execution

3. Predictive Optimization - Analyzes usage patterns to prevent resource overruns before they occur

4. Distributed Orchestration - Multi-provider support with policy-aware routing

5. Auditability & Compliance - Complete governance layer with logging and rate limiting

6. Cron-Based Task Orchestration - Extends orchestration to async operations with budget inheritance

Multi-Agent Orchestration Enhancement (DeepSeek V4-Inspired)

Added: January 2026 (v1.1.0)

Building upon the core orchestration layer, NV oOS now includes a sophisticated multi-agent coordination framework inspired by DeepSeek V4's orchestration patterns:

Key Components:

• Agent Role System - Four specialized roles (Planner, Executor, Critic, Specialist) with role-specific capabilities

• Team Composition - Automated team assembly based on task requirements and profession expertise

• Coordinated Workflows - Multi-step workflows with agent delegation, result aggregation, and validation

• Team CPT Integration - Persistent team configurations with orchestration modes (single/sequential/parallel/swarm)

• Profession-Based Discovery - 296 professions auto-assigned agent roles via intelligent seeding across 17 knowledge bases

Example Multi-Agent Workflow:

// 1. Compose research team (planner + executors + critic)
$orchestrator = new WP_MCP_AI_Agent_Team_Orchestrator();
$team = $orchestrator->compose_team( array( 'task_type' => 'research' ) );

// 2. Execute coordinated workflow
// Planner decomposes task → Executors research subtasks → 
// Communication service aggregates → Critic validates quality
$result = $orchestrator->execute_team_workflow( $team, $task, $context );

Documentation:

• See Multi-Agent Orchestration for complete technical details

• See DEEPSEEK-V4-README.md for documentation suite overview

• See DEEPSEEK-V4-USAGE-GUIDE.md for practical examples

Why This Architecture Is Novel: Overcoming PHP's Limitations

• Event loops and background workers

PHP/WordPress, by contrast, is fundamentally request-based:

• Every HTTP request spawns a new process that dies after responding

• I/O operations block execution

• No persistent memory between requests

• No native event loop or async coordination

NV oOS solves this by implementing an orchestration layer that creates a "persistent-behavior illusion" — effectively recreating Node.js's event loop behavior within WordPress's synchronous, request-based architecture. This architectural compensation is the system's core technical innovation:

This makes NV oOS patent-worthy as a technical workaround — it achieves sophisticated AI orchestration in an environment specifically not designed for such patterns. See ORCHESTRATION-LAYER-ARCHITECTURE.md for the complete technical analysis.

Computer-Implemented Resource Management

The system operates as a computer-implemented method executing on a processor with memory, performing:

1. Dynamic Resource Budget Allocation: The orchestration layer dynamically allocates token and memory budgets to tool execution requests based on real-time system capacity and operation requirements. The WP_MCP_AI_Resource_Manager continuously monitors server resources (PHP memory limits, execution time constraints) and automatically adjusts operational parameters.

2. Capability-Based Access Control: Tool execution endpoints enforce granular capability-based access controls. Each tool in the registry declares required WordPress capabilities, and the REST API controller validates user permissions before allowing execution. This ensures secure, policy-driven access to all operations.

3. Registry-State-Based Scheduling: The WP_MCP_AI_Tool_Registry maintains tool availability state and schedules execution based on policy constraints. Tools are loaded conditionally based on dependency availability, and execution is scheduled according to assistant configuration and user permissions.

4. Metrics-Driven Budget Adjustment: The system continuously monitors execution metrics (memory usage, API response times, token consumption) and adjusts resource budgets in response to prevent resource exhaustion and reduce latency. The WP_MCP_AI_Token_Budget_Manager implements safety margins and dynamic chunking to prevent API limit overruns.

System Components

The system comprises a processor and memory storing instructions that:

• Monitor real-time resource availability through PHP runtime introspection

• Enforce capability checks at REST endpoint boundaries

• Schedule tool execution through a centralized registry

• Adjust token and memory budgets based on detected system metrics

• Maintain operation logs for audit and optimization

This architecture is embodied in non-transitory computer-readable media (PHP source files) that, when executed by a web server processor, cause the system to perform the complete resource management workflow. The implementation prioritizes stability, security, and efficient resource utilization across diverse hosting environments.

Symfony Process Integration (December 2025)

NV oOS Pro addon integrates the Symfony Process component for secure external command execution. This modern framework replaces direct exec() calls in 6 Pro tools and 2 supporting services, providing:

• Enhanced Security: Proper argument escaping and command validation

• Timeout Management: Configurable timeouts with graceful handling

• Better Error Handling: Comprehensive exception catching and WordPress-friendly error reporting

• Process Control: Real-time output streaming and cancellation support

Migrated Tools & Services:

• FFmpeg operations (video frame extraction, metadata reading)

• Python rembg (background removal)

• WP-CLI execution

• Meta AI Jukebox (music generation)

• Supporting services for video and audio processing

The Process Service (WP_MCP_AI_Process_Service) provides WordPress-friendly wrappers with WP_Error integration, making external process execution consistent with WordPress coding standards.【F:includes/services/class-wp-mcp-ai-process-service.php†L1-L220】【F:docs/history/2025/implementations/symfony-phases/SYMFONY_PHASE2B_PROCESS_INTEGRATION.md†L1-L100】

📜 Release History

The 12 most recent releases are documented in full below. Every older release has a one-line summary in the Previous Releases table, and complete per-release detail lives in CHANGELOG.md.

v1.1.91 — October 1, 2026

FlowHub MCP Mode, OAuth Discovery & JSON Envelope Protection

• 🔌 FlowHub Connection MCP mode (PR #6836). FlowHub Remote Sites connections gain a flowhub_mode selector (api default | mcp) — MCP mode designates the connection as the backend for the FlowHub toolkit MCP server. WP_MCP_AI_FlowHub_Connection_Helper::get_mcp_connection_id() resolves the first enabled MCP-mode connection; the toolkit MCP REST controller injects its connection_id into tool arguments only when the caller passes none — MCP-triggered refresh/sync calls route through the explicit-connection path so decrypted credentials and the connection's encrypted proxy apply via http_api_curl. Explicit connection_id always wins; without an MCP-designated connection, behavior is byte-for-byte unchanged; the seam is generic (WP_MCP_AI_Toolkit_Server_Base::get_mcp_connection_id()).

• 🔐 MCP App OAuth discovery per MCP spec (PR #6835). WP_MCP_AI_MCP_App_OAuth_Client::discover_metadata() walks the full chain — RFC 8414 metadata (+ §3.2 path insertion for path-scoped servers), RFC 9728 protected-resource metadata (trying every authorization_servers entry), the 401 WWW-Authenticate: Bearer resource_metadata probe, OIDC fallback, and WordPress REST fallback. RFC 8414 documents are accepted only with both endpoints; every attempt is recorded (URL → HTTP status / transport error) and the metabox failure alert surfaces the real transport error; server-advertised default_scope is honored; parse_www_authenticate() splits multiple challenges per RFC 7235 §2.1; 10 s per-probe cap.

• 🔗 OAuth redirect allowlists (PRs #6831, #6832). LinkedIn, QuickBooks, Mailjet, and Yahoo Sports connect buttons no longer silently bounce to wp-admin — each flow allowlists its consent-page host (www.linkedin.com, appcenter.intuit.com, app.mailjet.com, api.login.yahoo.com) via the allowed_redirect_hosts filter, deriving the host from the provider's authorize-endpoint filter; matching ports land in the Content Graph AI platform.

• 🛡 JSON envelope protection (PR #6827). Orchestration CCT reads gate on the physical table — table_exists() probe → is_storage_ready() (table present and every required column; schema drift trips the gate → transients fallback, logged; per-request cache with a reset_storage_cache() seam). The new WP_MCP_AI_Db_Output_Guard::run() suppresses $wpdb error output around callbacks (logging failures with the last query) and wraps the central tool dispatch — execute_tool() + both REST tool handlers — so no surface can leak database error HTML into a JSON response again; the four agent-command-center read AJAX handlers gain with_suppressed_db_errors().

• 🐞 Security events display + double-render fixed (PRs #6829, #6830). The Security tab's "Recent Security Events (last 10)" table and the compliance CSV exporter now read the canonical event_type/ip_address keys (with legacy fallbacks), label known event slugs, and show user display names (Guest for unauthenticated) — stored entries were always correct, only the display keys were wrong. The orchestration dashboard no longer renders twice: the self-instantiating class gained a duplicate new in the bootstrap loader, registering two distinct callbacks on the same page hook (duplicate DOM IDs breaking the auto-refresh JS) — the redundant new is removed.

• 🧩 RF-DETR presets + coverage manifest (PR #6828). rfdetr_catalog_search joins the ecommerce preset ("Product operations"); rfdetr_detect stays deliberately out of presets (gated behind enable_vision_analysis_toolkit, matching its siblings); the Pro tool coverage manifest is regenerated with the two missing class basenames.

• 🔒 Dependency advisories (PRs #6833, #6834). nodemailer ^9.1.1 → ^10.0.9 in addons/pro + addons/media-worker (GHSA-g57g-f23g-4646, alerts #977/#978 — quoted local-part envelope injection) with the vendor copy spec switched to dist/ (nodemailer 10 ships no top-level lib/) and the vendor bundle refreshed 8.0.5 → 10.0.9; fast-uri override floor → >=4.1.5 across the four alert-bearing trees (GHSA-jvvf-x445-j334, alerts #979–#982 — mailto header injection), verified additive-only via npm-pack diff.

• 🌐 Ecosystem port (PR #6825). The RF-DETR vision cluster ports byte-identical into nvoos-content-graph-pro — the Roboflow inference service (three trust tiers, fail-closed credentials, SSRF/HTTPS discipline), WP_MCP_AI_Tool_Rfdetr_Detect, the vision count normalizer, the e-commerce catalog search (44-tool e-commerce registration), the D8-compat image-dHash copy, and the slim standalone init with the toolkit_vision_analysis module gate — dual-matrix green with the documented deviations; tracker row F3 appended (sub-cluster 1 complete).

• 📦 Versioning — bumped to 1.1.91 across all version-bearing files. Pro addon: 1.1.91. Media Worker: v3.2.0 (unchanged — the #6833 nodemailer bump carries no version change). SaaS Controller: 0.3.0 (unchanged). Design System addon: 0.3.0 (unchanged). nvoos-content-graph: 1.0.8 (unchanged). nvoos-content-graph-ai: 1.0.4 (unchanged). nvoos-content-graph-ai-platform: 2.0.0 (unchanged — OAuth ports + build refresh). nvoos-content-graph-pro: 1.0.0 (unchanged — two in-feature ports landed: the RF-DETR cluster (#6825) and the FlowHub MCP-mode mirrors (#6836)). Checkout API: 0.1.2 (unchanged). Docs Hub addon: 0.5.1 (unchanged). Comic Reader addon: 0.5.0 (unchanged). Chat SPA addon: 0.7.0 + Canvas Toolkit addon: 0.2.0 (unchanged). Model catalog: v2026.09.22 (unchanged — no model PRs in-window). Tool count: ~347 base + ~1,301 Pro (~1,648 total — unchanged) — no tool registrations in-window (FlowHub MCP mode is a connection-binding seam; #6828 only wires the existing RF-DETR pair into presets/manifest; live registry authoritative). Provider count: 15 chat providers (unchanged). Addon count: 28 (unchanged). Bundled skills: 75 base + 41 Pro (unchanged). Coding-time agent skills: 61 (unchanged). Stale build ZIPs removed: the 1.1.89 build set (30 files: 9 in build/ incl. 3 .sha256, 2 in build/optional-components/, 19 in build/toolkit-addons/).

v1.1.90 — September 30, 2026

RF-DETR Vision Cognition, Strict MCP Scope & Memory Identity Closure

• 🔍 RF-DETR vision cognition (PR #6824, Proposal 049). New Pro WP_MCP_AI_Roboflow_Inference_Service — one HTTP client across three trust tiers (key-less self-hosted Docker Inference server on loopback/private hosts; dedicated deployments; Serverless Cloud API) with fail-closed credentials (va_roboflow_api_key as the raw Authorization header for serverless/dedicated, HTTPS enforced off-loopback, every URL passes the SSRF guard, operator-allowlist seam). Two new Pro tools — rfdetr_detect (task=detect|segment|keypoints: ranked boxes, instance-segmentation mask polygons, 17-COCO person keypoints) and rfdetr_catalog_search (fine-tuned catalog models by alias or workspace/project/version, per-model + dHash 5-min transient cache) — returning the canonical {label, confidence, box, mask_points?, keypoints?} shape. The roboflow provider joins analyze_image_objects (detector-owns-the-count invariant, no new slug); identify_image rung 3c reports rfdetr_detections as an additional source (class-guarded — Base installs skip with pro_addon_required/not_configured, zero behavior change). Apache-2.0 aliases by default; XL/2XL (PML 1.0) behind the va_roboflow_allow_pml consent toggle. RF-DETR settings section (Vision Analysis) + deployment guide (docs/operations/deployment/roboflow-inference-server-setup.md).

• 💼 Upwork MCP as first-class MCP Apps references (PR #6823). Upwork-in-MCP-mode Remote Sites connections now appear in the assistant MCP Apps metabox "Add from Remote Sites" dropdown (labelled Name (Upwork MCP — https://mcp.upwork.com/mcp)) with the full OAuth login UI (web login / loopback paste-back / authenticated state). resolve_connection_ref() resolves Upwork refs at chat time via build_upwork_mcp_app_config() (official gateway + decrypted central mcp_oauth); the import validator no longer auto-disables Upwork refs; finalize_oauth_flow() persists the reference entry onto the assistant so it survives the post-login reload.

• 🧠 Memory identity resolution + cross-agent access closure (PR #6815). All eight memory tools (retrieve_agent_memory, store_agent_context, recall_memory, wake_up_context, semantic_context_search, mine_agent_memory, manage_context_lifecycle, batch_manage_memory) accept an optional agent_id and otherwise resolve the caller's identity from the execution context via WP_MCP_AI_Agent_Identity_Resolver. Cross-agent access gated behind manage_options (403 mcp_ai_memory_scope_denied — the IDOR closed); 400 mcp_ai_memory_no_agent when no identity resolves; every success envelope echoes resolved_agent_id + resolution_source. store_agent_context scans for credential patterns (incl. the plugin's own cred_…<secret> format) flagged sensitive_patterns/contains_sensitive; retrieve_agent_memory carries expiry signalling (expires_in, expires_soon ≤7 days).

• 🛡 Strict MCP assistant-scope toggle (PR #6819). Opt-in mcp_require_assistant_scope (Security → Access & Identity, default OFF): MCP tools/list + tools/call fail closed with HTTP 403 (wp_mcp_ai_assistant_scope_required) when no assistant resolves (no explicit assistant_id, no token-bound assistant, no default assistant). Shared maybe_enforce_strict_scope() gates mcp_tools_list() after the resolve/scope chain and mcp_tools_call() before the tool executor; the 403 special-case is scoped to this one error code (all other errors keep the HTTP 200 JSON-RPC envelope). Closes #6769.

• ✉️ Letterhead email personalization (PR #6816). The letterhead template renders Dear {{to_name}},; the renderer gains {{#to_name}}…{{/to_name}} conditional blocks (bare addresses never emit Dear ,); get_builtin_html() prefers the direct filesystem transport with a plain local-read fallback — bundled templates no longer silently no-op on hosts where direct is unavailable.

• 🔒 Dependency advisories (PR #6817). js-yaml overrides → >=5.4.1 across 13 package trees (lockfiles → 5.4.2) + scoped webpack-dev-middleware@^8 → >=8.3.0 (root + addons/pro/assets/spa) — 15 of 17 open Dependabot alerts resolved; 13 lockfiles regenerated + npm ci --dry-run verified; the AI SDK 2.x-line advisory stays open intentionally (sync→async signature change would break useChat) — tracked as #6818.

• 📦 Versioning — bumped to 1.1.90 across all version-bearing files. Pro addon: 1.1.90. Media Worker: v3.2.0 (unchanged). SaaS Controller: 0.3.0 (unchanged). Design System addon: 0.3.0 (unchanged — the letterhead/registry fix ships on the 0.3.0 line). nvoos-content-graph: 1.0.8 (unchanged). nvoos-content-graph-ai: 1.0.4 (unchanged). nvoos-content-graph-ai-platform: 2.0.0 (unchanged). nvoos-content-graph-pro: 1.0.0 (unchanged — the RF-DETR ecosystem port is open as #6825). Checkout API: 0.1.2 (unchanged). Docs Hub addon: 0.5.1 (unchanged). Comic Reader addon: 0.5.0 (unchanged). Chat SPA addon: 0.7.0 + Canvas Toolkit addon: 0.2.0 (builds refreshed in-window). Model catalog: v2026.09.22 (unchanged — Roboflow is a vision inference service outside the catalog). Tool count: ~347 base + ~1,301 Pro (~1,648 total; +2 Pro) — the RF-DETR pair; the roboflow provider is no new slug and identify_image rung 3c is additive-only (live registry authoritative). Provider count: 15 chat providers (unchanged). Addon count: 28 (unchanged). Bundled skills: 75 base + 41 Pro (unchanged). Coding-time agent skills: 61 (+1 — the dependabot-loop skill). Stale build ZIPs removed: the 1.1.88 build set (30 files: 9 in build/ incl. 3 .sha256, 2 in build/optional-components/, 19 in build/toolkit-addons/).

v1.1.89 — September 29, 2026

Google Classroom ECA, Design System Rename + Email Templates & Upwork MCP Mode

• 🎓 Google Classroom integration for the ECA toolkit (PR #6809, Proposal 046). Shared includes/google/ Classroom foundation mirroring the Calendar stack — Scopes (restricted-scope discipline, granular-consent implication checks), Client (REST v1, repeated-parameter building, page-token pagination, RESOURCE_EXHAUSTED backoff, terminal @MissingGrant, updateMask PATCH), Credentials (Pro Remote Sites resolution, decrypt-on-read, quota-user attribution), Push (Pub/Sub webhook with shared-secret verification, ack-fast cron deferral, weekly renewal). New google_classroom Remote Sites connection type (OAuth on the shared service, real courses.list test probe with needs_reconnect). 12 new ECA tools (list_classroom_courses, sync_classroom_roster_to_students, sync_classroom_courses_to_ecas, link_classroom_course_to_eca, create_classroom_course, update_classroom_course, post_classroom_announcement, create_classroom_coursework, list_classroom_submissions, classroom_course_analytics, list_classroom_guardians, manage_classroom_push_watch) behind enable_eca_classroom_integration (default off) with a nightly jittered sync engine + push-delta roster/course reconciliation. New base REST route mcp-ai/v1/google-classroom/webhook.

• 🎨 Design System addon rename + token-driven email templates (PR #6810, Proposals 047 + 048). addons/crocoblock-ds/ → addons/nvoos-design-system/ (0.1.0 → 0.3.0, zero-breakage: --cds-*/.cds-* aliases, one-way option migration, class_alias, legacy admin-post action). Token-driven email module: 5 built-in accessible templates, global wp_mail wrapper (sentinel double-wrap guard, full-document + text/plain skips), 15-token emails group with dark-mode pairs, WCAG/EMC audit gates (contrast math, BLOCK gates, 100 KB budget), multipart AltBody pairing, opt-in WooCommerce rebrand, Paper Store mirror/import bridge. 8 admin-gated nds_* tools (generate/list/preview/audit/set-active/test-send/export/import) — addon-provided via wp_mcp_ai_register_tools, not counted in base/Pro totals. Two latent addon bugs fixed (double-prefixed CSS vars that never matched component CSS; a broken integration autoloader that silently disabled all four integrations).

• 💼 Upwork MCP connection mode (PR #6804). Third upwork_mode (mcp) alongside api and web_search — talks to the official Upwork MCP gateway (https://mcp.upwork.com/mcp, 51 upwork__* tools) through a sessionful WP_MCP_AI_Upwork_MCP_Bridge (upwork__find_jobs/upwork__list_accounts, defensive normalization); search_upwork_jobs/import_upwork_project branch to the bridge with _external_source_id/_external_source_platform dedupe meta; real-handshake Test Connection; upwork_org_uid resolution; OAuth login reuses the MCP Apps flow (connection_ref on /oauth/init) with tokens in the encrypted central mcp_oauth store.

• 🖼 Vision + remote reliability + EZuite integrity (PR #6805). submit_document_prompt routes image attachments through the input_image vision segment path (previously rejected on every provider) with provider-bound client selection; WP_MCP_AI_DeepSeek_Client converts input_image to OpenAI-compatible image_url blocks for deepseek-flash (the wp_mcp_ai_deepseek_supports_vision filter gates the payload); DeepSeek gains a vision lane. Remote connections check access controls against canonical slugs (page/attachment) and surface actionable rest_no_route guidance; EZuite enforces the requested item_code client-side (no more wrong-product stock/pricing) and fixes "Untitled Product" cards; the model catalog migration now rewrites per-provider model settings (deepseek_model, default_gemini_model, anthropic_model, kimi_model) at the next catalog bump.

• ⚡ MCP legacy-dialect handshake cache (PR #6802). WP_MCP_AI_MCP_App_Client::handshake() caches a 24h per-URL legacy hint (wp_mcp_ai_mcp_app_legacy_<md5(url)>) so strict 2025-era gateways skip the doomed server/discover probe; stale hints self-heal on stateless rejections; test_connection() + registry discover_tools() delegate to it. Upwork Test Connection: ~24.9s → ~8.5s steady state.

• 🛡 Security (PRs #6807 + #6806). All 38 CodeQL alerts closed — 0 open code scanning alerts (DOM XSS escaping in the diagnostic page, CSPRNG OAuth1 nonces in the twitter-api-v2 vendor bundle, health-consolidate.js hardening, yfinance cleanup); ip-address → 10.7.2 (NAT64 SSRF), undici floors 7.29.1/8.10.2/6.28.1 (WebSocket DoS), multer → 2.4.0 (orphaned writes) across every affected tree.

• 📦 Versioning — bumped to 1.1.89 across all version-bearing files. Pro addon: 1.1.89. Media Worker: v3.2.0 (unchanged). SaaS Controller: 0.3.0 (unchanged). Design System addon: 0.1.0 → 0.3.0 (own track — the in-window inventory row said 0.2.0, corrected this pass). nvoos-content-graph: 1.0.8 (unchanged). nvoos-content-graph-ai: 1.0.4 (unchanged). nvoos-content-graph-ai-platform: 2.0.0 (unchanged). nvoos-content-graph-pro: 1.0.0 (unchanged — one byte-identical in-feature port: the product-card trait, #6805). Checkout API: 0.1.2 (unchanged). Docs Hub addon: 0.5.1 (unchanged). Comic Reader addon: 0.5.0 (unchanged). Model catalog: v2026.09.22 (unchanged). Tool count: ~347 base + ~1,299 Pro (~1,646 total) — +12 Pro (the classroom tools; the 8 nds_* tools are addon-provided and not counted; live registry authoritative). Provider count: 15 chat providers (unchanged). Addon count: 28 (unchanged — rename, not addition). Bundled skills: 75 base + 41 Pro (unchanged). Coding-time agent skills: 60 (unchanged — four updated in place). Stale build ZIPs removed: the 1.1.87 build set (30 files: 9 in build/ incl. 3 .sha256, 2 in build/optional-components/, 19 in build/toolkit-addons/).

v1.1.88 — September 28, 2026

Decision-Model Orchestration, MCP Apps Hardening & SaaS Controller 0.3.0

• 🧠 Decision-model orchestration Phase A (PR #6792, Proposal 045). The TypeSafe Jev decision model wires into the router and orchestration layers for the first time. Base: WP_MCP_AI_Verification_Cascade implements the SDE-cascade pattern (build_battery() per-field nouls framed bad=true, one batched decision call chunked at 50, max aggregation, single-rung escalation, injectable Interface_WP_MCP_AI_Decision_Client, filterable wp_mcp_ai_cascade_escalate_threshold default 0.7) plus the new wp_mcp_ai_execution_depth_confidence filter seam in execute_with_depth(). Pro: opt-in enable_jev_tier_routing tier routing (code-owned (2 − complexity)/2 confidence, neutral 0.65 fallback, caller signals always win, decision_model metadata) and opt-in enable_jev_citation_escalation citation cascade (two-head battery per claim, escalate_flagged_citations() verification-tier revision capped via wp_mcp_ai_citation_escalation_max) wired into research_eca + generate_research_report. Fail-open everywhere, off by default, only the first user message ever reaches Jev, thresholds stay in PHP. Gap review: docs/project/audits/2026-09/decision-model-orchestration-gap-review.md. Deferred: extraction cascade + G2/G3/G4/G6–G8.

• 🔐 MCP Apps OAuth + credential hardening (PRs #6794/#6795/#6798). Upwork accepts only loopback redirect URIs — initiate_oauth() falls back to redirect_mode: manual_loopback on DCR invalid_redirect_uri and the admin pastes the localhost callback into the new POST mcp-ai/v1/mcp-apps/oauth/complete endpoint (10-minute state TTL, shared finalize_oauth_flow(), JSON-first with form-encoded retry on 415). client_id is sent in token-exchange/refresh bodies (Upwork requires it) and the paste-back box survives reloads. Inline MCP App secrets (token, oauth_data) + Remote Sites verify_token/verification_token are now encrypted at rest (AES-256-CBC) and masked in forms; rotated tokens persist (inline meta, update_mcp_oauth(), tool-bridge re-hydration); Test/Discover restores stored OAuth credentials (fixes "No OAuth access token available"); mcp_oauth_refresh activity events carry metadata only.

• 🛡 Toolkit MCP servers gated on assistant grants (PR #6796). Deny-by-default: handle_jsonrpc() requires an explicit grant for assistant-scoped requests (params.assistant_id) — non-granted servers return -32601 "Server not granted to this assistant"; initialize/ping stay ungated and toolkitServers always reflects the exact grant list (empty allowlist = no grants, per the corrected UI copy); assistant_id-less requests bypass the gate; the server-level toggle is unchanged. CG Pro mirror byte-identical.

• 🔌 MCP App transport fixes (PRs #6799 + #6800). Strict 2025-era gateways that reject the server/discover probe with a bare HTTP 400 (no JSON-RPC envelope) now trigger the legacy initialize fallback (400/404/405/501), and legacy sessions omit the 2026-only MCP-Protocol-Version/Mcp-Method headers + _meta envelope; HTTP-error WP_Errors carry a 400-char body snippet. SSE-answering gateways (Envoy AI Gateway / Agent Router) no longer fail enumeration with "invalid JSON" — send_request() detects SSE via Content-Type or data: sniffing and parse_sse_payload() extracts the message event (dedicated wp_mcp_ai_mcp_app_empty_sse for empty streams).

• 🔎 Upwork job-link canonicalisation round-trip (PRs #6790 + #6793). The canonical marketplace form is restored to https://www.upwork.com/jobs/<slug>_~<jobId>/ (per vanooo/upwork-mcp's live-SPA scraper — #6790's /freelance-jobs/apply/ form still produced wrong links); login-walled SPA surfaces (/nx/…, /o/jobs/…, /r/…) are dropped as non-listings (except /nx/search/jobs/details/~<jobId> → bare-id form); tracking query strings dropped; MCP OAuth web login surfaces real errors and the callback route renders the friendly error page for auth-server denials.

• 🩹 PayHere/Flowhub guarded requires (PR #6801). A production install missing includes/class-wp-mcp-ai-payhere-client.php fatalled on every request during plugins_loaded — all 8 affected tool files now file_exists()-guard their dependency requires so is_available() self-reports unavailable, and the 7 Flowhub tools return canonical WP_Errors (wp_mcp_ai_flowhub_client_missing/wp_mcp_ai_flowhub_helper_missing) instead of fatals.

• ☁️ SaaS Controller 0.1.0 → 0.3.0 (PRs #6791 + #6797) + gateway express bump (#6787). 0.2.0 ships the production NV oOS Cloud worker (byte-identical port from addons/cloud-worker/src/, diff -q verified; compatibility_flags: ['nodejs_compat']; worker:dryrun fixed; jest + flat eslint repaired). 0.3.0 (Phase 12) folds Worker secrets + D1 schema into Plan/Apply (worker_secret rows resolve from the encrypted credential store at Apply time, values never in plans or audit logs; comment/PRAGMA-stripped idempotent CREATE TABLE IF NOT EXISTS via the D1 /raw endpoint) — the whole NV oOS Cloud deployment runs from WP-Admin. The mcp-wordpress gateway pins express@4.22.3, closing Dependabot alerts #897/#899/#900/#902 (0 vulnerabilities, 22/22 tests).

• 📦 Versioning — bumped to 1.1.88 across all version-bearing files. Pro addon: 1.1.88. Media Worker: v3.2.0 (unchanged). SaaS Controller: 0.1.0 → 0.3.0 (own track). nvoos-content-graph: 1.0.8 (unchanged). nvoos-content-graph-ai: 1.0.4 (unchanged). nvoos-content-graph-ai-platform: 2.0.0 (unchanged). nvoos-content-graph-pro: 1.0.0 (unchanged — three byte-identical in-feature ports: Upwork URL round-trip #6790/#6793, toolkit grant gating #6796). Checkout API: 0.1.2 (unchanged). Docs Hub addon: 0.5.1 (unchanged). Comic Reader addon: 0.5.0 (unchanged). Model catalog: v2026.09.22 (unchanged). Tool count: ~347 base + ~1,287 Pro (~1,634 total) — unchanged (no tools added or removed; live registry authoritative). Provider count: 15 chat providers (unchanged). Addon count: 28 (unchanged). Bundled skills: 75 base + 41 Pro (unchanged). Coding-time agent skills: 60 (unchanged — design-crm + design-elementor-mcp-connection reconciled in place). Stale build ZIPs removed: the 1.1.86 build set (30 files: 9 in build/ incl. 3 .sha256, 2 in build/optional-components/, 19 in build/toolkit-addons/).

v1.1.87 — September 27, 2026

Parity Suite, Image Identification & Outbound Booking

• 🔧 mcp-wordpress parity suite — 30 native base tools (PR #6777). Comment CRUD (list_comments/get_comment/create_comment/update_comment/delete_comment), user CRUD (list_users/create_user/update_user/delete_user), content/media/terms (get_post_revisions, get_term, delete_term, get_media, upload_media, update_media, delete_media), site settings + application passwords (get_site_settings/update_site_settings allowlist-only, list_application_passwords/create_application_password log-masked/delete_application_password), and a 9-tool SEO toolkit (seo_analyze_content through seo_keyword_research). Capability checks, multisite guards, chat-client restriction trait on sensitive write tools, and new comment_id/user_id/attachment_id ID-handoff contracts (gap matrix: docs/developer/mcp-wordpress-tool-parity.md).

• 🖼️ Non-LLM image identification ladder (PRs #6780 + #6785, Proposal 043). identify_image orchestrates a cheap-first deterministic ladder — WordPress metadata → pure-PHP dHash media lookup → classic Cloud Vision detection → deterministic layout description → optional reverse-image web search — and never calls a vision LLM (confidence + escalation hint). Five new base tools join the Media Generation preset (identify_image, get_image_metadata, find_similar_media, detect_image_content, describe_image_layout); two new Pro tools (ocr_image_classic tesseract-only OCR, search_similar_images Bing Visual Search / SerpApi Google Lens) sit on the shared WP_MCP_AI_Cloud_Vision_Client. Every external rung is key-gated and fails closed — missing credentials = skipped, never an error, never an HTTP request; SSRF guards on server-side fetches.

• 📅 Outbound appointment booking toolkit (PR #6786, Proposal 044). New Pro toolkit gated by enable_outbound_booking_toolkit: ICP list building (CSV → mcp_ai_lead, ICP-scored, sequence enrollment), an hourly cron engine over mcp_ai_sequence steps with send windows / daily caps / consent attestation, email + LinkedIn/Instagram DM channels behind a human approval board, the mcp_ai_oa_angle angle bank with champion/challenger A/B + weekly promotion, booking links + [nvoos_oa_booking] shortcode + a rate-limited honeypotted consent-gated public booking endpoint, a pipeline dashboard + Slack notifications + daily digest, and three new Pro tools (outbound_get_pipeline_stats, outbound_import_leads, outbound_manage_angle).

• 🌐 mcp-wordpress gateway addon (PR #6778). addons/mcp-wordpress-gateway/ — an auth-gated Streamable HTTP MCP server on pinned docdyhr/mcp-wordpress internals for Cloudways Velocity (timing-safe X-MCP-Token ≥32 chars with rotation overlap, 1 MB body cap, deny-wins MCP_TOOLS_ALLOW/MCP_TOOLS_DENY registration-time policy), deployed via subtree split to the nvoos-mcp-wordpress mirror.

• 🚦 Per-session budget warnings (PR #6776). Blocked-session messages report session state + the real reset path (Restricted Users / wp mcp-ai restrictions lift); the dormant 75% wp_mcp_ai_session_limit_approaching hook is wired to a one-shot warning on the next chat turn; new wp_mcp_ai_chat_messages filter on both chat paths; Token Manager reset semantics documented. The two untracked Elementor bundled skills are committed — the 75-skill base bundle is now genuinely tracked.

• 🧹 Restriction admin notice fixed (PR #6779). One queue entry per user (re-flag refreshes), render-time sweep of expired windows + unrestricted users + legacy dedupe, lift pruning, and a new count_active_users() distinct-user counter — the Pro command-center banner is fixed too.

• 🔎 Upwork search + in-place workflow editing (PR #6784). update_pro_schedule gains workflow_steps (replace semantics — no more delete-and-recreate); search_upwork_jobs gains exclude_keywords, an all sentinel, quoted-OR fallback skills, tier + budget parsing, and criteria echoing; upwork_job_discovery_scan preset carries academic-noise exclusions; byte-identical CG Pro port; the design-pro-schedule-manager + design-crm coding-time skills updated.

• 📦 Versioning — bumped to 1.1.87 across all version-bearing files. Pro addon: 1.1.87. Media Worker: v3.2.0 (unchanged). nvoos-content-graph: 1.0.8 (unchanged — explorer motion/UX + remote-source driver fixes landed in-window on its own track). nvoos-content-graph-ai: 1.0.4 (unchanged). nvoos-content-graph-ai-platform: 2.0.0 (unchanged). nvoos-content-graph-pro: 1.0.0 (unchanged — one byte-identical tool port in-window). Checkout API: 0.1.2 (unchanged). Docs Hub addon: 0.5.1 (unchanged). Comic Reader addon: 0.5.0 (unchanged). Model catalog: v2026.09.22 (unchanged — no model PRs in-window). Tool count: ~347 base + ~1,287 Pro (~1,634 total) — +35 base (30 parity + 5 image) and +5 Pro (2 image + 3 outbound); live count via WP_MCP_AI_Tool_Registry::get_tools() is authoritative. Provider count: 15 chat providers (unchanged). Addon count: 27 → 28 (new mcp-wordpress-gateway). Bundled skills: 75 base + 41 Pro (counts unchanged — now genuinely tracked). Coding-time agent skills: 60 (unchanged). Stale build ZIPs removed: the 1.1.85 build set (30 files: 9 in build/ incl. 3 .sha256, 2 in build/optional-components/, 19 in build/toolkit-addons/).

v1.1.86 — September 25, 2026

MCP Server Connections, Higgsfield Media Provider, Log Filters & Delivery Templates

• 🔌 MCP Apps as a Remote Sites connection type — PR #6761 (Proposal 041). New mcp_server connection type with AES-256-CBC-encrypted central credentials (including the mcp_oauth blob), a real JSON-RPC handshake Test Connection, tool discovery with persisted snapshots, restricted-host enforcement, and activity logging; auth mapping basic_auth/application_password → MCP basic (Elementor application passwords), custom_header → header, bearer, oauth. Reference mode — assistant entries carry a connection_ref resolved decrypt-on-use at chat time (credentials never written back to post meta); missing refs skip with error-status snapshots; imported bundles with missing refs auto-disable with a warning (wp_mcp_ai_mcp_apps_validate_imported_refs). Portability hardening — token/oauth_data redacted on export + stripped on import (opt-out filters); stored credentials survive overwrite imports; the metabox gains "Add from Remote Sites" reference rows + read-only "Managed in Remote Sites" rows. New coding-time skill design-elementor-mcp-connection.

• 🎬 Higgsfield video & image provider — PR #6772 (Proposal 042). Four new base tools: generate_higgsfield_video (five verified models — Cinema Studio 4.0, Seedance 2.5/2.0, Wan 3.0, Kling 3.0 — behind one model parameter with per-model payload mapping/clamping, image/video/audio references, cinematic controls), generate_higgsfield_image (SOUL V2 + SOUL Cinema workflows, batch 1|4, style_id gating), check_higgsfield_request, cancel_higgsfield_request. Shared WP_MCP_AI_Higgsfield_Client (two-part Key ID:SECRET auth, submit/status/cancel lifecycle, backoff+jitter polling 2s→10s, immediate download against the 7-day retention; settings → env → constants credential chain) + provider settings section + 480 s async-executor timeout override; check_video_status resolves async_* job IDs; lib/core dual-layer wrappers via oos-bridge. Also fixes the TypeSafe tool schemas + Pro coverage manifest and suppresses a benign Sora phpcs warning.

• 🔍 get_system_logs since/levels/search filters — PR #6768. Optional AND-combined since (relative "2h"/"30m"/"3d"/"45 minutes" or absolute ISO 8601 / Y-m-d H:i:s UTC; bare number = minutes; malformed → wp_mcp_ai_invalid_since), levels (critical/error/warning/notice/deprecated), and search (case-insensitive, 200-char cap, mb-safe) filters over the structured NV oOS buffers + file logs; responses carry a filters summary (resolved UTC cutoff) and per-file filtered_out counts; timestamp-less lines kept conservatively; parse_since() is the shared canonical parser; CG AI ports base-identical.

• 📨 Action-items template + smart excerpts — PR #6773. Scheduled digests no longer blind-trim the first 80 words: the new action_items delivery template (email + chat) sends only the actionable section with graceful fallbacks, and the summary excerpt prefers the response's own distillation ("Summary"/"TL;DR"/"Key points"/"Results"), then the action block, then centroid-ranked sentences (MEAD-style centrality × positional decay), with a lead trim as final fallback.

• 💰 Tool costs reach the final response label — PR #6771. New build_tool_cost_envelope() emits the top-level toolResult.cost shape (cost_usd/is_estimated/provider/model) on both the agentic loop and the SSE streaming path; the client's shared aggregateToolUsageBadgeData() aggregates it with legacy-shape fallbacks and carries tool model/provider into the badge; tool bubbles render the same usage/cost badges.

• 🩺 Environment status fixed — PR #6767. The always-on "no assistants published" warning and the never-firing default-assistant branch were an envelope-key mismatch (summarise_assistants() wraps under environment, build_warnings() read flat keys) — both repaired, base + CG port in sync; DeepSeek joins the provider warning maps; new plugin.default_provider_model resolves the effective per-provider model; the default assistant entry carries its provider/model meta.

• 📦 Versioning — bumped to 1.1.86 across all version-bearing files. Pro addon: 1.1.86. Media Worker: v3.2.0 (unchanged). nvoos-content-graph: 1.0.8 (unchanged). nvoos-content-graph-ai: 1.0.4 (unchanged — ZIP rebuilt in-window). nvoos-content-graph-ai-platform: 2.0.0 (unchanged). nvoos-content-graph-pro: 1.0.0 (unchanged — no port waves in-window). Checkout API: 0.1.2 (unchanged). Docs Hub addon: 0.5.1 (unchanged). Comic Reader addon: 0.5.0 (unchanged). Model catalog: v2026.09.22 (unchanged — no model PRs in-window). Tool count: ~312 base + ~1,282 Pro (~1,594 total) — +4 base (the Higgsfield quartet, #6772); the lib/core wrappers are the core registry's own tools and are not counted; live count via WP_MCP_AI_Tool_Registry::get_tools() is authoritative. Provider count: 15 chat providers (unchanged — Higgsfield is a media-generation provider, not a model-catalog provider). Addon count: 27. Bundled skills: 75 base + 41 Pro (unchanged). Coding-time agent skills: 59 → 60 (new design-elementor-mcp-connection, #6761). Stale build ZIPs removed: the 1.1.84 wp.org package set (6 files: 3 ZIPs + 3 .sha256).

v1.1.85 — September 24, 2026

MCP Apps Connection & Exposure Wave, Docs Hub 0.5.1, README Consolidation

• 🔌 MCP Apps connection diagnostics + correctness — PR #6753. Per-row Test Connection / Discover Tools buttons with inline results (negotiated protocol, handshake type, server info, session state, latency, live tool count, verbatim errors); persisted _wp_mcp_ai_mcp_app_status badge + tool-count chip; Test All. Basic auth end-to-end (raw user:pass auto-encoded or pre-encoded base64) with token masking — stored credentials never echoed into the metabox HTML, empty = keep. Mcp-Session-Id capture + echo; legacy-handshake fallback on -32601/-32600/session errors; JSON-RPC error decoding on HTTP 4xx; spec-compliant Accept; stdClass-params coercion fix; mcpServers JSON import; loopback detection with a PHP-FPM deadlock warning. Security Center → Network & Headers: MCP App Allowed Hosts (constant hard override → filter + saved setting merged).

• 🤝 Negotiated protocol header after session fallback — PR #6754. The client advertises the negotiated protocolVersion on post-initialize requests and suppresses the 2026-only _meta envelope once a legacy session is established — sessionful servers no longer reject tools/list. Test infra: PHPUnit 11 one-class-per-file discovery fixed (the #6753 registry/REST suites now genuinely execute).

• 🌉 Bridge tools reach the chat payload — PR #6755. New base wp_mcp_ai_chat_effective_tools filter seam in build_tools_payload() (after attention-based filtering, before the per-tool capability check; empty selection no longer short-circuits before the filters); Pro wp_mcp_ai_mcp_apps_expose_tools() appends the enabled apps' mcp_app_<label>_<tool> slugs; registry gains collect_remote_tools() + get_remote_tool_slugs().

• ⚡ In-process same-site bridge — PR #6756. Same-origin MCP endpoints dispatch via rest_do_request() — no outbound socket, no TLS handshake, no second PHP-FPM worker (ends the self-request TLS deadlock); outbound HTTP kept for remote hosts, unregistered routes, and the wp_mcp_ai_mcp_app_disable_inprocess_bridge filter.

• 📨 rest_post_dispatch parity — PR #6757. The in-process path re-applies the filter after rest_do_request() (mirroring serve_request()), so response-side session headers (e.g. EMCP's Mcp-Session-Id) reach the client and tool enumeration stops failing.

• 🧰 Bridge tools on every chat tool surface — PR #6758. The seam carries a third $assistant_id argument applied on handle_tools_list(), handle_tool_request(), execute_tool_call_internal(), and the list_mcp_tools catalogue filter; Pro exposure registers bridges in the local registry (idempotent, transient-cached discovery); rest_pre_dispatch registers bridges before REST arg validation; 60 s negative discovery cache; save_apps() invalidates the /tools REST list cache.

• 📚 Docs Hub 0.5.1 — PRs #6749/#6750/#6759. 0.5.0 went local-first by default (sources = ['uploads'], zero remote calls) with the GitHub importer as an explicit opt-in service (enable_remote_repos, off by default, server-side enforced); is_path_safe() symlink-escape hardening (0 blocking Plugin Check errors); 0.5.1 moves uploads to the slug-named nvoos-docs-hub/content/ folder with a one-time non-destructive migration of the legacy uploads/docs path.

• 📐 README anchors + consolidation — PRs #6751/#6752. Six VS16-fallback TOC anchors fixed; bin/validate-readme-anchors.py repaired to GitHub's real anchor rules (leading hyphens kept, no collapsing, emoji/VS16/ZWJ stripped, full-file scan) + CI enforcement on README changes; one ## 📜 Release History section keeps the 12 most recent releases in full plus a complete Previous Releases table (README 4,423 → 3,301 lines); the 12-entry maintenance rule codified in the README + the updates skill.

• 📦 Versioning — bumped to 1.1.85 across all version-bearing files. Pro addon: 1.1.85. Media Worker: v3.2.0 (unchanged). nvoos-content-graph: 1.0.8 (unchanged). nvoos-content-graph-ai: 1.0.4 (unchanged). nvoos-content-graph-ai-platform: 2.0.0 (unchanged). nvoos-content-graph-pro: 1.0.0 (unchanged — no port waves in-window). Checkout API: 0.1.2 (unchanged). Docs Hub addon: 0.4.7 → 0.5.1 (#6749 → 0.5.0, #6750 hardening, #6759 → 0.5.1). Comic Reader addon: 0.5.0 (unchanged). Model catalog: v2026.09.22 (unchanged — no model PRs in-window). Tool count: ~308 base + ~1,282 Pro (~1,590 total) — unchanged, no static registrations in-window (the MCP App bridge slugs are dynamic chat-time registrations); live count via WP_MCP_AI_Tool_Registry::get_tools() is authoritative. Provider count: 15 chat providers (unchanged). Addon count: 27. Bundled skills: 75 base + 41 Pro (unchanged). Coding-time agent skills: 59 (unchanged — the updates skill gained the README-anchor guardrail + 12-entry maintenance rule, #6751/#6752). Stale build ZIPs removed: the 1.1.83 set (30 files: 9 in build/ incl. 3 .sha256, 2 in build/optional-components/, 19 in build/toolkit-addons/) + the superseded docs-hub 0.4.7 and 0.5.0 ZIPs (0.5.1 is current).

v1.1.84 — September 22, 2026

TypeSafe Jev Enhancement Wave: Fidelity, Guardrails & Decision Tools

• 🔮 API fidelity (Phase 0, PR #6747) — noul criteria + structured EntryType fields with a recursive two-gate sanitisation walk; bounded 429/5xx retries honouring retry-after on the native client + the OpenRouter decisions bridge (4xx/transport never retried; the bridge defaults to typesafe/jev-1.13); an opt-in advisory decision cache (enable_typesafe_cache, cached: true + zeroed usage on hits); typesafe_endpoint override; jev-preview alias (catalog + settings + list_models()); min_confidence, weights, advisory token warnings, and usage aliases on typesafe_decide.

• 🛡️ Base typesafe_guardrail (Phase 1, PR #6747) — one noul question per hazard category → advisory pass/review/block verdicts; ai_ml preset + coverage manifest + tool-status. New bundled skill mcp-ai-wpoos-jev-decisions (bundled skills 74 → 75 base).

• 🧩 Pro Jev integrations (Phase 2, PR #6747) — opt-in fail-open guest-chat guardrail (enable_jev_guest_guardrail on the Layer I wp_mcp_ai_pre_chat_message filter); advisory citation checking on generate_research_report/research_eca; three new manage_options-gated tools — typesafe_rerank, typesafe_eval (+ WP_MCP_AI_Pro_Jev_Eval), typesafe_skill_select.

• ✅ typesafe_decide capability alignment (PR #6745) — declared manage_options matches the enforced gate (metadata-only, CI-pinned).

• 📘 Proposal + plan 040 (PR #6746) — six API-fidelity fixes, official TypeSafe patterns, cost/reach workstreams; extraction tools, the CG port cluster, and NV Cloud passthrough deferred.

• 📦 Versioning — bumped to 1.1.84 across all version-bearing files. Pro addon: 1.1.84. Media Worker: v3.2.0 (unchanged). nvoos-content-graph: 1.0.8 (unchanged). nvoos-content-graph-ai: 1.0.4 (unchanged). nvoos-content-graph-ai-platform: 2.0.0 (unchanged). nvoos-content-graph-pro: 1.0.0 (unchanged — no port waves in-window). Checkout API: 0.1.2 (unchanged). Docs Hub addon: 0.4.7 (unchanged). Comic Reader addon: 0.5.0 (unchanged). Model catalog: v2026.09.22 (+1 jev-preview decision entry, #6747). Tool count: ~308 base + ~1,282 Pro (~1,590 total) — +1 base (typesafe_guardrail) +3 Pro (typesafe_rerank, typesafe_eval, typesafe_skill_select), #6747; live count via WP_MCP_AI_Tool_Registry::get_tools() is authoritative. Provider count: 15 chat providers (TypeSafe Jev remains decision-only, separate from chat). Addon count: 27. Bundled skills: 75 base + 41 Pro (+1 mcp-ai-wpoos-jev-decisions). Coding-time agent skills: 59 (unchanged). Stale build ZIPs: none removed this pass — the 1.1.83 wp.org package set is retained as current; removal moves to the next catch-up after the 1.1.84 packages build.

v1.1.83 — September 21, 2026

Tool Guidance Everywhere, Jev Decisions, Assistant Builder, ID-Handoff Contracts

• 🧠 TypeSafe Jev Decision Provider + Pro Integrations — PR #6728. Jev joins as a first-class decision provider (typed choice/score/noul over state; 70–500 ms; $0.042/M input, output free) via a new decision-client contract, the native TypeSafe client, the OpenRouter Decisions bridge, and the new base tool typesafe_decide (canonical envelope, adversarial-state caveat, manage_options-gated). Pro gains the fail-open Jev classifier (cascade routing via jev_routing on the Parallel Model Dispatcher) and an opt-in research source filter; fixes the pre-existing dispatcher chat_completion() bug.

• 🛠️ "The Assistant Builder" Meta-Assistant — PR #6727. Seeded on activation (roster 6 → 7): a seven-phase build workflow + 10-component prompt framework for designing, building, and verifying other assistants; one-shot backfill for existing installs.

• 🔗 P3 ID-Handoff Data Contracts — PRs #6729–#6739. Every ID-bearing tool family (post, cron, term, assistant, vector store, batch, Pro schedule, toolkit_cpt, medical record, plan, calendar, WPCode, session, member, webchat room) declares produces/consumes contracts, enforced by permanent manifest-driven honesty + round-trip suites; in-wave fixes for format_code_prettier envelopes and the webchat log_activity() latent fatal.

• 🔧 Usage Monitor Saves Again — PR #6726. The dashboard save handler now applies the monitor bridge filter (raw input, pre-sanitize), so the toggle and limits persist and sites flipped "Disabled" by the pre-#6632 merge bug can re-enable.

• 🐞 Webchat SQL + Guidance Close-Out — PRs #6738, #6740. get_webchat_messages rebuilds its queries with explicit placeholders (root cause of the phpcs warnings); the last three webchat tools and the CG Pro member mirrors gain usage guidance; the CG interface copy gains the guidance interface (standalone-resolution fatal fix).

• 🧭 Tool Description Engineering — PRs #6686, #6695, #6687–#6723. Model-facing usage guidance on every base+Pro tool class (~1,487 tools; 1,584/1,584 files clean): a guidance interface assembles a [Usage: …] suffix on the model-facing payload, legacy classes opt in through the wrapper, and the sniff is enforced at severity 5. Opt-in adaptive tool cap + lazy schema loading (tool_slug, include_schemas).

• 🛡️ Pro Bootstrap + Telegram + Gmail/Skill/OKF Hardening — PR #6677. Partial Pro deploys degrade to an admin notice instead of a site-wide fatal; Telegram messages over 4,096 chars auto-chunk; connection_id: "settings" resolves to the settings fallback; skill/OKF errors append the available options.

• 🔍 Upwork & Workflow Delivery — PRs #6678, #6679, #6680, #6682, #6684. Mode + credential gating, category-page dropping, always-on broad second pass, sort/location args; workflow deliveries ship the full 50-item result set with URLs/budget/recency as a single properly numbered list; steps render as a compact execution log.

• 🧪 Playground Ollama Demo — PR #6683. Permalink seed fix ends the fresh-install landing 404; local npx is the primary test path; capture harness rewritten (REST-index wait + cookie jar).

• 🔒 npm Advisories — PR #6681. adm-zip 0.6.1, js-yaml 4.3.2, colord 2.10.0 across five lockfile trees.

• 📏 Canonical Envelope Migrations — PRs #6689, #6737. Five regulatory tools and format_code_prettier move to the canonical WP_Error envelope.

• 📦 Versioning — bumped to 1.1.83 across all version-bearing files. Pro addon: 1.1.83. Media Worker: v3.2.0 (unchanged). nvoos-content-graph: 1.0.8 (unchanged; ZIP rebuilt in-window). nvoos-content-graph-ai: 1.0.4 (unchanged; ZIP rebuilt in-window). nvoos-content-graph-ai-platform: 2.0.0 (unchanged). nvoos-content-graph-pro: 1.0.0 (unchanged — mirror patches only, no port waves). Checkout API: 0.1.2 (unchanged). Docs Hub addon: 0.4.7 (unchanged). Comic Reader addon: 0.5.0 (unchanged). Model catalog: v2026.09.21 (+3 Jev decision entries — jev-1.13.0, jev-latest, OpenRouter typesafe/jev-1.13, #6728). Tool count: ~307 base + ~1,279 Pro (~1,586 total) — +1 base (typesafe_decide, #6728); the P3 ID-handoff waves are contract annotations on existing tools; live count via WP_MCP_AI_Tool_Registry::get_tools() is authoritative. Provider count: 15 chat providers (TypeSafe Jev joins as a decision-only provider, separate from chat). Addon count: 27. Bundled skills: 74 base + 41 Pro. Coding-time agent skills: 59 (unchanged — no new skills; the test-suite skill gained patterns 49–50 and the ecosystem-port skill gained the CG interface-port rule, #6742). Stale build ZIPs removed: the 1.1.81 set (30 files), then the 1.1.82 set (30 files) after the 1.1.83 wp.org packages rebuilt.

v1.1.82 — September 18, 2026

WordPress Playground Demos, Pro SPA Fixes, Token-Tracking & Delivery Hardening

• 🎮 One-Click Playground Demos — PRs #6662, #6663, #6666, #6670, #6673, #6674. Content Graph "Project Asteria" (seeded universe, deterministic build, 49 nodes / 255 edges) and NV oOS Complete × local Ollama (pre-wired provider, Oma assistant, Test Lab page) blueprints; generator auto-discovers the newest bundle ZIP; build workflow regenerates the blueprint on every build; README demo button + docs/user-guides/playground-demo.md walkthrough (#6671).

• 🧰 Pro SPA: cron_monitor flag + model-store seeding — PRs #6665, #6672. [nvoos_pro_spa cron_monitor="0"] no-ops the blocking SSE cron-status stream + REST poll; embedded mode seeds the model store from the assistant's real config instead of hardcoded gpt-4o.

• 🛠️ Token Tracking Table Hardened — PR #6669. Verify-then-version + hourly retry backoff + quiet failure + graceful reads for SQLite-backed environments; ported 1:1 to nvoos-content-graph-ai (ecosystem matrix 13/13).

• ✂️ Result Delivery Dedupe + Metadata Redaction — PR #6661. delivery_safe_data() strips the duplicated response copy and assistant_id/is_agentic before rendering; summary/SMS prefix dedupe; no empty ## Details.

• 📡 [ollama_status] Banner Fixed — PR #6668. Footer-enqueued checker JS replaces the texturize-mangled inline script (&& → &&).

• 🛡️ Portability Coverage Guards Repaired — PR #6645. Preset + 9 AJAX tests + regenerated manifests; CI run 35096081494's 4 guard failures closed.

• 📚 Skill #59 + Updates Track C — PRs #6664, #6656. mcp-ai-wpoos-playground-demos codifies the blueprint playbook; the updates skill gains the PR deferred-item sweep.

• 🏥 Docs Hub 0.4.7 — PRs #6659, #6667. Third wp.org reviewer pass; 0 blocking Plugin Check errors.

• 📦 Versioning — bumped to 1.1.82 across all version-bearing files. Pro addon: 1.1.82. Media Worker: v3.2.0 (unchanged). nvoos-content-graph: 1.0.8 (unchanged; ZIP built in-window). nvoos-content-graph-ai: 1.0.4 (unchanged; ZIP built in-window). nvoos-content-graph-ai-platform: 2.0.0 (unchanged). nvoos-content-graph-pro: 1.0.0 (unchanged — no port waves in-window). Checkout API: 0.1.2 (unchanged). Docs Hub addon: 0.4.7 (was 0.4.6). Comic Reader addon: 0.5.0 (unchanged). Model catalog: v2026.09.10 (unchanged). Tool count: ~306 base + ~1,279 Pro (~1,585 total) — unchanged, no tool registrations in-window; live count via WP_MCP_AI_Tool_Registry::get_tools() is authoritative. Provider count: 15. Addon count: 27. Bundled skills: 74 base + 41 Pro. Coding-time agent skills: 59 (+1 — mcp-ai-wpoos-playground-demos). Stale build ZIPs removed: the 1.1.80 set (30 files) + the superseded docs-hub 0.4.6 ZIP.

v1.1.81 — September 17, 2026

Shopify UCP Tool Routing, FlowHub Connections, JobNavigator CRM, OpenTerminal Financial Resilience

• 🛍️ Shopify UCP Mode-Aware Tools + Image Cards — PRs #6634, #6638. Live UCP queries for shopify_products/shopify_catalog on storefront/global connections (no caching, live: true), actionable hints from admin-only tools, UCP passthrough + clamps, tools/list handshake validation, and image cards (images[] + markdown, 10-card cap) on every product-returning path. Byte-identical CG Pro ports with dual-matrix suites.

• 🔌 FlowHub Connection Resolution + Proxy — PRs #6635, #6637. Shared resolver chain reads Remote Sites connections (explicit ID, settings, sync connections, first enabled); live requests honor the connection proxy. New base helper WP_MCP_AI_FlowHub_Connection_Helper.

• 🧩 JobNavigator CRM + Gmail Poller — PRs #6636, #6640, #6641. Five new CRM tools (bulk stage moves, reply recording, handover, pipeline digest, tracked links), stage history, lead dedup, reply signals; cron-driven Gmail reply classification with sentiment + optional stage advancement; digest scheduling recipe for Workflow Builder + Pro Schedule Manager. design-crm skill updated.

• 💹 OpenTerminal Financial Toolkit — PR #6639. Eight new tools (screener, macro, economic/earnings calendars, options, crypto, portfolio ledger, price alerts), fallback chains + SWR caching, keyless auth, technical indicators, news de-dup. tool-status.txt +8.

• ✉️ Multi-Recipient Result Delivery Email — PR #6643. Comma/semicolon/whitespace lists, normalized on save, sanitized + deduped at the boundary, fanned out via Nodemailer + wp_mail.

• 📦 Versioning — bumped to 1.1.81 across all version-bearing files. Pro addon: 1.1.81. Media Worker: v3.2.0 (unchanged). nvoos-content-graph: 1.0.8 (unchanged). nvoos-content-graph-ai: 1.0.4 (unchanged). nvoos-content-graph-ai-platform: 2.0.0 (unchanged). nvoos-content-graph-pro: 1.0.0 (unchanged — byte-identical port batches only). Checkout API: 0.1.2 (unchanged). Docs Hub addon: 0.4.6 (unchanged). Comic Reader addon: 0.5.0 (unchanged). Model catalog: v2026.09.10 (unchanged). Tool count: ~306 base + ~1,279 Pro (~1,585 total); live count via WP_MCP_AI_Tool_Registry::get_tools() is authoritative — +13 Pro (#6636 +5, #6639 +8). Provider count: 15. Addon count: 27. Bundled skills: 74 base + 41 Pro. Coding-time agent skills: 58 (unchanged). Stale build ZIPs removed: the 1.1.79 set (30 files) + superseded docs-hub 0.4.3/0.4.4/0.4.5 ZIPs.

v1.1.80 — September 15, 2026

Assistant Portability, Shopify UCP Catalog, Security Usage Monitor, WP-CLI Repair

• 📦 Assistant Export/Import Everywhere — PR #6628. One engine, every surface: WP-CLI (export|import, legacy-compatible), REST (POST /mcp-ai/v1/assistants/export|import), an admin Import/Export page, and tools (export_assistant, import_assistant, duplicate_assistant, Pro export_assistant_blueprint). Credential hashes never leave the site and are stripped on import. Bundle spec: docs/assistant-import-export.md; skill: .agents/skills/mcp-ai-wpoos-assistant-portability/.

• 🛡️ Security Center Usage Monitor — PR #6632. New usage_monitor sub-tab: triage log, status cards, shutdown recovery, editable config, REST clear routes; the admin notice deep-links and shows the latest violation. Monitor sanitize-clobber bug fixed; malformed patterns hardened.

• 🛍️ Shopify Catalog Trilogy — PRs #6623, #6624, #6630. REST Catalog 401s fixed (60-min token cap, scope validation, purge-and-retry) and the JetEngine sync gate unified with System Status; two keyless UCP modes (Storefront + Global Catalog) replace the deprecated REST API on Pro and CG Pro, with the public UCP agent-profile route and byte-identical ports.

• 💻 WP-CLI Repairs + Streaming — PRs #6625, #6626. PHP 8+ fatals gone from provider list/chat and every base-class command; chat --stream streams natively (cURL SSE) or simulates chunks, honoring the shared streaming filters. Live-validated in the Design Stack.

• 🟢 Remote Sites & OKF — PRs #6622, #6631. WhatsApp webhook self-tests (verification/signature/subscription) on the connection edit form; OKF editor saves keep their bundle/concept context.

• 📚 Skills — PRs #6621, #6627, #6629. Docs Hub syntax/anchor color fixes; agent skills corrected to the verified plugin surface; new design-brand-assistant-provisioning skill; brand template phpcs-clean.

• 📦 Versioning — bumped to 1.1.80 across all version-bearing files. Pro addon: 1.1.80. Media Worker: v3.2.0 (unchanged). nvoos-content-graph: 1.0.8 (unchanged). nvoos-content-graph-ai: 1.0.4 (unchanged). nvoos-content-graph-ai-platform: 2.0.0 (unchanged). nvoos-content-graph-pro: 1.0.0 (unchanged — byte-identical port patches only). Checkout API: 0.1.2 (unchanged). Docs Hub addon: 0.4.6 (unchanged — CSS fix, no bump). Comic Reader addon: 0.5.0 (unchanged). Model catalog: v2026.09.10 (unchanged — no model PRs in-window). Tool count: ~306 base + ~1,266 Pro (~1,572 total); live count via WP_MCP_AI_Tool_Registry::get_tools() is authoritative — +3 base +1 Pro from #6628). Provider count: 15. Addon count: 27. Bundled skills: 74 base + 41 Pro. Coding-time agent skills: 58 (new design-brand-assistant-provisioning + mcp-ai-wpoos-assistant-portability). Stale 1.1.78 build ZIPs removed (30 files).

📋 Previous Releases

For full details on all releases, see CHANGELOG.md.

🚀 Features

Note: Some features require third-party plugins (WooCommerce, JetEngine, Elementor, etc.). See 🔌 What You Lose Without Third-Party Plugins for details.

Assistant & conversation tools

• 🧠 Create AI Assistants via a custom post type (mcp_ai_assistant)

• 👔 Professional & Team Templates - Deploy assistants from ~311 pre-built profession templates spanning 12 industry categories, or create entire teams of specialists with one click. Includes backend testing for professions, teams, and assistants before public deployment.

• 🚀 Getting Started Wizard - Guided 4-step onboarding (/wp-admin/admin.php?page=wp-mcp-ai-getting-started) that walks new users through provider setup and use-case selection. Selecting a preset (Content Creator, Customer Support, E-commerce, SEO & Research, Developer Copilot, Media & Creative Studio, Site Administrator, or General Purpose) seeds a fully-configured assistant with tools, system prompt, and tuned temperature — ready to use immediately.【F:includes/admin/class-wp-mcp-ai-onboarding-wizard.php†L1-L53】【F:assets/js/onboarding-wizard.js†L1-L303】

• 🔄 Automatic synchronization to JetEngine Custom Content Types when available (CPT → CCT)

• 💬 Chat interface via [mcp_ai_chat assistant="ID"]

• 🧰 Per-assistant defaults for model, temperature, system prompt, and knowledge attachments with permission-aware download URLs

• ⚡ Build reusable prompt shortcuts with optional tool targeting and inline descriptions so operators can trigger common tasks with one click.【F:includes/assistants/class-wp-mcp-ai-assistant-cpt.php†L893-L1048】【F:includes/class-wp-mcp-ai-shortcode.php†L430-L693】【F:assets/js/chat.js†L600-L666】

• 🧊 Elementor widgets for embedding chat surfaces, onboarding content, and MCP dashboards inside Elementor

Language routing & knowledge management

• 🔁 Route conversations through OpenAI or Gemini using a provider-aware language model router

• 🎯 Enhanced Gemini API integration: list models dynamically, count tokens for budget management, create embeddings for RAG/semantic search, and streaming support for real-time responses【F:docs/reference/api/gemini/gemini-api-enhancements.md†L1-L100】

• 🧠 Assistant knowledge base management with Media Library files and optional vector store IDs

• 📚 OKF (Open Knowledge Format v0.1) engine with 6 MCP tools for curated, deterministic knowledge with cross-link navigation — complementary to vector/RAG stores

• 🔎 Perform lightweight web searches (DuckDuckGo or Brave) without leaving the assistant conversation

• 🌐 Crawl4AI job runner tool for large-scale content gathering workflows

Media generation & transcription

• 🔊 Generate speech audio via OpenAI's Text-to-Speech API and save the result to the Media Library

• 🎵 Generate instrumental music using Google Gemini Lyria with controls for genre, mood, tempo, and instrumentation

• 🎨 Generate on-brand imagery with OpenAI's Images API, honouring the configured response format (including GPT-Image-1's url responses) and storing the files as WordPress attachments

• 🖼️ Generate images with Cloudflare Workers AI using Stable Diffusion, Flux-2 Dev, Leonardo AI (Lucid Origin, Phoenix 1.0), and other text-to-image models with configurable dimensions and generation parameters

• 🖼️ Vectorize raster images (PNG, JPEG, WebP, GIF) to SVG format using @neplex/vectorizer with configurable quality settings - perfect for logos and icons

• 🎨 Comprehensive graphic editing with Graphic Editor Plus combining local operations (logo overlay, smart resize) and AI-powered features (style transfer, background removal, enhancement)

• 🏗️ Pro: Generate professional architectural drawings (floor plans, elevations, sections) with building codes, dimensions, and material specifications - designed for construction professionals

• 🎧 Transcribe or translate uploaded audio with OpenAI's speech-to-text endpoints

Commerce & finance workflows

• 🛍 WooCommerce-aware tools (fetch orders or products, requires WooCommerce)

• 📊 Finance-ready QuickBooks Online reporting tool for surfacing Profit and Loss, Balance Sheet, and other statements inside assistant conversations【F:includes/tools/class-wp-mcp-ai-tool-get-quickbooks-report.php†L15-L214】【F:includes/admin/class-wp-mcp-ai-admin-settings.php†L906-L955】

• 🖥️ Pro: QuickBooks Desktop sync via QODBC relay API — connect to QuickBooks Desktop through a Windows relay server for data synchronization

• 🛒 Pro: Shopify integration with auto-resolved connections — connection_id auto-resolved from assistant context, covering products, orders, customers, inventory, and catalog tools

• 🚗 Pro: Vehicle estimation tools — VIN decode (NHTSA vPIC), image-to-repair-estimate pipeline, and car wash package pricing engine (always available)

• 📸 Pro: Listing image download tools — bulk-download Google Maps, Facebook, and Instagram business listing images into the Media Library or ZIP

Slash Commands & Workflow Automation ⭐ NEW

• ⚡ 8 Core Commands: /help, /next-task, /ship, /clean-content, /optimize-perf, /sync-docs, /workflow - Command-line style interface for content management

• 🔄 Workflow Orchestrator: Multi-step workflow execution with state management, conditional logic, and human-in-the-loop checkpoints

• 🛠️ 21 Pro Toolkit Commands: Specialized commands for E-commerce (6), Social Media (6), and Video Production (6) toolkits

• 🎯 7 Automated Workflows: Pre-built workflow templates for abandoned cart recovery, social media campaigns, video marketing, inventory management, and more

• 🔐 Security: Capability-based authorization, rate limiting, comprehensive audit logging

• 💡 Integration: JavaScript autocomplete, REST API endpoint, WP-CLI support

• Documentation → | Pro Commands →

Chat Channels & Messaging Integration ⭐ NEW

• 💬 Chat Channels Toolkit (47 Tools): Integrate with 11 platforms - Telegram, WhatsApp, Slack, Discord, Microsoft Teams, Facebook Messenger, Apple Messages for Business, Google Chat/Spaces, Twitter/X, Office 365 (Outlook + OneDrive), iCloud Drive

• 📧 Office 365 Integration ⭐ NEW: Send and retrieve Outlook mail, list/download/upload OneDrive files via Microsoft Graph API (5 tools)

• ☁️ iCloud Drive Integration ⭐ NEW: List, download, and upload iCloud Drive files via a configurable gateway service (3 tools)

• 🌐 Unified Broadcasting: Send messages across multiple platforms simultaneously with unified_channel_broadcast tool

• 🏠 WebChat Rooms: Custom post type for real-time collaborative chat rooms with AI assistant assignment

• 📝 Message Persistence: JetEngine CCT integration for permanent message history

• 🔊 WebRTC Support: Self-hosted WebRTC signaling via WordPress REST API for voice/video

• 🤖 AI-Powered Rooms: Assign dedicated assistants to chat rooms for automated support

• Chat Channels Guide → | WebChat Setup →

Communications & outreach

• ✉️ Mailjet-powered outbound email automation with granular capability enforcement and sender defaults configurable in the MCP settings.【F:includes/tools/class-wp-mcp-ai-tool-send-mailjet-email.php†L19-L405】【F:includes/admin/class-wp-mcp-ai-admin-settings.php†L1008-L1054】

• 📅 Google Workspace automations for creating calendar events and searching connected Gmail inboxes directly from assistant workflows.【F:includes/tools/class-wp-mcp-ai-tool-create-google-calendar-event.php†L1-L200】【F:includes/tools/class-wp-mcp-ai-tool-search-gmail.php†L1-L200】

• 🧾 JetFormBuilder orchestration for listing forms, reviewing submissions, and proxying REST calls on behalf of assistants (requires JetFormBuilder)

• 📚 JetEngine REST route reference tool for surfacing endpoint metadata inside AI workflows

• 🧱 Ready for extension with ChatKit integration

Integrations, security & controls

• 🔧 Tool Registry for registering PHP functions callable by the AI

• ⚙️ JetEngine integration for dynamic content queries (requires JetEngine)

• 🔌 JetEngine 3.8 MCP Server Bridge ⭐ NEW - JSON-RPC 2.0 client bridges NV oOS into JetEngine's native MCP Server with 7 new Pro tools for CPT/taxonomy/meta field creation, relations management, site context grounding, and prompt template access. MCP-first dispatch with REST v2 fallback.

• 🤝 Agent-to-Agent (A2A) Protocol ⭐ NEW - Full A2A protocol making NV oOS assistants discoverable and interoperable with any A2A-compliant agent. /.well-known/agent.json discovery, JSON-RPC 2.0 server with task state machine, A2A client for remote agent delegation, push notification webhooks.

• 📊 Agent Command Center ⭐ NEW - Unified agent management dashboard with 7 tabs: Overview (KPI cards, live status), Activity Log, Active Tasks, Approvals (human-in-the-loop), Analytics (Chart.js with real per-agent metrics), Uptime & Health, and Strategy (efficiency scoring with recommendations).

• 💬 Floating Chat Bubble ⭐ NEW - Configurable floating chat bubble widget for Elementor and Gutenberg. 4 position variants, 3 sizes, bounce/pulse animations, dark mode, WCAG focus states, sessionStorage persistence.

• 🧷 Granular control over allowed attachment MIME types for chat uploads

• 🔐 Secure REST API endpoints

• 🔑 Root Security Key - Optional wp-config.php constant that can be enabled during emergency shutdown to require authentication before re-initializing the plugin. Provides an additional layer of protection against unauthorized reactivation after security incidents.【F:docs/features/security/root-security-key.md†L1-L511】【F:includes/class-wp-mcp-ai-root-security-key.php†L1-L360】

• 🛰 Assistant directory endpoint that advertises MCP tool/resource capabilities and negotiates Server-Sent Events handshakes for clients such as LM Studio or Claude Desktop.【F:includes/class-wp-mcp-ai-rest.php†L520-L666】【F:includes/class-wp-mcp-ai-rest.php†L1690-L1772】

• 📝 Full JSON-RPC 2.0 MCP endpoint (/mcp) for standards-compliant remote client communication

• 🔑 Configurable API credentials and defaults for OpenAI, Gemini, and Anthropic (with subscription tier support for Team/Enterprise plans and custom base URLs)

• 🤖 ChatGPT’s connector beta currently requires an Auth0 tenant; the plugin’s assistant credentials are compatible with LM Studio, Claude, and other MCP clients that support bearer headers directly.【F:docs/reference/api/mcp-server-authentication.md†L22-L46】

• 🌐 Mesh networking for distributed compute pooling across multiple WordPress sites. Server-to-server architecture enables anonymous and authenticated users to benefit from shared AI resources, budget pooling, and workload distribution across 100+ trusted peer sites. Backend assistants coordinate mesh operations via secure inter-site keys while maintaining user attribution and audit trails for compliance.【F:docs/features/federation/mesh-compute-pooling.md†L1-L615】【F:includes/tools/class-wp-mcp-ai-tool-query-remote-site.php†L1-L237】

• 🔗 Federation & Discovery - Decentralized AI capability network allowing WordPress sites to publish their capabilities via well-known endpoints (/.well-known/ai-peer) and discover peer sites through directory services. Supports peer registration, health verification, search & ranking by capability/region/policy, and automatic cron-based health monitoring. Enable federation to join the network or run your own directory service for private peer discovery.【F:docs/features/federation/federation-discovery.md†L1-L511】【F:FEDERATION-IMPLEMENTATION-SUMMARY.md†L1-L381】

• 🧾 Optional logging of chat interactions, tool executions, and API errors

• 🧮 Built-in per-user usage tracking for provider/model billing summaries

• 🧩 Developer hooks and filters for integrating custom behaviours

• ⏱ Per-site request timeout control with sensible minimum enforcement

• 🗑 Toggleable uninstall cleanup to purge stored assistants and settings automatically

Performance & reliability

• ⚡ Client-side message bundling (800ms window) to reduce API calls and server load【F:docs/user-guides/chat/message-bundling-feature.md†L1-L80】

• 🎯 Intelligent token overflow handling with automatic model switching (gpt-4.1-mini → Gemini 2.0 Flash)【F:docs/features/tools/presets/high-token-tool-handling.md†L1-L80】

• 📡 Server-Sent Events (SSE) support for real-time streaming responses and job notifications【F:docs/features/streaming/ENABLE-SSE-STREAMING.md†L1-L100】

• 🌊 Real-time job status updates via SSE streaming and webhook notifications for async operations【F:docs/features/async-jobs/job-notification-system.md†L1-L100】

• 🔧 Symfony Process Component - Modern process execution framework replacing direct exec() calls in Pro addon tools for enhanced security, timeout management, and error handling【F:includes/services/class-wp-mcp-ai-process-service.php†L1-L220】【F:docs/history/2025/implementations/symfony-phases/SYMFONY_PHASE2B_PROCESS_INTEGRATION.md†L1-L100】

• 🔄 Server-side WP-Cron polling for long-running tasks (Crawl4AI, background jobs)

• 💾 Chat history persistence with localStorage (24h) and optional JetEngine CCT storage【F:docs/user-guides/chat/chat-history-persistence.md†L1-L50】

• ⚙️ Optimized settings page with external CSS stylesheet (240 lines added to admin-settings.css) and request-level caching for improved admin performance【F:assets/css/admin-settings.css†L1-L984】【F:includes/admin/class-wp-mcp-ai-admin-settings.php†L27-L32】

Settings Management ⭐ NEW

• 🔧 Robust Settings System - 7-step save process with automatic backups, validation, and cache management ensures settings persist correctly across all tabs and subtabs【F:includes/admin/class-wp-mcp-ai-settings-dashboard.php†L262-L410】

• 🔍 Health Check - Run 6 diagnostic checks to verify settings integrity, provider configuration, and system status with GOOD/WARNING/CRITICAL status indicators【F:includes/admin/sections/class-wp-mcp-ai-section-advanced.php†L1500-L1650】

• 💾 Export Settings - Download all plugin settings as timestamped JSON files for backup or migration to other sites【F:docs/admin-guides/settings-management.md†L40-L80】

• 📤 Import Settings - Upload and validate settings from previously exported backups with automatic pre-import backup and 5-step validation【F:docs/admin-guides/settings-management.md†L85-L135】

• 🗑️ Clear Cache - One-click clearing of static cache, object cache, and transients when settings changes don't take effect【F:docs/admin-guides/settings-management.md†L140-L165】

• ↩️ Reset to Defaults - Safely reset all settings to default values with automatic backup before reset【F:docs/admin-guides/settings-management.md†L170-L200】

• 🔒 Security - File size validation (max 5MB), MIME type checking, JSON validation, and comprehensive input sanitization【F:includes/admin/class-wp-mcp-ai-settings-dashboard.php†L970-L1030】

• 📊 Automatic Backups - Every save operation creates a timestamped backup (keeps last 5) for emergency recovery【F:includes/admin/class-wp-mcp-ai-settings-dashboard.php†L285-L295】

• 🛡️ Data Protection - 3-layer protection (section filtering, merge strategy, sensitive key filtering) prevents accidental data loss when saving from tabs/subtabs【F:docs/admin-guides/settings-management.md†L230-L280】

• 📖 Pro Toolkits - Enable and configure 8 specialized Pro toolkits (650+ tools) including Project Management, Document Generation, Health & Wellness, CRE Debt & Securitization, and more【F:docs/admin-guides/pro-settings-toolkits.md†L1-L650】

➡️ Complete Documentation: Settings Management Guide | Quick Reference | Visual UI Guide | Pro Toolkits Guide

🧠 Memory & Tool Stack Overview

Model defaults

Global settings capture the default provider, model, and timeout used when assistants are created, ensuring every conversation inherits stable generation behaviour until explicitly overridden. These defaults ship with sensible values for OpenAI and Gemini out of the box and can be tailored from the NV oOS settings screen.【F:includes/admin/class-wp-mcp-ai-admin-settings.php†L36-L77】

Base knowledge

Each assistant can preload Media Library files and optionally link to an external vector store, giving the model persistent project context before a chat begins. Editors manage these knowledge sources from the assistant post type via the “Base Knowledge” meta box, which supports multiple attachments and vector store identifiers.【F:includes/assistants/class-wp-mcp-ai-assistant-cpt.php†L892-L1002】

Available tools

The tool registry boots with a curated catalogue of content, commerce, automation, and research utilities, then exposes hooks so developers can register their own providers. During initialisation the registry loads each bundled tool class—ranging from JetEngine accessors to Crawl4AI jobs and Mailjet automations—and makes them callable within conversations.【F:includes/class-wp-mcp-ai-tool-registry.php†L74-L220】

Chat-client Memory Drawer

The chat front-end exposes a persistent Memory Drawer (assets/js/chat-memory-drawer.js) with three tabs:

• Memories — browse, pin, and delete stored context items; 🧠 badge auto-appears on any assistant message that used a memory tool.

• Scope — set the active wing/room scope for subsequent memory operations in the current session.

• Audit — lazy-loaded audit trail from WP_MCP_AI_REST_Chat_Memory_Controller::audit().

The drawer is wired to the REST proxy at /mcp-ai/v1/chat-memory/ and receives real-time updates via the memory_event SSE frame emitted by the agentic loop. Pagehide auto-capture stores the session state before tab close. Two gates control access: site-wide filter wp_mcp_ai_chat_memory_enabled and per-user meta wp_mcp_ai_chat_memory_enabled. Full reference: docs/features/memory/chat-client-integration.md.

Retroactive Transcript Mining

WP_MCP_AI_Transcript_Mining_Job retrospectively extracts memories from past chat transcripts. Enqueue a job via POST /mcp-ai/v1/transcript-mining/jobs (admin-only), poll progress with GET /jobs/{id}, or cancel with POST /jobs/{id}/cancel. Full reference: docs/features/memory/transcript-mining.md.

LLM Harnessing Subsystem

Seven opt-in per-request layers (includes/harness/) improve response quality without changing existing tool behaviour. Activated per-assistant via the LLM Harness metabox. Layers: A Prompt/Cue → B Reasoning Trace → C Tool Routing → D Retrieval → E Self-Refine → F Memory Scoping + PII Filter → G Eval Scheduler. Pro Layer H exports fine-tune curricula as OpenAI JSONL. Full reference: docs/features/llm-harness.md.

Workflow families & tool combos

The core plugin ships with a centrally registered tool catalogue that lets assistants mix and match capabilities into cohesive workflows without additional coding. Teams can chain authoring, media, research, commerce, marketing, and operational tools to deliver end-to-end outcomes inside a single conversation.

• Content & knowledge production – Combine submit_document_prompt, search_content, and search_attachments to gather source material, then follow up with save_post, create_wpcode_snippet, or get_rankmath_seo for structured drafting and optimisation.

• Media generation & transcription – Pair generate_openai_image, generate_gemini_image, vectorize_image, or graphic_editor_plus with generate_openai_speech and transcribe_openai_audio to build multimedia assets that flow into editorial or marketing outputs. Use vectorize_image to convert logos to scalable vectors, and graphic_editor_plus for comprehensive image editing with both local and AI-powered operations.

• Research & situational awareness – Chain discovery helpers like web_search, run_crawl4ai_job, reliefweb_reports, get_gdacs_events, and get_nhc_active_storms to assemble briefing packs before drafting follow-up actions.

• Commerce & finance operations – Use WooCommerce and finance tools such as create_woo_product, get_woo_products, get_woo_recent_orders, crawl4ai_price_lookup, get_import_duty, and quickbooks_report to coordinate merchandising, pricing, and bookkeeping reviews.

• Marketing & analytics insights – Combine measurement tools including google_analytics_report, get_google_business_insights, get_facebook_instagram_insights, get_linkedin_insights, and get_tiktok_insights to guide campaigns and reporting.

• Publishing & outreach automations – Trigger distribution via post_facebook_instagram, post_google_business_update, post_linkedin_update, post_tiktok_video, send_group_email, send_mailjet_email, send_telegram_message, send_whatsapp_message, and schedule_notify_sms once plans are ready.

• Integrations & scheduling – Connect external systems with create_google_calendar_event, search_gmail, list_jetengine_rest_routes, invoke_jetengine_route, and run_openai_external_action as part of larger automations.

• Operations & diagnostics – Close the loop with create_cron_job, list_cron_jobs, get_cron_job, delete_cron_job, check_wp_cli, purge_cache, purge_cloudflare_cache, purge_varnish_cache, get_site_summary, get_site_health, get_system_logs, get_update_status, and OpenAI usage/log review helpers for monitoring and maintenance.

• Automation & scheduling workflows – Agents can autonomously schedule background tasks with create_cron_job, monitor scheduled operations via list_cron_jobs and get_cron_job, and clean up outdated automations with delete_cron_job. Combine with cache management tools (purge_cache, purge_cloudflare_cache, purge_varnish_cache) to orchestrate content publishing workflows where agents schedule posts, then automatically invalidate caches at publication time.

🛠 Built-in tools & automations

The assistant registry ships with a comprehensive catalogue of editorial, marketing, commerce, and operational helpers. The tables below outline every bundled tool and the slug assistants call when orchestrating workflows.

Content & knowledge workflows

Media generation & transcription

Research & situational awareness

Commerce & finance operations

Marketing & analytics insights

Publishing & outreach

Integrations & scheduling

Operations & diagnostics

What the Cron Manager means to AI agents

The Cron Management Suite transforms AI assistants from reactive responders into proactive automation orchestrators. By providing full control over WordPress's background task scheduler, agents can:

Autonomous Task Scheduling

• Schedule content publishing workflows to go live at optimal times without human intervention

• Automate recurring maintenance tasks like cache clearing, database optimization, or backup operations

• Coordinate multi-step operations that span hours or days by chaining scheduled hooks

Intelligent Monitoring & Self-Management

• List and inspect all scheduled tasks to understand what automation is currently active

• Audit who created each task and when it's scheduled to run next

• Identify and remove outdated or redundant scheduled tasks to maintain system health

Real-World Agent Workflows

1. Content Calendar Automation - An agent helping with content strategy can schedule posts to publish at researched optimal engagement times, set up recurring social media cross-posts, and schedule follow-up email campaigns.

2. Site Maintenance Orchestration - When troubleshooting performance issues, agents can schedule off-peak cache purges, coordinate database cleanup tasks, and set up recurring health check notifications.

3. Business Process Automation - Agents can schedule recurring report generation, periodic data syncs with external systems, and automated backup verification checks.

Technical Implementation The cron manager tracks all scheduled tasks in wp_mcp_ai_cron_jobs option with full audit trails including:

• Job ID for unique identification

• Hook name and sanitized arguments

• Schedule type (single-run or recurring interval)

• Creation timestamp and user attribution

• Next execution time for monitoring

Jobs are automatically pruned when they complete (single-run) or are manually removed (recurring), keeping the tracking database clean. All cron operations require manage_options capability, ensuring only authorized users can delegate automation authority to agents.【F:includes/class-wp-mcp-ai-cron-manager.php†L12-L280】

Each tool inherits the assistant context and authenticated user from the REST layer, making it easy to layer custom permissions or extend behaviour via the documented filters and actions.【F:includes/class-wp-mcp-ai-rest.php†L236-L360】【F:includes/class-wp-mcp-ai-rest.php†L1124-L1198】

Need per-tool prerequisites or capability callouts? Consult docs/reference/tools/tool-reference.md for a detailed matrix of every bundled integration.

Tool Status Labels

The Tools Manager page displays status labels beside tool names to indicate their development stage and stability:

Status labels are displayed as 3-letter abbreviations (e.g., "STA" for stable, "BET" for beta) to keep the UI compact.

Important: Tools marked with the bug status are automatically disabled when the plugin loads. This prevents problematic tools from being used until issues are resolved. Administrators can manually re-enable them from the Tools Manager if needed for testing.

Status labels are managed via the tool-status.txt file in the repository. To assign a status label to a tool:

1. Open docs/tool-status.txt in a text editor

2. Add a line in the format: tool_slug = status_label

3. Save the file - changes appear immediately in the Tools Manager

Example:

create_post = stable
web_search = beta
generate_openai_image_validated = experimental
problematic_tool = bug

This file-based approach allows quick status updates without code changes, making it easy for maintainers to reflect tool maturity as development progresses. The automatic disabling of buggy tools provides an additional safety layer to prevent issues in production environments.

🗨 Front-end chat surfaces

NV oOS ships multiple ways to embed assistants on the front end:

• Classic chat shortcode – [mcp_ai_chat] renders the bundled interface with attachment uploads, tool invocation feedback, and optional guest access via allow_guests="true". When guest mode is enabled, the shortcode provisions a temporary token and injects it into the JavaScript bootstrap so visitors without WordPress accounts can continue chatting while still respecting capability checks and attachment safety limits.【F:includes/class-wp-mcp-ai-shortcode.php†L132-L258】【F:includes/class-wp-mcp-ai-shortcode.php†L188-L226】

• Floating chat bubble ⭐ NEW – A configurable floating button that sits at a screen corner and opens a chat panel powered by the [mcp_ai_chat] shortcode. Available as both an Elementor widget and a Gutenberg block. Supports 4 position variants, 3 sizes, auto-open delay, session persistence, dark mode, and WCAG keyboard navigation.【F:includes/elementor/class-wp-mcp-ai-elementor-chat-bubble-widget.php†L1-L200】【F:includes/blocks/chat-bubble/block.json†L1-L50】

• Elementor widgets – Drop the chat UI anywhere Elementor is active, pair it with intro/FAQ blocks, and surface dashboard telemetry without custom code. The chat widget mirrors the shortcode controls (including allow_guests), and companion widgets expose onboarding content, usage timers, provider quick links, and activity feeds for operational views.【F:includes/elementor/class-wp-mcp-ai-elementor-widget.php†L79-L138】【F:includes/class-wp-mcp-ai-elementor-integration.php†L48-L98】【F:includes/elementor/class-wp-mcp-ai-elementor-chat-intro-widget.php†L47-L140】【F:includes/elementor/class-wp-mcp-ai-elementor-chat-usage-timer-widget.php†L48-L226】【F:includes/elementor/class-wp-mcp-ai-elementor-dashboard-activity-feed-widget.php†L48-L167】

Guest tokens are honoured by the REST endpoints through the X-WP-MCP-AI-Guest header or guest_token parameter, allowing the chat shortcode and Elementor widget to make authenticated requests on behalf of public visitors without exposing persistent credentials.【F:includes/class-wp-mcp-ai-rest.php†L289-L307】【F:includes/class-wp-mcp-ai-rest.php†L2088-L2104】

Chat History Persistence

The chat interface automatically persists conversation history to the browser's localStorage, preventing data loss when users navigate away or refresh the page. Conversations are:

• Automatically saved after each user message and assistant response

• Automatically restored when returning to the chat page (within 24 hours)

• Stored per assistant so different assistant conversations remain separate

• Server-side storage available with JetEngine - See note below about optional JetEngine integration

Server-Side Chat Transcript Storage (Requires JetEngine)

⚠️ Third-Party Plugin Required: JetEngine (not included with NV oOS)

Without JetEngine, chat conversations are only stored in browser localStorage (client-side, 24-hour retention). To enable permanent server-side chat transcript archiving:

1. Install and activate the JetEngine plugin (third-party, paid plugin from Crocoblock)

2. Enable the Custom Content Types module in JetEngine settings

3. NV oOS will automatically provision the ai_chat_transcripts CCT for permanent storage

What you get with JetEngine:

• ✅ Permanent server-side chat transcript storage

• ✅ Cross-device conversation access

• ✅ Admin visibility into chat history

• ✅ Database-backed chat logs for compliance/auditing

Without JetEngine:

• ⚠️ Chat history only stored in browser localStorage

• ⚠️ Limited to 24-hour retention

• ⚠️ No cross-device synchronization

• ⚠️ Lost if browser data is cleared

See docs/user-guides/chat/chat-history-persistence.md for complete details on the persistence mechanism, data structure, and troubleshooting.

📦 Installation

ℹ️ Plugin Directory Status
This plugin is currently pending approval in the WordPress Plugin Directory. We are committed to maintaining high quality and security standards throughout the review process. You can install the plugin manually from our GitHub repository or wait for the official WordPress Plugin Directory listing.

🚀 Getting Started Wizard
After activating the plugin, you'll be redirected to a 4-step setup wizard that walks you through connecting an AI provider, choosing a use case, and creating your first assistant — all in under 2 minutes. The wizard creates fully-configured assistants with tools, system prompts, and tuned temperatures so your site is working out of the box. You can access the wizard any time at NV oOS → Getting Started or directly at /wp-admin/admin.php?page=wp-mcp-ai-getting-started.

🌱 Try It on Your PC

No live site. No API costs. No risk. The primary way to test NV oOS is a one-command demo that boots WordPress and the Complete bundle locally via WordPress Playground and wires the chat to your local Ollama — no API key, no server, and no prompts leave your machine.

⚡ Fastest: One Command (Playground + Local Ollama)

One-time prerequisites:

1. Install Ollama and pull a model:

   ollama pull llama3.1:8b

2. Allow the local origin, then restart Ollama:

   • Windows: setx OLLAMA_ORIGINS "https://playground.wordpress.net,http://localhost,http://127.0.0.1", then quit Ollama from the system tray and relaunch it.

   • macOS / Linux: OLLAMA_ORIGINS="https://playground.wordpress.net,http://localhost,http://127.0.0.1" ollama serve

Then run this command (requires Node.js 20+):

npx -y @wp-playground/cli@3.1.54 server --blueprint=https://raw.githubusercontent.com/nvdigitalsolutions/mcp-ai-wpoos/alpha-working/blueprints/ollama-demo.json --login

Open the printed local URL (e.g. http://127.0.0.1:9400/ollama-test-lab/). The first boot takes a few minutes while it downloads and installs the whole stack — after that you land on the Ollama Test Lab: a live status banner plus a chat that answers from your local model. Admin login: admin / password.

Full walkthrough, browser quick-preview link, and troubleshooting: docs/user-guides/playground-demo.md.

🧰 Classic 3-Step Install (Local, Studio, XAMPP, etc.)

Prefer a traditional local WordPress install? Follow the full walkthrough on the NV Digital Solutions blog: How to Test NV oOS on Your Own PC Using Local + Downloading the Plugin →

1. Install a local WordPress environment — Local by WP Engine or WordPress Studio is the easiest option (one-click install, no server config). Alternatives: XAMPP, MAMP, or DevKinsta.

2. Download the NV oOS plugin zip — grab the latest release from GitHub Releases (look for mcp-ai-wpoos-x.x.x.zip), or use the Code → Download ZIP button for the current development snapshot.

3. Upload, activate, and run the wizard — in your local WordPress dashboard go to Plugins → Add New → Upload Plugin, select the zip, activate it, and follow the 🚀 Getting Started Wizard. For a free local AI model (no API key needed), install LM Studio and point the wizard at http://localhost:1234.

🗺 Single-file auto-installer (roadmap) — A single cross-platform installer that bootstraps the entire stack automatically is on the roadmap. See the App / Plugin Distribution Proposal for current status and the plan.

Requirements

Minimum Requirements:

• WordPress 6.0+

• PHP 7.4+ (PHP 8.0+ recommended)

• MySQL 5.7+ or MariaDB 10.3+

Optional Requirements for Enhanced Features:

• Node.js 14+: Required for image vectorization tools (vectorize_image tool)

• PHP Functions: proc_open, proc_close, proc_terminate (for Node.js integration and Process Service)

  • These functions are often disabled on shared hosting for security

  • Can be enabled on Cloudways via Application Settings (see troubleshooting guide)

• JetEngine Plugin: For CCT storage and advanced content management tools

• WooCommerce: For e-commerce integration tools

• Elementor: For visual page builder widgets

Note: The plugin works without optional requirements, but some features will be disabled. See deployment troubleshooting for enabling disabled PHP functions.

For Developers (GitHub Clone)

✅ Production-Ready Repository
This repository includes production-optimized vendor dependencies with classmap-authoritative autoloading configured by default in composer.json. You can clone and activate immediately without running composer. The composer install command is only needed if you want to update dependencies or add development tools.

⚡ Use a shallow clone
A full clone of this repository is ~10 GB due to its long history. Use --depth 1 to download only the latest snapshot (~500 MB) — much faster and smaller. If you later need the full history, run git fetch --unshallow.

git clone --depth 1 https://github.com/nvdigitalsolutions/mcp-ai-wpoos.git

If you're cloning from GitHub:

Option 1: Cloudways and Managed Hosting (Recommended)

For Cloudways and similar managed hosting platforms, clone directly into the WordPress plugins directory:

# SSH into your server
# Navigate to WordPress plugins directory
cd /home/master/applications/YOURAPP/public_html/wp-content/plugins/

# Clone the repository (production-ready, no composer needed!)
# Use --depth 1 for a fast shallow clone (recommended for production)
git clone --depth 1 https://github.com/nvdigitalsolutions/mcp-ai-wpoos.git
cd mcp-ai-wpoos

# Verify you're in the correct directory
pwd  # Should show the plugins path

# Optional: Only needed for frontend asset rebuilding or development
# npm install && npm run build

# Optional: Only run if you need to update dependencies or add dev tools
# Note: Autoloader optimization is now configured by default in composer.json
# composer install --no-dev

⚠️ Cloudways Important Notes:

• Always clone directly into /home/master/applications/YOURAPP/public_html/wp-content/plugins/

• Do NOT clone elsewhere and then move/copy - this causes getcwd() failed errors

• Replace YOURAPP with your actual Cloudways application name

Option 2: Local Development or VPS

For local development or standard VPS hosting:

# Option A: Clone directly into WordPress plugins directory (recommended, production-ready!)
cd /path/to/wordpress/wp-content/plugins/
# Use --depth 1 for a fast shallow clone (recommended for production)
git clone --depth 1 https://github.com/nvdigitalsolutions/mcp-ai-wpoos.git
cd mcp-ai-wpoos
# Ready to activate! No composer or npm needed for production use.

# Option B: Clone and copy (also production-ready!)
# Use --depth 1 for a fast shallow clone (recommended for production)
git clone --depth 1 https://github.com/nvdigitalsolutions/mcp-ai-wpoos.git
cd mcp-ai-wpoos
cp -r . /path/to/wordpress/wp-content/plugins/mcp-ai-wpoos/

For Development Only:

# Only if you need to rebuild assets or modify dependencies:
npm install && npm run build
# Note: Autoloader optimization is now configured by default in composer.json
composer install --no-dev

Optional: Strip Dev Files for Production

If you are deploying via git clone to a production server with anti-malware / EDR scanning, the working tree will contain test fixtures that embed verbatim attack-payload literals (XSS canaries, SQL-injection samples, prompt-injection strings) used by the security test suite. These can occasionally trip signature-based scanners.

For a clean production tree, run the bundled strip script after cloning:

# Preview what would be removed
bin/strip-dev-files.sh --dry-run

# Remove tests/, docs/, bin/, .github/, .bmad/, .context/, examples/,
# phpunit.xml.dist, phpcs.xml.dist, dev configs, etc.
bin/strip-dev-files.sh

The script mirrors the exclusion list in .distignore (used for the WordPress.org SVN deploy) and the export-ignore rules in .gitattributes (used for GitHub-distributed ZIPs). It is idempotent and refuses to run on a working tree with uncommitted changes (override with --force).

Note: Do not run this on a development checkout — it removes the test suite, docs, and build tooling. It is intended for deploy targets that only run the plugin.

Final Steps

1. Activate Open Operator System Complete (NV oOS) from WordPress admin

2. You now have the complete version with all ~1,648 tools (~347 base + ~1,301 Pro; live count via WP_MCP_AI_Tool_Registry::get_tools() is authoritative)

What you get from the repository clone:

• ✅ The full codebase — all ~1,648 built-in tools ready to use (~347 base + ~1,301 Pro; live count via WP_MCP_AI_Tool_Registry::get_tools() is authoritative)

• ✅ Single plugin activation (not separate base + pro)

• ✅ Pro features automatically available (no separate Pro plugin to install)

Notes:

• The repository includes mcp-ai-wpoos-base.php and addons/pro/mcp-ai-wpoos-pro.php which are used for building separate distributions but do NOT appear as separate plugins when cloning

• Only the main plugin file (mcp-ai-wpoos.php) has a plugin header in the repository

• The build script adds headers to the other files when creating standalone distributions

Standard Installation

1. Upload mcp-ai-wpoos.zip to /wp-content/plugins/

2. Activate NV oOS from the WordPress admin

3. Go to Settings → NV oOS

4. Enter your OpenAI API key

5. Create a new “AI Assistant” in AI Assistants

6. Add [mcp_ai_chat assistant="123"] to a page or post

Optional: JetEngine Integration

⚠️ Third-Party Plugin (Not Included): JetEngine is a paid plugin from Crocoblock

JetEngine is completely optional - NV oOS works perfectly without it. However, if you want server-side chat transcript storage:

1. Purchase and install JetEngine separately

2. Enable the Custom Content Types module in JetEngine settings

3. NV oOS will automatically provision the ai_chat_transcripts CCT for permanent chat storage

What works WITHOUT JetEngine:

• ✅ All core AI assistant features

• ✅ Chat interface and conversations

• ✅ ~300 base tools (more with optional third-party plugins)

• ✅ MCP server functionality (/wp-json/mcp-ai/v1/)

• ✅ Browser-based chat history (localStorage, 24 hours)

• ✅ OpenAI/Gemini/Anthropic/Ollama/Hugging Face/Cloudflare integrations

What requires JetEngine:

• ❌ Server-side chat transcript storage (chat history only in browser without it)

• ❌ 5 JetEngine-specific tools (see 🔌 Optional Tools & Dependencies)

🔌 What You Lose Without Third-Party Plugins

NV oOS works perfectly with vanilla WordPress, but certain features require third-party plugins (sold separately). Here's exactly what you lose without each plugin:

Without JetEngine (Crocoblock - Paid Plugin)

Lost Features:

• ❌ AI metaboxes for JetEngine CPTs/Taxonomies - No AI assistant integration on JetEngine edit screens

• ❌ Research & Add pages - No AI-powered content creation with automatic field mapping

• ❌ Server-side chat transcript storage - Chat history only stored in browser localStorage (24 hours)

• ❌ Cross-device chat synchronization - No database-backed conversation history

• ❌ Admin chat history access - Cannot view/audit conversations from admin panel

• ❌ Assistant CCT synchronization - Assistants only in WordPress CPT (MCP server still works perfectly)

Lost Tools (5 tools):

• get_jetengine_items - Query JetEngine custom post types

• list_jetengine_rest_routes - List JetEngine REST API routes

• invoke_jetengine_route - Execute JetEngine REST operations

• get_jetformbuilder_forms - List JetFormBuilder forms (also requires JetFormBuilder)

• get_jetformbuilder_submissions - Get form submissions (also requires JetFormBuilder)

✅ Still Works: All core features, MCP server, ~300 base tools, AI conversations

Get JetEngine →

Without WooCommerce (Free Plugin)

Lost Features:

• ❌ E-commerce automation - Cannot create or manage products via AI

• ❌ Order management - Cannot query or analyze orders

• ❌ Product catalog access - Cannot search or update product data

Lost Tools (3 tools):

• create_woo_product - Build draft WooCommerce products with AI-generated descriptions, pricing, and images

• get_woo_products - Search and retrieve product catalog with pricing and stock status

• get_woo_recent_orders - Summarize recent orders with billing details and totals

Use Cases Lost: E-commerce content generation, order fulfillment assistance, product merchandising

Get WooCommerce →

Without Elementor (Freemium Plugin)

Lost Features:

• ❌ Template management - Cannot list or reference Elementor templates via AI

• ❌ Elementor widgets - Cannot use pre-built chat/dashboard widgets (shortcodes still work)

Lost Tools (2 tools):

• get_elementor_templates - List Elementor library templates with status, type, and edit links

• import_elementor_template_kit - Import Elementor template kits

Lost UI Components:

• Elementor Chat Widget

• Elementor Chat Intro Widget

• Elementor Dashboard Widgets (Tool Matrix, User Capabilities, Activity Feed, etc.)

✅ Still Works: Standard [mcp_ai_chat] shortcode, all AI features

Get Elementor →

Without Rank Math SEO (Freemium Plugin)

Lost Features:

• ❌ SEO analysis - Cannot query SEO scores or optimization recommendations

• ❌ Schema data access - Cannot retrieve structured data for posts

Lost Tools (1 tool):

• get_rankmath_seo - Get SEO scores, focus keywords, robots metadata, and schema details for posts

Use Cases Lost: AI-powered SEO content optimization, SEO audit assistance

Get Rank Math →

Without WPCode (Freemium Plugin)

Lost Features:

• ❌ Code snippet management - Cannot create or update code snippets via AI

• ❌ Custom functionality automation - Cannot automate adding hooks, filters, or custom code

Lost Tools (1 tool):

• create_wpcode_snippet - Create or update code snippets with validation and activation control

Use Cases Lost: AI-assisted custom development, automated code snippet generation

Get WPCode →

Without Simple JWT Login (Free Plugin)

Lost Features:

• ❌ JWT token generation - Cannot generate JWT bearer tokens for headless WordPress integrations

Lost Tools (1 tool):

• generate_simple_jwt_token - Generate JWT bearer tokens for authenticated API access

Use Cases Lost: Headless WordPress authentication, mobile app integration, SPA authentication

Get Simple JWT Login →

Summary: Third-Party Plugin Dependencies

Total Impact: Without these plugins, you lose 13 tools but retain ~300 base tools and all essential AI assistant functionality.

Base Version (Default)

NV oOS runs in Base Version mode by default, providing ~300 essential tools that work with vanilla WordPress without requiring any third-party plugins:

Base Version includes ~300 essential tools that work with vanilla WordPress:

• Content management (search, save posts, attachments)

• AI media generation (images via OpenAI/Gemini, speech, transcription, video)

• Research tools (web search, weather, disaster alerts)

• Site operations (health checks, logs, cron jobs, cache management)

• WordPress-native email (via wp_mail)

• Image manipulation (resize, crop, rotate, convert, vectorize to SVG)

• Graphic editing (local operations and AI-powered transformations)

• Profession and assistant management

• GitHub integration tools

• Google Maps Platform tools

Base Version excludes 31 tools requiring third-party plugins or external APIs:

• Third-party WordPress plugins (13 tools) - See 🔌 What You Lose Without Third-Party Plugins for details

  • WooCommerce tools (3)

  • JetEngine/JetFormBuilder tools (5)

  • Elementor tools (2)

  • RankMath/WPCode/Simple JWT Login tools (3)

• External API services (18 tools) - Require API credentials

  • Google services (5)

  • Social media integrations (8)

  • External messaging services (4)

  • QuickBooks (1)

Full Version Installation (Opt-in)

To enable the Full Version with all third-party integrations and external API tools, add this constant to your wp-config.php file:

define( 'WP_MCP_AI_BASE_VERSION', false );

📖 See BASE-VERSION.md for the complete tool list and customization options.

When to use Base Version:

• Starting fresh with WordPress

• Testing or development environments

• Simpler installations without external dependencies

• Sites that don't need e-commerce or advanced integrations

• Don't want to purchase/install third-party plugins

When to use Full Version:

• Production sites with WooCommerce, JetEngine, or Elementor already installed

• Sites needing social media automation (requires API credentials)

• Advanced workflows requiring external APIs

• Need server-side chat transcript storage (requires JetEngine)

📖 See detailed breakdown: 🔌 What You Lose Without Third-Party Plugins

📚 Documentation

NV oOS includes comprehensive documentation covering all aspects of the plugin. Documentation reorganized June 2026 — Unix-theory separation of concerns. All docs sorted into 12 purpose-driven directories with zero content loss.

📖 Documentation Hub

• Documentation Hub ⭐ Start here - Central navigation with organized categories

• Documentation Index - Complete map of all 1,600+ documentation files

• Architecture Overview - System architecture (15 providers, ~1,648 tool classes, 36 REST controllers)

• Request Flow Walkthrough - End-to-end chat request lifecycle trace

• Quick Reference Guide - Fast access to common tasks and commands

Essential References

• Tool Reference - All ~1,648 tools documented (~347 base + ~1,301 Pro; live count via WP_MCP_AI_Tool_Registry::get_tools() is authoritative)

• REST API Documentation - Complete API reference with examples

• Testing & Quality Report - Test results and code quality analysis

📦 Archive

• Historical Documentation — 50+ archived files from 2024-2025 development

• Docs Archive - Consolidated implementation history and superseded documentation

For New Users

• 🚀 Getting Started Wizard ⭐ NEW — 4-step guided setup that connects your AI provider, selects a use case, and creates a ready-to-use assistant in under 2 minutes. 8 presets available: Content Creator, Customer Support, E-commerce, SEO & Research, Developer Copilot, Media & Creative Studio, Site Administrator, General Purpose.

• Use Cases & Quickstart Guides ⭐ NEW - Comprehensive guide covering 7 major use cases with step-by-step quickstarts

• 5-Minute Quick Start - Get started immediately: from zero to first chat

• Setup Checklist - Step-by-step installation and configuration

• Remote Client Quickstart - Connect Claude Desktop, LM Studio, or other MCP clients

• Best Practices - Recommended usage patterns and optimization tips

For Developers

• Testing & Quality Report - Test suite results (2,106 tests, 73.4% pass rate), code quality analysis, security audit

• Code Review Master - Comprehensive code quality analysis (95/100 score)

• Action Items - Prioritized development tasks (180+ hours)

• Authentication Guide - Authentication methods and security

• MCP JSON-RPC 2.0 Endpoint - Model Context Protocol implementation

For Administrators

• Deployment Troubleshooting - Common issues and solutions

• Multisite Support - WordPress multisite configuration

• Rate Limit Protection - API rate limiting setup

• Mesh Routing Guide - Intelligent compute routing across sites and providers

• Federation & Discovery - Decentralized AI capability network with peer discovery and well-known endpoints

Performance & Optimization

• Message Bundling - Client-side message optimization

• High Token Tool Handling - Agentic loop token management

• Job Notification System - Real-time async job updates

• Chat Performance Optimizations - Complete performance guide

• Mesh Routing Guide - Intelligent compute routing across sites and providers

Historical Documentation

• Archive Directory - 95+ historical documents organized by category:

  • implementations/ - Implementation summaries and technical details

  • phases/ - Development phase documents

  • fixes/ - Bug fix summaries and issue resolutions

  • features/ - Feature documentation

  • code-reviews/ - Code review reports

  • testing/ - Test infrastructure documentation

⚙ Configuration Checklist (Action Items)

Complete these after installation to unlock every integration point:

• Add your OpenAI API key in Settings → NV oOS → OpenAI API Key so API calls are authorised.

• Add your Gemini API key in Settings → NV oOS → Gemini API Key if you plan to route assistants through Gemini.

• Confirm or override the default model via Settings → NV oOS → Default Model (gpt-4.1 ships as the default).

• Set a default Gemini model under Settings → NV oOS → Default Gemini Model when Gemini is enabled.

• Choose the default provider from Settings → NV oOS → Default Provider so new assistants know whether to use OpenAI or Gemini by default.

• Adjust the request timeout under Settings → NV oOS → Request Timeout (minimum 5 s, default 30 s) to match your hosting environment.

• Select a default assistant with Settings → NV oOS → Default Assistant so REST and shortcode requests have a fallback.

• Decide on logging with Settings → NV oOS → Enable Logging when you need verbose diagnostics.

• Monitor token usage in Settings → NV oOS → Token Usage Statistics to track API consumption across users, providers, and models for billing and budget management.

• Choose your uninstall behaviour via Settings → NV oOS → Remove Data on Uninstall if this site should purge assistants and settings during cleanup.

• Configure Crawl4AI access in Settings → NV oOS → Tools when you want the Crawl4AI tool to be available to assistants.

• Review attachment MIME overrides in Settings → NV oOS → Attachments before enabling file uploads for end users.

• Review Send Group Email permissions in Settings → NV oOS → Tools to choose the capability and recipient cap for the group email automation.【F:includes/admin/class-wp-mcp-ai-admin-settings.php†L348-L359】【F:includes/admin/class-wp-mcp-ai-admin-settings.php†L938-L953】

• Connect Gmail under Settings → NV oOS → Tools → Connections → Gmail to enable Gmail search tools with OAuth 2.0. See Google OAuth Setup Guide for complete configuration steps.

• Connect QuickBooks Online under Settings → NV oOS → QuickBooks Company ID / API Key so the bundled reporting tool can fetch finance statements for authorised operators.【F:includes/admin/class-wp-mcp-ai-admin-settings.php†L906-L955】

• Configure Mailjet credentials in Settings → NV oOS → Mailjet API Key / Secret / From Email / From Name before enabling Mailjet-powered tools or Elementor widgets that send email on behalf of assistants.【F:includes/admin/class-wp-mcp-ai-admin-settings.php†L1008-L1054】

• Enable Federation & Discovery (Optional) in Settings → NV oOS → Federation & Discovery to publish your site's AI capabilities via /.well-known/ai-peer and optionally run a directory service for peer discovery. Configure regions, data tags, and rate limits to control how your site participates in the decentralized AI network.【F:docs/features/federation/federation-discovery.md†L1-L511】【F:FEDERATION-IMPLEMENTATION-SUMMARY.md†L1-L381】

• Configure Root Security Key (Optional) by adding define( 'WP_MCP_AI_ROOT_SECURITY_KEY', 'your-secure-key' ); to wp-config.php. This provides an additional security layer that can be enabled during emergency shutdown to require authentication before re-initializing the plugin.【F:docs/features/security/root-security-key.md†L1-L511】

• Enable Pro Dashboard (Optional) by adding define( 'WP_MCP_AI_PRO_DASHBOARD_ENABLED', true ); to wp-config.php. This activates the dedicated Pro Dashboard with ISO/IEC 27001 compliance monitoring, reporting, and management tools. See Pro Dashboard Documentation for details.

🧠 Language Model Providers (OpenAI, Gemini, Anthropic, Baseten, DeepSeek, OpenRouter, Kimi, DigitalOcean, NVIDIA NIM, Ollama, LM Studio, Hugging Face, Cloudflare)

A dedicated router transparently forwards chat completions to the active provider, allowing each request to target OpenAI, Gemini, Anthropic, DeepSeek, OpenRouter, Baseten, Kimi, DigitalOcean, NVIDIA NIM, a local Ollama instance, LM Studio, Hugging Face, or Cloudflare Worker AI while sharing the same assistant UX.【F:includes/class-wp-mcp-ai-language-model-router.php†L12-L86】 Configure the required API keys, default models, and the global default provider in Settings → NV oOS so new assistants inherit sensible defaults and administrators can switch providers without code changes.【F:includes/admin/class-wp-mcp-ai-admin-settings.php†L124-L333】【F:includes/admin/class-wp-mcp-ai-admin-settings.php†L505-L530】 Assistants can still override provider, model, and generation parameters on a per-post basis.

Privacy & Terms: All AI providers have specific terms and privacy policies:

• OpenAI: Terms | Privacy

• Google Gemini: Terms | Privacy

• Anthropic: Terms | Privacy

• NVIDIA NIM: Terms | Privacy

• Cloudflare: Terms | Privacy

• Hugging Face: Terms | Privacy

• Ollama/LM Studio: Self-hosted (no external data transmission)

• Baseten: Terms | Privacy

LM Studio Support

LM Studio with Function Calling - Full support for OpenAI-compatible function calling with local LM Studio instances:

• OpenAI-compatible message structure preserved for tool calls

• Tools/functions can be invoked by LM Studio models (e.g., qwen/qwen3-coder-30b)

• Streaming automatically disabled when tools are present for reliable execution

• Full backward compatibility with non-tool scenarios

• Connect via JSON-RPC endpoint (recommended) or SSE streaming

• See LM Studio setup guide for configuration details

Provider Priority List & Automatic Fallback

The plugin includes an intelligent provider priority system that automatically tries alternative providers when the primary one fails or is unavailable. In Settings → NV oOS, you can:

• Drag and drop providers to set your preferred order

• Automatic fallback - if the first provider fails, the system tries the next one

• Visual management - see all available providers (OpenAI, Gemini, Anthropic, Baseten, DeepSeek, OpenRouter, Kimi, DigitalOcean, NVIDIA NIM, Ollama, LM Studio, Hugging Face, Cloudflare) in one sortable list

• Flexible prioritization - adjust based on cost, performance, or availability needs

The first provider in the list serves as the default. If any provider returns an error, the router automatically attempts the next provider in the list until one succeeds. This ensures maximum uptime and resilience without manual intervention. All fallback attempts are logged for debugging and monitoring.

Local AI with Ollama

The Ollama provider enables privacy-focused, cost-free AI processing by connecting to a local Ollama or LM Studio instance running on your server or development machine. This is ideal for:

• Privacy-sensitive deployments where data must stay on-premises

• Development and testing without incurring API costs

• Custom or fine-tuned models not available through cloud providers

• Air-gapped environments without internet access

To configure Ollama:

1. Install Ollama on your server or local machine

2. Pull a model (e.g., ollama pull llama2)

3. Navigate to Settings → NV oOS → Ollama Configuration

4. Enter your Ollama endpoint URL (default: http://localhost:11434)

5. Click "Test Connection" to verify connectivity

6. Click "Fetch Models" to see available models

7. Select a model from the list or manually enter a model name

8. Set "Default Provider" to "Ollama (Local AI)" if you want it as the system default

The Ollama client supports the standard chat completion flow and automatically normalizes responses to match the OpenAI format for downstream compatibility. Note that some advanced features like tool calling may vary depending on the specific Ollama model you're using.

OpenAI model coverage

The plugin ships with presets for OpenAI’s current Responses, Reasoning, Audio, and Image APIs so site owners can choose the right model for each workflow. Token windows describe the maximum request size (messages, attachments, and tool payloads) the OpenAI API will accept for that model, while output limits reflect the largest single response the service will stream back. Leave a safety margin below each ceiling so assistants can add system instructions, tool calls, and knowledge snippets without hitting provider limits.

Media and multimodal defaults

OpenAI regularly revises token policies and media limits, so review the model specification dashboard before rolling out new assistants or increasing attachment budgets. Updating your defaults in Settings → NV oOS keeps every assistant aligned with the latest provider guidance.【F:includes/admin/class-wp-mcp-ai-admin-settings.php†L36-L105】【F:includes/admin/class-wp-mcp-ai-admin-settings.php†L2298-L2398】

🧱 ChatKit Integration

The ChatKit module now ships with the core NV oOS plugin, so no separate add-on installation is required. Once enabled it self-registers through ChatKit’s filter and action APIs as soon as both plugins load, exposing the mcp-ai/v1 REST namespace while advertising chat, tool invocation, attachment download, and guest token support without any manual bootstrapping. Return false from the wp_mcp_ai_chatkit_is_available filter if you need to disable the automatic registration for bespoke environments.【F:includes/class-wp-mcp-ai-chatkit-integration.php†L30-L204】【F:includes/class-wp-mcp-ai-rest.php†L16-L2104】

From the ChatKit dashboard configure the NV oOS integration and supply at least one assistant ID so ChatKit knows which conversation to join. Optional fields let you override the system prompt or preload tool shortcut payloads for operators; capability checks inherit the wp_mcp_ai_chat_capability filter, so you can align ChatKit access with the same policies used for shortcodes or REST calls.【F:includes/class-wp-mcp-ai-chatkit-integration.php†L182-L210】【F:mcp-ai-wpoos.php†L25-L72】

Consult docs/developer/integration/chatkit-integration.md for a full configuration walkthrough, JSON examples for shortcut presets, and notes on extending the definition via filters.

🌐 Crawl4AI Integration

Administrators with manage_options capabilities can run the Run Crawl4AI Job tool without any external service: when no Crawl4AI endpoint is configured the plugin performs the crawl directly on the WordPress server using the built-in HTTP client, extracts headings and text as Markdown, and records the raw HTML and response metadata for the assistant.【F:includes/tools/class-wp-mcp-ai-tool-run-crawl4ai-job.php†L32-L745】 Errors for individual URLs are captured in the response metadata so partial crawls still return useful context. When a remote Crawl4AI endpoint is configured the request now returns immediately with a task token while WP-Cron powered background polling captures the final payload and makes it available to the assistant UI once the crawl finishes.【F:includes/crawler/class-wp-mcp-ai-crawler.php†L1-L214】【F:assets/js/chat.js†L1-L2200】

Configure remote endpoints or API keys under Settings → NV oOS → Tools to tailor how the Crawl4AI integration runs across environments.【F:includes/admin/class-wp-mcp-ai-admin-settings.php†L248-L521】

Supplying a Crawl4AI base URL (and optional API key) switches the tool back to proxying crawl jobs to the remote Crawl4AI REST API, preserving backwards compatibility with existing deployments.【F:includes/tools/class-wp-mcp-ai-tool-run-crawl4ai-job.php†L206-L339】【F:includes/admin/class-wp-mcp-ai-admin-settings.php†L248-L521】 Local environments can still feed a custom endpoint to the integration through the WP_MCP_AI_CRAWL4AI_BASE_URL or CRAWL4AI_BASE_URL environment variable when you want to test against a dedicated Crawl4AI service.【F:mcp-ai-wpoos.php†L54-L96】

📡 Job Notification System

NV oOS includes a general-purpose infrastructure for real-time notifications on async WordPress jobs, providing SSE streaming and webhook support for external integrations.【F:docs/features/async-jobs/job-notification-system.md†L1-L100】

Architecture

Async Job → WordPress Action → Job Notifier → [SSE | Webhooks]
                                                 ↓       ↓
                                            Frontend  External

Automatic Crawl4AI Integration

The system automatically hooks into Crawl4AI jobs via the wp_mcp_ai_crawl4ai_job_completed action, providing real-time status updates as crawls progress. No additional code is needed—Crawl4AI jobs automatically trigger notifications.【F:includes/crawler/class-wp-mcp-ai-crawler.php†L1-L214】

Frontend SSE Subscription

JavaScript clients can subscribe to job status updates using Server-Sent Events:

const jobId = 'crawl_abc123';
const eventSource = new EventSource(
    `/wp-json/mcp-ai/v1/jobs/${jobId}/stream?max_duration=300&poll_interval=2`
);

eventSource.addEventListener('status', (e) => {
    const status = JSON.parse(e.data);
    console.log('Job status:', status.status, status.progress);
    updateProgressBar(status.progress);
});

eventSource.addEventListener('complete', (e) => {
    const data = JSON.parse(e.data);
    console.log('Job completed:', data.final_status);
    eventSource.close();
});

Webhook Registration

External systems can receive HTTP callbacks when jobs complete:

WP_MCP_AI_Job_Notifier::register_webhook(
    'crawl_abc123',
    'https://example.com/webhook',
    array( 'completed', 'failed' )
);

➡️ See docs/features/async-jobs/job-notification-system.md for complete implementation details.

🧊 Elementor Widgets

Sites running Elementor automatically register a suite of MCP blocks so you can assemble onboarding pages, operational dashboards, and standalone chat layouts without writing markup.【F:includes/class-wp-mcp-ai-elementor-integration.php†L12-L98】 The integration only boots when Elementor is present, so non-Elementor installs avoid any overhead.【F:includes/class-wp-mcp-ai-elementor-integration.php†L29-L46】

Chat surfaces and companion blocks

• NV oOS Chat – Renders the assistant interface with the same controls exposed by the [mcp_ai_chat] shortcode, including the allow_guests toggle for minting temporary visitor tokens.【F:includes/elementor/class-wp-mcp-ai-elementor-widget.php†L17-L138】

• NV oOS Chat Bubble ⭐ NEW – Floating chat bubble that sits at a configurable screen corner and opens a chat panel powered by the existing [mcp_ai_chat] shortcode. Also available as a Gutenberg block (wp:mcp-ai-wpoos/chat-bubble). 5 control sections: Chat Settings, Bubble Settings (position/size/animation/tooltip/badge/auto-open), Panel Settings, Bubble Style, Panel Style. BEM CSS with 4 positions, 3 sizes, bounce/pulse animations, dark mode, full-screen mobile (<480px), prefers-reduced-motion, WCAG focus states. Public API at window.wpMcpAiChatBubble.【F:includes/elementor/class-wp-mcp-ai-elementor-chat-bubble-widget.php†L1-L200】【F:includes/blocks/chat-bubble/block.json†L1-L50】

• NV oOS Chat Intro – Adds a configurable hero block above the conversation with headings, talking points, and an optional call-to-action button to guide visitors before they engage the model.【F:includes/elementor/class-wp-mcp-ai-elementor-chat-intro-widget.php†L47-L190】

• NV oOS Chat FAQ – Surfaces a repeater-driven FAQ list alongside the chat so product teams can document policies and best practices in context.【F:includes/elementor/class-wp-mcp-ai-elementor-chat-faq-widget.php†L47-L150】

• NV oOS Usage & Timer – Combines a focus timer with per-user token totals, gracefully handling logged-out visitors, disabled tracking, and empty usage histories.【F:includes/elementor/class-wp-mcp-ai-elementor-chat-usage-timer-widget.php†L48-L340】

Operations dashboards

• NV oOS Tool Matrix – Pulls the tool registry, groups integrations by focus area, and highlights the required capability for each assistant tool so administrators can plan enablement safely. The Send Group Email row now mirrors the capability and recipient limit configured in the MCP settings so editorial policies stay front-of-mind.【F:includes/elementor/class-wp-mcp-ai-elementor-dashboard-tool-matrix-widget.php†L48-L440】

• NV oOS User Capability Snapshot – Summarises the signed-in operator’s profile, common capabilities, JetEngine access, and multisite memberships to support governance reviews. It also surfaces the configured Send Group Email capability and limit so administrators immediately know whether the current user can trigger bulk mail jobs.【F:includes/elementor/class-wp-mcp-ai-elementor-dashboard-user-capability-widget.php†L48-L392】

• NV oOS Theme Preview – Renders a mock conversation using the saved chat color tokens and optionally displays a legend of every branding token for quick QA during rollouts.【F:includes/elementor/class-wp-mcp-ai-elementor-dashboard-theme-preview-widget.php†L48-L198】

• NV oOS Provider Quick Links – Reuses the OpenAI usage/log tools to populate external billing and telemetry shortcuts that open in new tabs for rapid debugging.【F:includes/elementor/class-wp-mcp-ai-elementor-dashboard-provider-links-widget.php†L48-L166】

• NV oOS Activity Feed – Streams the latest MCP log entries (tool runs, chat interactions, and optional provider requests), collapsing raw context into expandable JSON blocks for deeper analysis.【F:includes/elementor/class-wp-mcp-ai-elementor-dashboard-activity-feed-widget.php†L48-L210】

🧮 Usage Tracking

Privacy-First Analytics (v1.2.0+)

The plugin includes optional, privacy-first activation tracking to help us understand plugin usage and improve development priorities. This feature is:

Privacy Features:

• ✅ No PII collected - No personal information or identifiable data

• ✅ Site URLs hashed - Non-reversible SHA-256 hash with WordPress salts

• ✅ No IP storage - IP addresses are not logged or stored

• ✅ Local dev excluded - Automatically disabled for localhost and common dev domains

• ✅ Opt-out available - Easy to disable via settings or filter hook

• ✅ GDPR compliant - Meets all privacy regulations

• ✅ Fully transparent - All code is open source and documented

Data Collected:

• Plugin variant (complete, base, pro, or core)

• Plugin version number

• WordPress version

• PHP version

• Site locale (language)

• Multisite status

• Hashed site identifier (non-reversible)

• Timestamp

How to Opt Out:

1. Via Settings: Settings → NV oOS → General → Log Management → Disable Activation Tracking

2. Via Filter Hook:

   add_filter( 'wp_mcp_ai_enable_usage_tracking', '__return_false' );

Full Privacy Details: See EXTERNAL_SERVICES.md for complete documentation.

The plugin records aggregate token usage per user, provider, and model whenever responses include usage metadata, simplifying internal reconciliation or billing workflows. Usage data is stored as user meta and automatically purged when accounts are deleted, and hooks are exposed for custom reporting pipelines.【F:includes/class-wp-mcp-ai-usage-tracker.php†L12-L119】

Token Usage Management Dashboard

Administrators with manage_options capability can view comprehensive token usage statistics in Settings → NV oOS:

Global Statistics (All Users):

• Total requests across all users

• Total tokens consumed (prompt + completion)

• Prompt tokens used

• Completion tokens generated

• Cached tokens (for providers supporting prompt caching)

• Reset all usage data button (with confirmation)

Individual User Statistics:

• Your personal token consumption

• Per-user breakdown of requests and tokens

• Reset personal usage data button

Detailed Breakdown:

• Usage by provider (OpenAI, Gemini, Anthropic, NVIDIA NIM, Ollama, LM Studio, Hugging Face, Cloudflare)

• Usage by specific model (e.g., gpt-4.1-mini, gemini-2.0-flash)

• Request counts per provider/model combination

• Last used timestamp for each model

• Comprehensive table view with all metrics

The usage tracking system automatically:

• Records usage from all API responses that include usage metadata

• Aggregates data by user, provider, and model

• Updates in real-time as conversations occur

• Supports the Open OpenAI Usage tool for quick access to provider dashboards

• Provides AJAX-powered reset functionality for administrators

🧷 Attachment MIME Controls

Administrators can override the default image and file MIME allowlists used by the chat uploader. The settings screen accepts one MIME type per line, and the attachment helper merges the overrides with its defaults before enforcing them on upload and shortcode configuration.【F:includes/admin/class-wp-mcp-ai-admin-settings.php†L225-L669】【F:includes/class-wp-mcp-ai-message-attachments.php†L503-L559】 Leave the fields empty to fall back to the bundled safe defaults.

⚡ Message Bundling

NV oOS implements client-side message bundling to optimize API usage and reduce server load. When enabled, messages sent within an 800ms window are automatically grouped into a single API request, reducing costs and improving performance for users who send multiple messages in quick succession.【F:docs/user-guides/chat/message-bundling-feature.md†L1-L80】

How It Works

1. User sends a message → Displayed immediately in the chat UI

2. 800ms timer starts → System waits for additional messages

3. More messages arrive → Timer resets with each new message

4. Timer expires → All queued messages sent together in one request

Visual Feedback

• "Preparing to send…" - Messages are being queued during the bundling window

• "Sending…" - Bundled messages are being transmitted to the server

Benefits

• Reduced API costs - Fewer requests mean lower costs for pay-per-request APIs

• Lower server load - Fewer requests to process and respond to

• Better mobile experience - Ideal for users who type in short bursts

• Backward compatible - Server code unchanged, same payload format

Configuration

Message bundling is enabled by default and requires no configuration. To disable for debugging:

window.wpMcpAiChatDebugMode = true;

➡️ See docs/user-guides/chat/message-bundling-feature.md for configuration options and implementation details.

🎯 Agentic Loop Token Management

NV oOS includes intelligent handling for tools that return large responses, preventing token overflow errors during agentic loops (where the AI automatically calls multiple tools).【F:docs/features/tools/presets/high-token-tool-handling.md†L1-L80】

The Problem

Tools like run_crawl4ai_job can return 100,000+ tokens of content. In agentic loops, each API call includes all previous messages, causing token counts to grow rapidly and exceed model limits (e.g., gpt-4.1-mini's 200k TPM limit).

The Solution: Three-Tier Strategy

Tier 1: Token Limit Detection

• Estimates total tokens before each API call

• Checks against model's TPM (Tokens Per Minute) limit

• Prevents requests that would exceed limits

Tier 2: Automatic Model Switching

• When limits exceeded, auto-switches to fallback model

• Default fallback: Gemini 2.0 Flash (1-2 million token capacity)

• Preserves full context without data loss

• Transparent to the user

Tier 3: Message Truncation

• If even fallback model can't handle tokens

• Truncates older messages from conversation

• Always preserves system prompts and recent context

• Logs what was truncated for debugging

Configuration

Automatic model switching is enabled by default. Configure fallback model under Settings → NV oOS:

// Default fallback model
'fallback_model' => 'gemini-2.0-flash-exp'

➡️ See docs/features/tools/presets/high-token-tool-handling.md for complete technical details and examples.

🔄 Chat Performance Optimizations

NV oOS includes several performance optimizations to enhance the chat experience:

• Message bundling - Reduces API calls by grouping rapid user inputs

• Token budget management - Prevents API limit overruns with safety margins【F:docs/features/performance/tpm-limit-validation.md†L1-L50】

• Chat history persistence - LocalStorage (24h) + optional JetEngine CCT storage【F:docs/user-guides/chat/chat-history-persistence.md†L1-L50】

• Automatic model switching - Seamlessly handles token overflow scenarios

• Rate limit protection - Intelligent retry with exponential backoff【F:docs/features/performance/rate-limit-protection.md†L1-L50】

➡️ See docs/features/chat/chat-performance-optimizations.md for detailed performance tuning guide.

🌐 Mesh Compute Routing

NV oOS includes intelligent mesh compute routing that automatically distributes AI workload across multiple sites OR multiple providers using AI-powered decision-making. This feature works in two modes:

1. Multi-Site Mesh: Distribute load across multiple WordPress installations

2. Single-Site Multi-Provider: Balance load across OpenAI, Gemini, Anthropic, NVIDIA NIM, Hugging Face, Cloudflare, and Ollama on one site

Both modes use the same AI-powered routing engine to optimize for cost, performance, and reliability.

Key Capabilities

• AI-Optimized Routing - Analyzes prompt complexity and routes to optimal provider/site

• Cost Optimization - Use GPT-4o-mini for simple queries, GPT-4o for complex tasks

• Automatic Failover - Switch providers on rate limits or outages

• Compute Hubs - Designate powerful servers for heavy workloads

• Rate Limit Management - Auto-switch to alternative providers when limits hit

• Privacy Control - Route sensitive data to local Ollama instances

Quick Start Examples

Single-Site Setup (No mesh required):

• Configure multiple AI providers (OpenAI + Gemini + Anthropic + Hugging Face + Cloudflare + Ollama)

• Set assistant routing strategy to "AI Optimized"

• Save 90% on costs by routing simple queries to cheaper models

Multi-Site Setup (Distributed compute):

• Enable mesh networking on all sites

• Designate compute hubs with larger models

• Automatic load balancing across peer sites

• Cross-server compute pooling for Cloudways, SiteGround, etc.

➡️ See docs/features/federation/mesh-routing-guide.md for complete setup guide, routing strategies, and use cases. ➡️ See docs/features/federation/mesh-compute-pooling.md for architecture and authentication details.

🔗 Federation & Discovery System

NV oOS includes a decentralized AI capability network that allows WordPress sites to publish their capabilities and discover peer sites. Think of it as "npm for AI tools" — sites can advertise what they offer and find complementary capabilities from trusted peers.

Overview

The Federation & Discovery system provides three deployment modes:

1. Publisher Mode: Publish your site's capabilities via /.well-known/ai-peer

2. Directory Mode: Run a discovery service for peer registration and search

3. Consumer Mode: Query directories to find and use peer capabilities

Quick Start

Enable Federation (Publisher Mode):

1. Navigate to Settings → NV oOS → Federation & Discovery

2. Check Enable federation

3. Configure regions (e.g., us, eu, ap) and data tags (e.g., no_pii, gdpr_ok)

4. Your capabilities are now published at https://yoursite.com/.well-known/ai-peer

Enable Directory Service (Optional):

1. In the same settings section, check Enable directory service

2. Your directory API is now available at https://yoursite.com/wp-json/ai-dir/v1

3. Automatic hourly health checks verify registered peers

Key Features

• 📡 Well-Known Endpoints - Standards-based capability publishing

• 🔍 Peer Discovery - Search by capability, region, and data policy

• ✅ Health Monitoring - Automatic cron-based peer verification

• 🏆 Smart Ranking - Scores peers by region, latency, and policy match

• 🔐 JWKS Verification - Built-in security with public key discovery

• ⚙️ Conditional Loading - Zero overhead when disabled

API Endpoints

Directory REST API (/wp-json/ai-dir/v1):

• POST /peers/register - Register a new peer

• GET /peers - List all peers with health status

• GET /peers/{id} - Get peer details

• GET /search - Search peers by capability/region/policy

• POST /reverify/{id} - Manually trigger health check

• POST /report/{id} - Report peer issues

Well-Known Endpoints:

• GET /.well-known/ai-peer - Your site's capability manifest

• GET /.well-known/jwks.json - Public keys for verification

Use Cases

Private Organization Network:

• Multiple WordPress sites within one organization

• Share AI capabilities across internal sites

• Central directory for discovery

• Private peer network with secure authentication

Public Directory Service:

• Community-run capability discovery

• Accept registrations from external sites

• Provide search API for consumers

• Build an ecosystem marketplace

Capability Consumer:

• Query public directories for needed capabilities

• Integrate with mesh router for automatic peer selection

• No need to publish your own capabilities

• Access specialized tools from the network

Configuration Options

• Regions: Geographic locations (e.g., us, eu, ap, global)

• Data Tags: Compliance policies (e.g., no_pii, gdpr_ok, hipaa_like)

• QPS Limit: Queries per second (default: 5)

• Burst Capacity: Simultaneous requests (default: 10)

➡️ Complete Documentation: docs/features/federation/federation-discovery.md ➡️ Implementation Summary: FEDERATION-IMPLEMENTATION-SUMMARY.md

🕵 Code Review

The 2025-10-31 internal review confirms the hardening of the group email automation (header filtering and attachment caps) and the case-sensitive variable handling in the OpenAI external action tool, and only flags a low-severity performance concern around guest token transient churn for public chat embeds. These findings have been consolidated into the master code review document. One follow-up action item recommends re-using or rate-limiting guest tokens to keep the options table tidy on cache-less hosts.

➡️ See docs/developer/best-practices/CODE-REVIEW-MASTER.md for the complete code quality assessment.

🔒 MCP Server Authentication

Remote MCP assistants should authenticate with Auth0-issued bearer tokens (Authorization: Bearer YOUR_TOKEN) whose audience and scope align with the values configured under Settings → NV oOS. Same-origin experiences (the dashboard editor and shortcode UI) continue to rely on the X-WP-Nonce header tied to the logged-in WordPress session. Review docs/reference/api/mcp-server-authentication.md for a complete setup guide plus a breakdown of the structured error responses returned on failure, and keep the deployment troubleshooting checklist handy when diagnosing capability or credential regressions.

MCP transports (v1.1.55+): POST /wp-json/mcp-ai/v1/mcp speaks JSON-RPC 2.0 over Streamable HTTP by default. Legacy HTTP+SSE clients (SSE-only Accept: text/event-stream or ?stream=true) get a credential-bound session handshake from GET /mcp and receive responses as event: message on the GET stream — enable with WP_MCP_AI_LEGACY_SSE_ENABLED. JSON-RPC errors return HTTP 200 with the {"jsonrpc","id","error"} envelope so agent SDKs that drop non-2xx bodies relay tool errors instead of hanging; auth/permission failures keep real HTTP statuses. Assistant credential headers may be sent as Authorization: Bearer cred_xxxxx.SECRET or raw Authorization: cred_xxxxx.SECRET. Tool-call traffic is governed by the settings-driven tool rate limiter (credential tokens exempt by default), and GET/HEAD discovery probes never consume the request quota. See docs/developer/implementation-plan-mcp-agent-compat.md and docs/developer/legacy-sse-transport-plan.md for the full rationale.

Using NV oOS as an MCP server

1. Install the plugin and create assistants. Each WordPress instance that activates NV oOS exposes an MCP-ready assistant directory backed by the ai_assistant custom post type, so every published assistant becomes available to remote clients once credentials are issued.【F:includes/assistants/class-wp-mcp-ai-assistant-cpt.php†L460-L620】

2. Configure the REST and connector settings. Populate the Auth0, model provider, and optional integration credentials under Settings → NV oOS so the REST controller can advertise the correct namespace URLs and enforce bearer tokens per your tenant, scope, and provider defaults.【F:includes/admin/class-wp-mcp-ai-admin-settings.php†L36-L118】

3. Expose the MCP directory endpoints. The REST layer publishes /assistants, /chat, /tools, and an SSE-compatible /sse handshake inside the wp-json/mcp-ai/v1 namespace, automatically scoping responses to the authenticated assistant or returning every assistant the caller may read.【F:includes/class-wp-mcp-ai-rest.php†L234-L703】 Hand-held clients can subscribe to the streaming directory event or call the JSON routes directly using the base URLs returned in the directory payload.【F:includes/class-wp-mcp-ai-rest.php†L653-L703】

4. Register any additional tools. Extend the server’s capabilities by hooking into wp_mcp_ai_register_tools and loading custom tool classes; registered slugs flow through the assistant directory and tool execution endpoint without extra wiring.【F:includes/class-wp-mcp-ai-tool-registry.php†L75-L195】

5. Verify the deployment before sharing credentials. Run wp mcp-ai remote https://example.com/wp-json/mcp-ai/v1 --token=YOUR_TOKEN from any WP-CLI environment to confirm authentication, assistant scope, and chat probes succeed before you hand tokens to operators or client teams.【F:includes/class-wp-mcp-ai-cli-command.php†L137-L220】

Operating multiple MCP deployments

Provision a separate WordPress site (or network site) for each MCP server you need, activate NV oOS, and repeat the configuration steps above with environment-specific Auth0 audiences, scopes, and provider keys. Because the assistant directory response includes the resolved REST base and namespace metadata, MCP clients can be pointed at different deployments simply by swapping the base URL and the bearer credential minted for that site’s assistants.【F:includes/admin/class-wp-mcp-ai-admin-settings.php†L48-L118】【F:includes/class-wp-mcp-ai-rest.php†L653-L703】

Sites that enable the Simple JWT Login integration can now reuse those bearer tokens alongside Auth0 credentials. The plugin validates tokens with Simple JWT Login’s native services, falls back to manual JWT decoding when the dependency cannot resolve a user, and automatically scopes REST requests to the assistant encoded in the token so cross-assistant hops are blocked with actionable errors.【F:includes/class-wp-mcp-ai-simple-jwt-login-integration.php†L47-L214】【F:includes/integrations/class-wp-mcp-ai-integration-simple-jwt.php†L240-L378】【F:includes/class-wp-mcp-ai-rest.php†L2769-L2808】

🌐 Connecting Remote MCP Clients

NV oOS works seamlessly with popular MCP clients including Claude Desktop, LM Studio, and ChatGPT connectors. Each client connects to your WordPress site via the MCP REST API at /wp-json/mcp-ai/v1 and can access assistants, execute tools, and interact with your WordPress data remotely.

SSE Support: All MCP endpoints support Server-Sent Events (SSE) for real-time streaming. Enable SSE in your client configuration for better response times and real-time updates. See the SSE Streaming Support section for details.

Quick Start

1. Generate an assistant credential from any published assistant's API Credentials meta box

2. Copy the token (format: cred_xxxxx.SECRET) — shown only once!

3. Configure your MCP client with your site's base URL and the credential

4. Test the connection using the provided test script or WP-CLI command

Claude Desktop setup

Claude Desktop supports MCP servers through a JSON configuration file. Add your WordPress site:

{
  "mcpServers": {
    "wordpress-site": {
      "url": "https://your-site.com/wp-json/mcp-ai/v1",
      "headers": {
        "Authorization": "Bearer cred_xxxxx.SECRET"
      },
      "sse": true
    }
  }
}

See the complete Claude Desktop setup guide and example configurations for multi-assistant deployments.

LM Studio Setup

⚠️ Having SSE content-type errors? Use the JSON-RPC endpoint instead!

LM Studio can connect using two methods:

Method 1: JSON-RPC (Recommended - No SSE)

Use this if you're getting SSE error: Invalid content type, expected "text/event-stream":

{
  "servers": [
    {
      "id": "wordpress-mcp",
      "name": "WordPress Site",
      "url": "https://your-site.com/wp-json/mcp-ai/v1/mcp",
      "auth": {
        "type": "bearer",
        "token": "cred_xxxxx.SECRET"
      },
      "timeout": 30000
    }
  ]
}

Configure in LM Studio:

• Server Name: WordPress Site

• URL: https://your-site.com/wp-json/mcp-ai/v1/mcp

• Auth Type: Bearer Token

• Token: cred_xxxxx.SECRET

• Do NOT enable SSE

Method 2: SSE Streaming (Optional)

If you want to use SSE for real-time updates:

• Base URL: https://your-site.com/wp-json/mcp-ai/v1

• Enable SSE: ✓ (checked)

• SSE Endpoint: /sse

See the complete LM Studio setup guide and example configurations:

• lmstudio-mcp-without-sse.json - Recommended

• lmstudio-config.json - With SSE

ChatGPT connector setup

⚠️ Note: ChatGPT connectors currently require Auth0 authentication. Assistant-issued credentials are not yet supported by OpenAI's ChatGPT platform.

To connect via ChatGPT:

1. Configure Auth0 in Settings → NV oOS

2. Generate an Auth0 access token with the configured audience

3. Add the MCP server in ChatGPT's connector settings

See the ChatGPT connector guide for detailed Auth0 setup steps.

Testing your connection

Use the built-in test script to verify connectivity:

./bin/test-remote-connection.sh \
  -u https://your-site.com/wp-json/mcp-ai/v1 \
  -t cred_xxxxx.SECRET

Or use WP-CLI:

wp mcp-ai remote https://your-site.com/wp-json/mcp-ai/v1 \
  --token=cred_xxxxx.SECRET

Expected output confirms the server is reachable and lists available assistants.

Complete documentation

For comprehensive setup guides, troubleshooting, and advanced configurations, see:

• MCP Client Configurations – ⭐ NEW: Complete guide for all MCP clients (LM Studio, Claude Desktop, Cursor, Continue.dev, Cline, OpenAI)

• Remote Client Setup Guide – Step-by-step instructions for Claude Desktop, LM Studio, and ChatGPT

• MCP Server Authentication – Authentication methods and credential management

• REST API Reference – Endpoint documentation and payload examples

• Example Configurations – Ready-to-use config files for all major MCP clients

🎫 Token Management UI

NV oOS 1.0.0 introduces a centralized Token Manager for managing all external agent access tokens across your assistants. Access it via NV oOS → Token Manager in the admin menu.

Features

• Centralized Control - Manage all assistant credentials in one place

• Security Best Practice - Tokens shown only once after creation (cannot be retrieved later)

• Lifecycle Management - Create, view, revoke, and delete credentials

• Audit Trail - Track who created/revoked each token and when

• Metadata Display - See creation date, status (active/revoked), associated assistant

• Bulk Visibility - View credentials across all assistants at a glance

How It Works

The Token Manager follows industry standards similar to GitHub Personal Access Tokens, Stripe API keys, and Auth0 credentials:

1. Create Token - Generate new credentials from the assistant editor

2. Copy Immediately - Token shown once and cannot be retrieved later

3. Use in MCP Clients - Configure external applications (Codex CLI, MCP clients, custom integrations)

4. Revoke When Needed - Disable compromised tokens without deleting audit history

5. Delete When Done - Permanently remove tokens and all metadata

Security Notes

• Tokens are hashed before storage (only hash stored, never plaintext)

• Requires manage_options capability

• All actions logged with user attribution

• Revoked tokens cannot be reactivated (must create new)

• HTTPS strongly recommended for token transmission

Usage Example

# In assistant editor: Create credential → Copy token immediately
# Token format: cred_[YOUR_PREFIX].[YOUR_SECRET_KEY_HERE]
# Example format only - never share real tokens!

# Configure MCP client (e.g., Codex CLI)
export WPOOS_BEARER_TOKEN="your_token_here"
codex chat --assistant 123 "Hello world"

# Later: Revoke from Token Manager UI if compromised
# Or: Delete entirely when integration removed

⚠️ Security Warning: The examples above use placeholder tokens. Never share real tokens publicly or commit them to version control.

Access Requirements

• Capability: manage_options (administrators only)

• Menu Location: NV oOS → Token Manager

• REST API: /wp-json/mcp-ai/v1/token-manager/*

For complete documentation, see Token Management Guide.

🤖 ChatGPT Connector

OpenAI’s ChatGPT connector beta currently authenticates exclusively through Auth0. Because NV oOS issues its own assistant-scoped bearer credentials, you can connect LM Studio, Claude Desktop, and other MCP-aware clients today, while ChatGPT support will require either Auth0 bridging or native bearer support from OpenAI. We’ll update this section as soon as ChatGPT adds compatibility with first-party tokens.【F:docs/reference/api/mcp-server-authentication.md†L22-L46】

🛰 REST API Endpoints

All front-end chat surfaces ultimately call the MCP REST namespace at /wp-json/mcp-ai/v1, which exposes dedicated endpoints for chat completions and direct tool execution. Both routes share the same authentication rules described above: supply an Auth0 bearer token, a plugin-issued assistant credential, or a WordPress REST nonce for same-origin requests. Guest tokens issued by the shortcode or Elementor widget continue to be honoured when allow_guests="true" is enabled.【F:includes/class-wp-mcp-ai-rest.php†L230-L322】【F:includes/class-wp-mcp-ai-rest.php†L289-L343】【F:includes/class-wp-mcp-ai-rest.php†L1288-L1336】

• GET /assistants – Returns a directory of accessible assistants with provider defaults, tool counts, capability metadata, and implementation details so remote clients can choose which assistant to call. Credential tokens are automatically scoped to their issuing assistant while Auth0 tokens and REST nonces surface every published assistant the caller can read.【F:includes/class-wp-mcp-ai-rest.php†L238-L666】 The endpoint also supports Server-Sent Events for MCP clients that expect streaming discovery payloads, emitting a single directory event with cache-busting headers before closing the stream.【F:includes/class-wp-mcp-ai-rest.php†L1690-L1772】

• GET /sse – Mirrors the assistant directory response but forces a Server-Sent Events handshake so MCP clients that negotiate /sse subscriptions receive the streaming directory payload without additional query parameters.【F:includes/class-wp-mcp-ai-rest.php†L400-L715】

• POST /chat – Normalises structured messages, injects assistant defaults, auto-enables the Submit Document Prompt tool when uploads are present, and forwards the request through the language model router. Responses include the assistant ID and the raw provider payload so clients can stream or render messages as needed.【F:includes/class-wp-mcp-ai-rest.php†L230-L322】【F:includes/class-wp-mcp-ai-rest.php†L931-L1095】

• POST /tools – Executes a specific registered tool outside of a chat turn. The endpoint enforces assistant tool allowlists, scopes credential-based requests to the issuing assistant, merges assistant defaults (such as external action identifiers), and returns the tool result with execution metadata.【F:includes/class-wp-mcp-ai-rest.php†L264-L322】【F:includes/class-wp-mcp-ai-rest.php†L1162-L1321】

See docs/reference/api/rest-api.md for payload examples, attachment handling rules, and troubleshooting tips when integrating custom clients.

🌊 SSE Streaming Support

NV oOS includes comprehensive Server-Sent Events (SSE) support for real-time streaming responses, enabling faster perceived response times and better user experience.

What is SSE?

Server-Sent Events provide unidirectional server-to-client streaming over HTTP, allowing the server to push updates as they become available rather than waiting for the complete response.

Benefits:

• ⚡ Faster perceived response time - Users see content immediately as it's generated

• 🔄 Real-time updates - Progressive loading for long-running operations

• 📶 Connection keep-alive - Prevents timeouts during lengthy responses

• 🎯 Better UX - ChatGPT-style typing effect for AI responses

SSE-Enabled Endpoints

1. Assistant Directory Streaming (GET /assistants)

Stream the assistant directory for MCP clients expecting SSE handshakes:

curl -H "Accept: text/event-stream" \
  https://your-site.com/wp-json/mcp-ai/v1/assistants

The endpoint emits a single directory event with all accessible assistants, then closes the connection.

2. Dedicated SSE Endpoint (GET /sse)

Force SSE mode for MCP clients that specifically probe the /sse endpoint:

curl https://your-site.com/wp-json/mcp-ai/v1/sse

This mirrors the /assistants response but always uses SSE format, ensuring compatibility with LM Studio and Claude Desktop.

3. Job Status Streaming (GET /jobs/{job_id}/stream)

Subscribe to real-time updates for async operations like Crawl4AI jobs:

const eventSource = new EventSource(
    `/wp-json/mcp-ai/v1/jobs/${jobId}/stream?max_duration=300&poll_interval=2`
);

eventSource.addEventListener('status', (e) => {
    const status = JSON.parse(e.data);
    console.log('Progress:', status.progress + '%');
});

eventSource.addEventListener('complete', (e) => {
    console.log('Job finished:', e.data);
    eventSource.close();
});

SSE Configuration

Enable POST Method for SSE (LM Studio Compatibility)

By default, SSE uses the standard GET method. For clients with SSE bugs (like LM Studio), enable POST support:

1. Go to Settings → NV oOS → Assistant Settings

2. Enable "Enable POST Method on SSE Endpoint"

3. Save settings

⚠️ Note: Standard SSE specification uses GET. Only enable POST if you experience client compatibility issues.

Modern SSE Features (2024-2025)

The SSE implementation includes current best practices:

• Automatic reconnection with retry: directive (3-second interval)

• Event IDs for tracking reconnection state

• HTTP/2 compatibility for multiplexing

• Proper CORS headers for cross-origin requests

• Cache-Control directives to prevent proxy buffering

• Heartbeat messages to keep connections alive

Frontend Integration

Enable SSE streaming in your JavaScript client:

// Request streaming in chat
const response = await fetch('/wp-json/mcp-ai/v1/chat', {
    method: 'POST',
    headers: {
        'Content-Type': 'application/json',
        'Accept': 'text/event-stream',
        'X-WP-Nonce': wpMcpAi.nonce
    },
    body: JSON.stringify({
        assistant_id: 123,
        messages: [{ role: 'user', content: 'Hello' }],
        stream: true
    })
});

// Process SSE stream
const reader = response.body.getReader();
const decoder = new TextDecoder();
let buffer = '';

while (true) {
    const { done, value } = await reader.read();
    if (done) break;
    
    buffer += decoder.decode(value, { stream: true });
    const events = buffer.split('\n\n');
    buffer = events.pop();
    
    for (const event of events) {
        if (event.startsWith('data: ')) {
            const data = JSON.parse(event.substring(6));
            // Update UI with streaming chunk
            updateChatUI(data);
        }
    }
}

Documentation

For complete SSE implementation details, configuration options, and troubleshooting:

• SSE Streaming Guide - Complete implementation guide with code examples

• MCP and SSE - Understanding SSE benefits for MCP protocol

• Job Notification System - Real-time job status via SSE

• REST API Reference - SSE endpoint specifications

📝 MCP JSON-RPC 2.0 Endpoint

NV oOS implements a dedicated /mcp endpoint that follows the Model Context Protocol specification version 2024-11-05 using JSON-RPC 2.0 for bidirectional communication with AI assistants and tools.【F:docs/reference/api/mcp-endpoint.md†L1-L80】

MCP Version: 2024-11-05
Compliance: Full MCP 2024-11-05 — all 11 protocol methods, OAuth 2.1, Streamable HTTP, JSON-RPC batching, tool annotations, session management

What's New in MCP 2024-11-05

The latest specification is fully implemented:

• OAuth 2.1 Security: PKCE, token rotation, mandatory HTTPS

• Streamable HTTP Transport: Better reconnection and bidirectional communication

• JSON-RPC Batching: Efficient parallel task processing (up to 20 messages per batch)

• Tool Annotations: readOnlyHint, destructiveHint, idempotentHint, openWorldHint metadata

• Progress Notifications: Descriptive status updates during tool execution

• Completions: Argument autocompletion for tools and prompts

• Session Management: State recovery via Mcp-Session-Id header (1h TTL)

• Logging: Client-controlled log verbosity via logging/setLevel

• Cancellation: Request cancellation via notifications/cancelled

Endpoint URL

POST /wp-json/mcp-ai/v1/mcp

JSON-RPC 2.0 Format

All requests must use standard JSON-RPC 2.0 format:

{
  "jsonrpc": "2.0",
  "id": "unique-request-id",
  "method": "initialize",
  "params": {}
}

Supported Methods

• initialize - Initialize MCP connection and retrieve server capabilities

• ping - Server liveness check

• tools/list - List available tools with annotations for the authenticated assistant

• tools/call - Execute a specific tool with progress notifications support

• resources/list - List available resources (knowledge files, etc.) with metadata

• resources/read - Read resource content by URI with MIME-typed responses

• prompts/list - List available prompt shortcuts

• prompts/get - Get full prompt content with system instructions and argument values

• completion/complete - Argument autocompletion (enum/boolean for tools, slug matching for prompts)

• logging/setLevel - Client-controlled log verbosity (8 standard levels)

• notifications/cancelled - Cancel a pending request

Authentication (OAuth 2.1 Enhanced)

The MCP endpoint uses enhanced authentication aligned with MCP 2024-11-05 security standards:

• WordPress Nonce (X-WP-Nonce header)

• Bearer Tokens (Authorization: Bearer <token>) with rotation support

• Assistant Credentials (generated from assistant editor, OAuth 2.1 compliant)

• Auth0 JWT (for enterprise authentication)

• Session Management (Mcp-Session-Id header for reconnection)

Error Handling

Enhanced Error System (Phase 3):

• Severity Levels: CRITICAL, ERROR, WARNING, INFO, DEBUG for categorized logging

• User-Friendly Messages: Automatic translation of technical errors into actionable guidance

• Recovery Suggestions: Built-in troubleshooting steps for common failure scenarios

• Centralized Error Handler: Consistent error creation with automatic logging

• Comprehensive Logging: Track errors, tool executions, and chat interactions

• Sensitive Data Protection: Automatic redaction of API keys and tokens in logs

See Error Handling Documentation for detailed usage.

MCP Standard Error Codes:

• -32700: Parse error (invalid JSON)

• -32600: Invalid Request (malformed JSON-RPC)

• -32601: Method not found

• -32603: Internal error

Use Cases

Learn More

➡️ Complete MCP Documentation:

• MCP Endpoint Reference - Complete method documentation and 2024-11-05 features

• MCP and SSE Explained - Understanding transport layers and protocol updates

• MCP Server Authentication - OAuth 2.1 and security enhancements

• MCP Client Configurations - Connect LM Studio, Claude Desktop, etc.

• Official MCP Specification 2024-11-05

🛠 Assistant Editor Overview

Assistant posts ship with dedicated controls that map directly to runtime behaviour:

• Available Tools – Choose which registered tools (core, WooCommerce, JetEngine, or custom) the model may invoke. Dependency-aware notices explain why certain tools are unavailable, and you can now disable the pre-built prompt shortcuts that tools normally contribute.

• Quick Tool Selection Presets – one-click presets group the current live registry by use-case (🤖 Agentic Workflow, 🛒 E-commerce, ⚕️ Healthcare, 💬 Communication, 💻 Development, 📋 Registration & Compliance, and more). Click a preset to add its tools to the current selection; click again to remove them. Combine multiple presets freely. Use ✓ Select All / ✗ Clear All for bulk actions. Implemented in includes/helpers/class-wp-mcp-ai-tool-presets-helper.php.

• Model Defaults – Provide assistant-specific overrides for the OpenAI model, temperature (0–2), and system prompt applied to every conversation.

• Base Knowledge – Attach Media Library items that are chunked, truncated, and streamed as memory context, and optionally store an external Vector Store ID to coordinate retrieval workflows.

• Prompt Shortcuts – Capture labelled prompts with optional descriptions and tool affinities; they render as accessible quick actions in the chat UI so operators can seed conversations instantly.【F:includes/assistants/class-wp-mcp-ai-assistant-cpt.php†L893-L1048】【F:includes/class-wp-mcp-ai-shortcode.php†L430-L693】【F:assets/js/chat.js†L600-L666】

If an API or shortcode request omits the assistant parameter, the plugin automatically uses the default assistant configured in the global settings.

📊 Assistant Storage: CPT vs CCT

NV oOS uses a Custom Post Type (CPT) as the primary storage for AI assistants, with automatic synchronization to a JetEngine Custom Content Type (CCT) when JetEngine is available.

Storage Architecture

• CPT (mcp_ai_assistant): The authoritative source for all assistant data

  • Full-featured WordPress editor with 14 meta fields

  • Supports credentials, shortcuts, memory files, and advanced features

  • Always available in both Base and Full versions

  • Primary REST endpoint: /wp-json/mcp-ai/v1/

• CCT (assistants): Synchronized secondary storage (Full Version only)

  • Receives automatic updates when CPT is saved

  • 7 basic fields: title, description, provider, model, system_prompt, temperature, tools

  • Available via JetEngine REST endpoint: /wp-json/jet-cct/assistants

  • Ideal for JetEngine-based integrations and queries

Automatic Synchronization (v1.0.0+)

When you save an assistant through the WordPress admin:

1. CPT is updated with all settings

2. CCT is automatically synced (if JetEngine is active)

3. Link is maintained via _wp_mcp_ai_cct_item_id meta

4. Deletion cascades - removing CPT also removes linked CCT item

What gets synced: Basic configuration (title, description, provider, model, system_prompt, temperature, tools)
What's CPT-only: Advanced features (credentials, shortcuts, memory files, role rules, vector store, external actions)

When to Use Each Endpoint

Use CPT endpoint (/wp-json/mcp-ai/v1/) for:

• Chat, tools, and directory interactions

• Full assistant configuration access

• Credential-based authentication

• Primary integration scenarios

Use CCT endpoint (/wp-json/jet-cct/assistants) for:

• JetEngine-specific queries and filters

• Building JetEngine relations

• Integrating with JetEngine dashboards

• Querying basic assistant metadata

➡️ Read the complete CPT vs CCT guide for detailed comparisons, code examples, and migration information.

⚡ Assistant Tool Shortcuts

Every assistant exposes a Prompt Shortcuts meta box so editors can curate prewritten instructions, scope them to registered tools, and add operator-facing descriptions that appear as tooltips and screen reader hints in the chat UI.【F:includes/assistants/class-wp-mcp-ai-assistant-cpt.php†L893-L1048】【F:includes/class-wp-mcp-ai-shortcode.php†L430-L693】【F:assets/js/chat.js†L600-L666】 The shortcode merges these custom prompts with each tool’s declared shortcut tasks and always appends a safe fallback so assistants remain usable even without bespoke entries.【F:includes/class-wp-mcp-ai-shortcode.php†L430-L693】

Developers can extend or replace these prompts with filters such as wp_mcp_ai_assistant_custom_tool_shortcuts and wp_mcp_ai_default_tool_shortcut, letting sites tailor default quick actions per assistant or environment.【F:includes/class-wp-mcp-ai-shortcode.php†L444-L692】

➡️ Read the full guide to assistant prompt shortcuts.

🧠 Agent Skills

Agent Skills (agentskills.io) are reusable, portable behaviour packages that extend any assistant without touching its system prompt. Each skill is a SKILL.md file — a standard Markdown document with a small YAML frontmatter block — that lives in wp-content/uploads/mcp-ai-skills/{skill-name}/SKILL.md. When an assistant loads a skill, its instructions are automatically injected into the conversation context so the model knows exactly when and how to use that capability.

67 Pre-Built Skills (Base Plugin)

The base plugin ships with 67 pre-built skills that are automatically installed to wp-content/uploads/mcp-ai-skills/ on first activation. No Pro add-on is required — they are available on every install out of the box. The skills include 24 general-purpose tools (document handling, design, testing), 22 WordPress developer skills (security, APIs, plugin patterns), 21 design-* skills (analytics through video creation), and the bundled mcp-ai-wpoos-plugin skill.

How Skills Are Loaded

Skills are selected per-assistant via the Skills meta box in the assistant editor. Whichever skills are checked, their combined instructions are prepended to the system prompt under an # Active Skills heading at inference time. This means skills are composable — you can combine pdf + xlsx + doc-coauthoring on a single document-specialist assistant.

Skills are stored as plain text files and can be customised in-place. The original bundled content can be restored at any time from Settings → Advanced → Skill Management → Force Reinstall Bundled Skills.

Managing Skills

Base plugin — Skill management is available under Settings → Advanced → Skill Management:

• View installed skills and their metadata

• Refresh the skill index

• Install or force-reinstall the 16 bundled skills

Pro add-on — The dedicated Skill Manager admin page (Assistants → Skill Manager) adds:

• Upload a SKILL.md file or a ZIP archive containing a skill directory

• Install a skill from a remote URL

• Inline CodeMirror editor to create or edit SKILL.md content directly in the browser

• Delete / uninstall skills

SKILL.md Format

---
name: my-skill
description: One-line description of what this skill does.
compatibility: claude-3-5-sonnet, claude-3-opus
---

# My Skill

Detailed instructions for the model go here in standard Markdown.
Use headings, lists, code blocks — whatever best conveys the behaviour.

The name field (max 64 chars) becomes the skill's slug. The description field (max 1 024 chars) is shown in the admin UI. The compatibility field is optional and informational.

➡️ See Agent Skills reference for the complete specification, filters, and developer API.

👔 Professional & Team Layers

NV oOS includes an enterprise-grade template system for rapid assistant deployment through Professions and Teams. Instead of manually configuring each assistant from scratch, administrators can:

1. Select from ~311 pre-built professional templates spanning 12 industry categories

2. Create custom profession templates with reusable configurations

3. Deploy entire teams of specialized assistants with one click

4. Test everything from the backend before exposing to end users

🎓 Professional Templates

Professions are reusable assistant templates with pre-configured:

• Role descriptions and expertise areas

• Default tools curated for each profession

• Knowledge bases with industry-specific best practices

• AI model defaults (provider, model, temperature)

• Warnings and disclaimers for professional contexts

Available Categories (~311 professions across 12 categories):

Methodology note: the current sanity check counts 311 profession knowledge documents; runtime availability can vary with seeders, filters, and installed features.

• 🌾 Agriculture & Natural Resources

• 🎨 Art, Media & Entertainment

• 💼 Business & Finance

• 🎓 Education

• 🏥 Healthcare & Medicine

• ⚖️ Law & Public Safety

• 🔬 Science & Engineering

• 🍽️ Service Industry

• 💻 Technology

• 🔧 Trades & Manual Labor

• 🚚 Transportation

• 📋 Miscellaneous

Example Professions:

• Software Developer, Web Developer, Data Scientist

• Accountant, Financial Advisor, Marketing Consultant

• Registered Nurse, Physician, Pharmacist

• Attorney, Paralegal, Mediator

• Content Writer, Graphic Designer, Social Media Manager

• And ~180 more, depending on active seeders and installed features...

Creating Assistants from Templates

Navigate to AI Assistants → Add New to browse the visual profession grid:

1. Browse by category or search for a specific role

2. Click "Create" on any profession to open a customization modal

3. Customize the assistant name and AI settings (or use defaults)

4. Deploy your configured assistant instantly

Each profession template includes:

• Pre-written system prompts with role-specific expertise

• Curated tool selections appropriate for the profession

• Industry knowledge bases and best practices

• Recommended model settings for optimal performance

👥 Team Deployments

Teams group multiple professionals for coordinated workflows. Deploy an entire team of specialists with one click:

Pre-Built Teams:

• Engineering Team - Software, Mechanical, Electrical, Civil Engineers

• Pharmaceutical Development Team - Pharmacist, Researcher, Clinical Pharmacologist, Regulatory Affairs

• Research & Data Science Team - Data Scientist, Research Scientist, Statistician, Computer Scientist

• Marketing & Growth Team - Marketing Consultant, Content Creator, Graphic Designer, Business Consultant

Team Features:

• Centralized configuration - Set provider, model, and temperature for all team members

• One-click deployment - Creates all team member assistants simultaneously

• Consistent settings - Team defaults override individual profession defaults

• Custom teams - Create your own teams with any combination of professions

Navigate to Teams → Add Team to deploy a pre-configured team or create custom team combinations.

🧪 Backend Testing

Test assistants, professions, and teams directly from the WordPress admin before deploying to end users:

Test Assistant (Admin → AI Assistants → Test Assistant)

• Full feature parity with frontend chat interfaces

• All tools enabled including sensitive/restricted tools (admin-only)

• File upload support with complete MIME type configuration

• Transcript saving for debugging and analysis

• Tool shortcuts pre-loaded from assistant configuration

• Streaming responses with real-time feedback

Test Profession (Admin → Professions → Test Profession)

• Preview profession templates before creating assistants

• Validate role descriptions and expertise areas

• Test default tool selections in live conversations

• Verify knowledge base content and accuracy

• Assess AI model performance with profession-specific tasks

Test Team (Admin → Teams → Test Team)

• Test entire teams before deployment

• Validate team member coordination and role separation

• Verify shared settings propagate correctly

• Multi-assistant conversations to test team dynamics

• Performance benchmarking across team members

Security Note: All test pages require manage_options capability and are restricted to WordPress administrators. Sensitive tools are enabled in test environments because administrators already have full site access.

Documentation:

• Test Assistant Feature Enhancements - Complete testing capabilities guide

• Dynamic Assistant Creation System - Visual guide to profession and team architecture

Custom Professions & Teams

Administrators can create custom profession templates and teams:

Create Custom Profession:

1. Navigate to Professions → Add New

2. Set title, description, and category

3. Define expertise areas and role description

4. Select default tools from the registry

5. Add knowledge base content

6. Configure AI model defaults

7. Publish for use in assistant creation

Create Custom Team:

1. Navigate to Teams → Add New

2. Set team name and description

3. Select profession members from your library

4. Configure team-wide defaults (provider, model, temperature)

5. Publish to enable one-click team deployment

Benefits

For Organizations:

• ✅ Rapid assistant deployment without manual configuration

• ✅ Consistent configurations across similar roles

• ✅ Template library grows with your organization

• ✅ Share profession templates across sites

• ✅ Professional-grade assistant quality out of the box

For Administrators:

• ✅ Test everything safely from the backend

• ✅ No coding required for template-based assistants

• ✅ Visual template selection interface

• ✅ Reusable configurations reduce errors

• ✅ Full control over custom templates

For Developers:

• ✅ JSON-based knowledge base system

• ✅ Extensible via filters and hooks

• ✅ WordPress standard CPT architecture

• ✅ REST API access for profession and team data

• ✅ Automated seeding from knowledge base files

🔑 Assistant API credentials

Administrators can issue per-assistant access tokens from the API Credentials meta box that appears on every assistant edit screen. Tokens are only available to users with the manage_options capability, surface the credential history in a table, and expose one-click revoke and delete actions for rapid cleanup.【F:includes/assistants/class-wp-mcp-ai-assistant-cpt.php†L483-L595】 When you click Generate Credential the plugin produces a single-use token in the form cred_xxxxx.SECRET, hashes the secret server-side, and records the issuer so you have an audit trail of who created each credential.【F:includes/class-wp-mcp-ai-credentials.php†L94-L135】

Remote integrations can authenticate by sending that token in the standard Authorization: Bearer header—no Auth0 dependency required. The REST layer validates the credential, emits structured errors when a token is revoked or malformed, and scopes the request to the assistant that issued the token so clients cannot hop between assistants without an explicit credential for each one.【F:includes/class-wp-mcp-ai-rest.php†L316-L444】【F:includes/class-wp-mcp-ai-rest.php†L1282-L1321】【F:includes/class-wp-mcp-ai-credentials.php†L242-L297】

🐳 Local Development with Docker

Spin up a disposable WordPress instance that mounts the plugin source directly into the container:

docker compose up -d

• WordPress will be available at http://localhost:8000.

• The plugin source in this repository is mounted to /var/www/html/wp-content/plugins/mcp-ai-wpoos inside the container, so edits on your machine are reflected immediately.

• The MySQL service is provisioned with the wordpress database, user, and password (wordpress / wordpress).

Visit the site in your browser to complete the standard WordPress installation flow, using the database credentials above when prompted. When you're finished developing, stop the stack with docker compose down.

🔁 Codex environment startup script

If you are working inside an OpenAI Codex environment, add bin/codex-startup.sh to your workspace start-up tasks so a fresh WordPress install is provisioned automatically for every session — no Docker required.

bin/codex-startup.sh

The script performs the following steps:

• Downloads WP-CLI locally (if necessary) and uses it to fetch the latest WordPress core files into .codex-wordpress/wordpress.

• Installs the SQLite Database Integration plugin so WordPress can run without a MySQL server.

• Symlinks this repository into the new install's wp-content/plugins/mcp-ai-wpoos directory.

• Installs Composer development dependencies (when available) and provisions the WordPress test suite so composer run test works immediately.

• Runs wp core install, activates the NV oOS plugin, enables pretty permalinks, and sets a default site tagline.

• Boots a development server on port 8000 via wp server and logs output to .codex-wordpress/wp-server.log.

Default credentials:

Override any of these values by exporting the environment variables WORDPRESS_URL, WORDPRESS_TITLE, WORDPRESS_ADMIN_USER, WORDPRESS_ADMIN_PASSWORD, WORDPRESS_ADMIN_EMAIL, or WORDPRESS_PORT before running the script.

🧑‍💻 Development Tooling

Install the PHP development dependencies (including PHP_CodeSniffer, the WordPress Coding Standards ruleset, and PHPUnit) with:

bin/setup-dev.sh

The script runs composer install and makes the following Composer scripts available:

These commands automatically resolve the bundled vendor/bin tools (such as phpcs, phpcbf, and phpunit), so a global installation is no longer required.

NPM Dependencies & Bundling

For details on how NPM dependencies are managed and bundled for both the base plugin and Pro addon, see DEPENDENCIES_BUNDLING.md.

Quick Reference:

• Base plugin dependencies: @microsoft/fetch-event-source, dompurify, marked, ky, chart.js, @neplex/vectorizer, @langchain/*, @mlc-ai/web-llm

• Build commands: npm run build:js, npm run install:chartjs, npm run install:vectorizer, npm run build:js:pro

• Pro addon has separate addons/pro/package.json for Pro-specific dependencies

📦 NPM Packages

Twenty-three standalone browser-utility packages have been extracted from the oOS chat UI and published to the NPM registry under the @nvdigitalsolutions scope. Each package is independently usable in any JavaScript/TypeScript project (no WordPress required).

Installation

# Tier 1 — Core utilities
npm install @nvdigitalsolutions/nvoos-storage
npm install @nvdigitalsolutions/nvoos-markdown marked dompurify
npm install @nvdigitalsolutions/nvoos-events @microsoft/fetch-event-source
npm install @nvdigitalsolutions/nvoos-types

# Tier 2 — Extended browser utilities
npm install @nvdigitalsolutions/nvoos-http-client ky
npm install @nvdigitalsolutions/nvoos-clipboard
npm install @nvdigitalsolutions/nvoos-offline-sync
npm install @nvdigitalsolutions/nvoos-sse-client
npm install @nvdigitalsolutions/nvoos-api
npm install @nvdigitalsolutions/nvoos-attachments

# Tier 3 — Chat UI utilities
npm install @nvdigitalsolutions/nvoos-slash-commands
npm install @nvdigitalsolutions/nvoos-audio
npm install @nvdigitalsolutions/nvoos-dom-batcher
npm install @nvdigitalsolutions/nvoos-chat-bubble
npm install @nvdigitalsolutions/nvoos-chat-memory
npm install @nvdigitalsolutions/nvoos-chat-memory-ui
npm install @nvdigitalsolutions/nvoos-cron-status
npm install @nvdigitalsolutions/nvoos-vad
npm install @nvdigitalsolutions/nvoos-transcription

# Tier 4 — AI runtime utilities
npm install @nvdigitalsolutions/nvoos-client-tools
npm install @nvdigitalsolutions/nvoos-llm-worker
npm install @nvdigitalsolutions/nvoos-model-loader
npm install @nvdigitalsolutions/nvoos-transformers-client

Publishing

Two GitHub Actions workflows handle NPM publishing automatically:

Setup — only one secret is required: add an NPM_TOKEN to the repository at Settings → Secrets and variables → Actions.

Adding a new package: update the PACKAGES environment variable in both workflow files and place the package directory under packages/.

See packages/README.md for a full package listing and API overview, and packages/QUICK_START.md for usage examples.

🧪 Testing & QA

• composer run test executes the PHPUnit suite bundled with wp-phpunit/wp-phpunit and Yoast’s polyfills, covering REST, tooling, and helper contracts.【F:composer.json†L16-L23】

• Run composer run test:install once per environment to provision the WordPress test scaffolding before the first test pass.【F:composer.json†L16-L23】

• For offline or air-gapped environments, use ./bin/package-vendor-dev.sh to create a downloadable test framework package (~140 MB), then ./bin/install-vendor-dev.sh to deploy it without requiring composer or internet access.

Coding standards & static analysis

• Enforce the WordPress Coding Standards with composer run lint; auto-fix what you can with composer run format.【F:composer.json†L16-L23】

• Validate cross-version compatibility (PHP 7.4–8.3) via composer run lint:compat prior to release builds.【F:composer.json†L16-L23】

Manual smoke tests

• Follow the scenarios in ## ✅ Manual QA Scenarios after significant changes to chat flows, tool execution, or authentication wiring.

• For logging-centric debugging, enable logging in the NV oOS settings and reference the retrieval commands in 🪵 Logging.

⚙ CI/CD Pipelines

The repository runs ~30 automated GitHub Actions workflows on every push and PR:

💬 Frontend Shortcode

Embed a published assistant anywhere on the site with the shortcode. Replace 123 with the post ID of the assistant you created under AI Assistants.

[mcp_ai_chat assistant="123"]

How it works

• The shortcode renders a lightweight chat UI that talks to the plugin's REST API endpoints.

• Scripts and styles are enqueued automatically and include REST nonces plus the selected assistant ID.

• Responses are displayed inline, including tool invocation feedback when the model requests a registered tool.

Requirements

• The assistant post must be published and, by default, the current user must have the edit_posts capability (matching the REST permission check). Add allow_guests="true" to the shortcode when you want anonymous visitors to participate in the chat.

• An OpenAI API key and default model must be configured in Settings → NV oOS.

Tips

• Omit the assistant attribute to fall back to the default assistant configured in the settings screen.

• Multiple shortcodes can be added to the same page; each chat instance maintains its own conversation context on the client.

• Use allow_guests="true" to expose the chat UI to logged-out visitors. Each render issues a short-lived guest token that authorises REST requests without a WordPress login.

• REST interactions rely on the [wp_rest] nonce, so caching plugins should avoid caching pages for logged-in editors running the chat.

Elementor widget

• Elementor sites automatically gain an NV oOS Chat widget that mirrors the shortcode controls, including the optional assistant selector and the guest access toggle.【F:includes/elementor/class-wp-mcp-ai-elementor-widget.php†L17-L109】

• Leaving the assistant control blank falls back to the default assistant configured in the plugin settings, and enabling Allow Guests injects the same temporary tokens used by the shortcode flow.【F:includes/elementor/class-wp-mcp-ai-elementor-widget.php†L45-L110】【F:includes/class-wp-mcp-ai-shortcode.php†L132-L224】

• The Elementor chat widget can surface everything saved on the assistant post—model defaults, knowledge files, prompt shortcuts, and assigned tools—so you can build documentation and dashboards without copying values manually.【F:includes/elementor/class-wp-mcp-ai-elementor-widget.php†L95-L845】

🧵 REST Chat Payloads & Attachments

The /wp-json/mcp-ai/v1/chat endpoint accepts rich, multi-part messages. Each message object still requires a role, but the content may now be either a plain string or an array of structured segments that map to OpenAI's multimodal contract.

{
  "assistant_id": 123,
  "messages": [
    {
      "role": "user",
      "content": [
        { "type": "text", "text": "Describe this photo" },
        { "type": "input_image", "attachment_id": 456, "detail": "high" }
      ]
    }
  ],
  "options": {
    "response_format": { "type": "json_schema", "json_schema": { "name": "caption" } }
  }
}

Supported segment types

• text – Free-form text (text property). Strings supplied directly to content are automatically wrapped in this format. For backwards compatibility, existing input_text payloads sent to the REST API are still accepted and normalised to the new schema.

• input_image – Reference an uploaded WordPress attachment (attachment_id) or provide a remote url. Optional detail hints (low, auto, high) and caption fields are preserved. (Fixed in v1.0.0: Chat client attachments now properly processed)

• input_file – Reference an uploaded attachment that should be streamed to the model. (Fixed in v1.0.0: Chat client file attachments now properly processed)

The REST controller validates attachment ownership/permissions, enforces a default 5 MB size cap (filterable via wp_mcp_ai_max_attachment_bytes), and only allows safe MIME types by default. Text and structured data formats include Markdown, CSV/TSV, HTML, JSON/JSONL/NDJSON, and XML; binary documents cover PDFs and Microsoft Word/PowerPoint/Excel variants; and audio/video uploads accept AAC/FLAC/M4A/MP3/OGG/OPUS/WAV/WEBM plus MP4 or QuickTime sources. 【F:includes/class-wp-mcp-ai-message-attachments.php†L642-L709】

Whenever attachments are present, the plugin automatically inlines the asset data when sending requests to OpenAI's Responses API. Image segments are converted to data URLs and file segments include the base64-encoded payload alongside the original filename, so integrators do not need to upload assets manually before invoking a model.

REST requests that include attachments automatically gain access to the bundled Submit Document Prompt tool so the files reach OpenAI even when the assistant has the tool disabled in its configuration.【F:includes/class-wp-mcp-ai-rest.php†L22-L29】【F:includes/class-wp-mcp-ai-rest.php†L963-L991】

Assistant memory files configured on the post (memory_files) are also promoted to structured text segments on the system channel, retaining the existing chunking/truncation safeguards.

Need to relax or tighten the allowed file types? Administrators can override the image and file MIME lists directly in Settings → NV oOS → Attachments, and the same values are used by shortcode-driven chat surfaces (including the Elementor widget) when building upload restrictions.【F:includes/admin/class-wp-mcp-ai-admin-settings.php†L225-L267】【F:includes/class-wp-mcp-ai-message-attachments.php†L456-L565】【F:includes/class-wp-mcp-ai-shortcode.php†L197-L218】 When JSON Lines support is enabled in the allowlist the plugin also registers .jsonl and .ndjson extensions with WordPress so uploads succeed without additional filters.【F:mcp-ai-wpoos.php†L236-L272】

Assistants can also query existing knowledge files with the Search Attachments tool, which reuses WP_MCP_AI_Message_Attachments::user_can_access_attachment() so only publicly accessible or user-owned media is returned alongside download URLs and file metadata for the model to reuse.【F:includes/tools/class-wp-mcp-ai-tool-search-attachments.php†L15-L207】【F:includes/class-wp-mcp-ai-message-attachments.php†L480-L575】