"File system requirements: mounted directory, persistent state, and full R/W access" matching MCP servers:

Self-hosted credential store and API proxy for AI agents. One Bearer token, all your services. Handles OAuth refresh, encrypted storage, audit logging, and per-agent permissioning.

An MCP-native state sidecar that externalises workflow state for distributed agent deployments.

Provides state and log management tools designed for long-lived AI agents that may be interrupted and resumed. It enables tracking agent progress and maintaining an append-only event history to ensure continuity across multiple sessions.

Single source of truth and control for agent-operated companies, managing business state with deterministic policy enforcement, seat identity, and hash-chained audit trail.

Enables AI agents to discover, register, and rate services in a decentralized agent-to-agent directory.

MCP Server for agent and service discovery — register, search, rate, and manage AI agents and services in a local directory.

Enables building and evaluating LangGraph agents over a protocol-level MCP server to measure failure rates across four agent topologies.

Domain-Driven MCP server for ed-tech workflows, exposing validated MCP tools backed by LangGraph agents, Supabase document retrieval, web search, and YouTube video discovery.

Cryptographic identity and trust protocol for AI agents. 38 MCP tools across 8 protocol layers: Ed25519 identity, delegation chains, values compliance, signed communication, policy engine, task coordination, cross-layer integration, and agentic commerce. 264 tests passing.

Enables MCP-compatible agents to arbitrate typed state-action schemas, dispatch routine actions deterministically, and apply pre-escalation filters that reduce unnecessary frontier LLM calls. It supports low-latency, schema-enforced routing with safety guardrails and local-first memory retention.

Enables self-hosted AI gateway and agent control plane with governed MCP tools, virtual-key budgets, caching, and audit, supporting OpenAI, Anthropic, Gemini, MCP, and A2A protocols. It provides deterministic prompt enhancement and governed execution with a zero-credential first run.

Enables AI agents to persist and restore checkpoint state, supporting crash recovery and replay for LangGraph-based workflows.

Enables multi-agent systems to share and coordinate a common state space over MCP, detecting concurrent mutation race conditions, synchronizing state through vector clocks, and resolving conflicting decisions via consensus arbitration. Also supports deterministic policy validation and cryptographic state hashing with zero external dependencies.

Enables AI agents to commit stateful workflow checkpoints by calculating state hashes and rollback points through the Model Context Protocol. It provides deterministic, dependency-free checkpoint management for autonomous agent execution.

Enables AI agents to arbitrate typed state-action schemas and dispatch deterministic actions locally, so routine or reflexive decisions are resolved in sub-millisecond fashion instead of incurring expensive frontier-LLM calls. It also applies token-saving pre-escalation filters, escalating only ambiguous or multi-hop plans to larger models while enforcing reversible execution checkpoints, strict token budgets, and local-first memory retention.

Enables AI agents to capture and commit stateful workflow checkpoints during autonomous execution, computing deterministic state hashes and rollback points. It runs as a zero-dependency Python MCP server that plugs into Claude Desktop, Cursor, and other MCP-compliant clients for reliable, low-latency checkpoint management.

System Initiative provides AI Native Infrastructure automation that gives you clarity over your running infrastructure, control to change, automate, and integrate it, with conifdence

A production-grade MCP server designed for multi-tenant, authenticated, and observable AI agent systems, enabling secure tool execution across heterogeneous data sources.

Enables LLMs to discover and invoke generated API actions as MCP tools and read context through MCP resources for list and get-by-id operations. It provides HTTP-based MCP access for clients such as Cursor and Claude without extra glue code.

A master control platform that orchestrates intelligent agents with a plug-and-play architecture, allowing users to manage and coordinate multiple AI agents through a unified system.

A state-based agent orchestration system that allows transitions between different states (IDLE, PLANNING, RESEARCHING, EXECUTING, REVIEWING, ERROR) while maintaining conversation context and providing state-specific prompts.

Provides AI agents with low-latency reflex tools for fast safety checks, option selection, verification, and scoring using calibrated probabilities, reducing reliance on slow LLM deliberation.

A local MCP proxy that connects AI clients to nomos system controllers, allowing registration and switching between them via natural language. Enables smart home control through MCP-compatible AI clients.

Enables Claude Code and other MCP clients to obtain fast, low-latency snap decisions — tool choice, option selection, and abstention when confidence is low — from a pluggable local decision engine such as Laya, Von, an Ollama chat model, or a custom provider. Engines can be swapped without changing the stable tools the client sees, with validation, per-attempt timeouts, confidence thresholds, and fallback chains handled by the server.

Open-source Chrome extension + MCP server that lets AI agents drive your real, signed-in Chrome by reading the live DOM (no screenshots).

Enables MCP-compatible apps to expose a folder of RAPP agent.py files as callable tools, deriving each tool's schema from its metadata and running calls in isolated, timed processes.

A meta MCP server that scales LLMs to 1000+ servers via automatic routing, without exposing all servers and tools directly.

Enables AI assistants to maintain continuity across sessions by tracking named work lanes, structured handoffs, artifacts, and reusable routines so work can pick up where it left off.

Enables AI assistants and terminals to control a user's already logged-in Chrome session, allowing them to navigate pages, read content, click and type, run JavaScript, and inspect console or network activity.

Exposes tools for listing files and reading their contents over stdio, allowing MCP clients to inspect local filesystem paths during agent runs.