"How to create the most intelligent agent" matching MCP servers:

Enables ordinary LLMs to be augmented fully offline — with no API keys or external services — through model-aware guardrails, exemplar retrieval, structured self-critique, compliance scoring, and an allowlisted verification runner. Also provides hybrid knowledge-base search, decaying long-term memory, and persistent plan/task management across 54 MCP tools usable from any MCP client such as OpenCode, Claude Desktop, Cursor, or VS Code.

MCP server for qualifying and responding to inbound leads in seconds using a multi-agent AI pipeline.

MCP server for The Commons (jointhecommons.space), a persistent, noncommercial space where AI voices from different models post and reply to each other with persistent identities. 48 tools; reading needs no token, writing uses a facilitator-issued token.

Enables structured learning with a verified loop: define goals as observable claims, learn through teach-lab-test-gate per claim, and get independently graded by an adversarial examiner to ensure genuine progress.

Give any LLM agent a real Android or iPhone. 62 MCP tools: tap, swipe, type, screenshot, screen-tree reading, app launch, camera, TTS, crash reports, batched execution. Android via ADB, iPhone via WebDriverAgent, on-device inference, Docker+KVM emulators. Works with Claude Code, Cursor, LangChain, LlamaIndex, and any MCP client. MIT.

Connects AI agents to The Agents Hub, visualizing them as pixel characters on a tile-based property with tools for state, assets, inboxes, and multi-agent orchestration.

Enables Claude Code agents to perform structured decision-making through TypeSafe Jev, supporting yes/no checks, route selection, scoring, and batched multi-question judgments with confidence values.

Converts AI Skills (following Claude Skills format) into MCP server resources, enabling LLM applications to discover, access, and utilize self-contained skill directories through the Model Context Protocol. Provides tools to list available skills, retrieve skill details and content, and read supporting files with security protections.

Lets LLMs play a local Slay the Spire 2 installation by exposing game state, action help, and 29 gameplay actions through STDIO tools, with waiting, wiki lookups, and profile inspection.

One-pass agentic inbox triage as an MCP server: fetch unread Gmail → classify (action_needed/fyi/newsletter/noise) → summarize → extract tasks → draft replies as Gmail DRAFTS (never sends) → flag calendar → write a triage report. Four stdio tools (fetch_emails, save_gmail_draft, append_tasks, write_report); the host is the LLM, so it runs keyless in Claude Code. Gmail scopes: readonly + compose

Hire an autonomous cold outreach agent directly inside any MCP-compatible LLM. Built by a PR tech publicist, Your Echo Agent delivers truly personalized cold emails tied LinkedIn groups for SaaS, agencies, e-commerce, founders, local businesses, and PR clients — all from Claude, Cursor, Windsurf, or Continue.

A Model Context Protocol server that converts Markdown content to HTML format.

Enables two LLMs to play Tic-Tac-Toe against each other autonomously using a shared tool and an SSE relay. The server facilitates agent-to-agent communication by holding tool responses until the opponent makes a move, managing the game state in real-time.

Enables MCP clients to interact with A2A agents through four ordinary tools, translating agent discovery, messaging, task reading, and cancellation between the A2A and MCP protocols, with support for the tasks extension.

An MCP server that turns a one-sentence idea into working, tested code using a pipeline of six AI agents, with optional deployment.

Enables MCP clients such as Claude Desktop to hand tasks to a running DeepSeek Harness window, where each task becomes a real session visible in the sidebar with a reusable session id. If the in-process plugin is unavailable, it falls back to running the task headless so the tool still returns a result.

Enables users to inspect database schemas, validate SQL syntax, and execute queries against PostgreSQL and Apache Hive through standardized Model Context Protocol tools for safe query generation and validation.

Enables autonomous agents and MCP-compatible clients to enforce policy-approved actions using risk tiers, reversible checkpoints, and token approval bounds.

Enables AI-assisted gameplay for Slay the Spire by reading game state and providing strategy advice or automated actions via Claude Code.

Enables autonomous agents and multi-agent frameworks to route actions through deterministic human approval gates before execution. Enforces risk tiers, reversible checkpoints, and token approval bounds so that risky or costly operations can be reviewed, bounded, and rolled back without LLM round-trips.

A filesystem-based MCP server for AI coding agents to coordinate work across git worktrees by claiming files, checking for conflicts, and logging progress without affecting the repository's git history.

A local stdio MCP service that unifies coding agents like Codex and Claude into cs_agent_* tools, enabling the root agent to create, invoke, and manage child agents with recursive delegation.

AGENTS.md + skills orchestration with CHP Profile A R0/adversary gates. @cubiczan/agent-conductor

Enables AI agents to create temporary email addresses, receive confirmation emails, and extract verification links, automating sign-up and email verification workflows without manual intervention.

Enables analyzing coding-agent session transcripts to measure tool efficiency, detect loops, track test outcomes, and report costs, with MCP tools for listing sessions, analyzing sessions, finding loops, and generating cost reports.

MCP server that lets you drive Claude Code sessions hands-free by voice from any MCP client, enabling remote models to send prompts, monitor progress, and get results read back.

Agent NERO is an MCP server that enables Claude Code to spawn, manage, and communicate with persistent, named LLM agents that maintain conversation history and can use tools like file I/O, command execution, and shared memory.

Enables AI agents to search and inspect a Windows machine's local inventory of agents, skills, MCP servers, projects, and cross-agent work records, with tools for full-text search, overviews, project details, and reindexing. All data stays local and only matching snippets enter model context.

Turns a Claude Desktop or Claude Code conversation into an orchestrator for parallel AI coding agents, each running in its own Tern terminal tab and git worktree on its own branch, with any model available on the machine. It enables starting, monitoring, correcting, and merging agents—reading their reports and diffs, switching models or thinking levels mid-task, and enforcing model policies.

MCP server for AI agent guardrails — validates and signs agent decisions (OAA tokens) so third parties can verify them without server access

Routes multiple ChatGPT chats to allowlisted Git workspaces through a single MCP endpoint, and manages persistent Pi and Codex agent pools for coordinated, checkpointed work.

Enables AI coding agents to coordinate through a local, pull-only message board by registering sessions, posting updates, proposing and accepting tasks, holding leases, and reading or acknowledging updates under scoped human authorization.

Enables multiple coding agents (Claude Code, Codex, Cursor) to discover each other's sessions, search transcripts, ask questions, and handoff tasks through a shared MCP server.

Enables AI assistants like Claude to interact with humans through intuitive GUI dialogs, supporting text input, choices, confirmations, and information displays.

Unified MCP interface to monitor and control coding agents across OpenCode, Claude Code, and Codex CLI.

An autonomous MCP server that uses the Claude Code CLI to solve coding problems without permission prompts.

Agent Toolbelt is an MCP server exposing 11 focused API tools for LLM agents — schema generation, text extraction, token counting, CSV conversion, Markdown conversion, URL metadata, regex builder, cron expressions, address normalization, color palettes, and brand kits. Each tool is a focused microservice with structured input/output, WCAG-scored color data, USPS address parsing, and multi-model to

Enables AI agent tool calls to be intercepted and judged before execution, allowing, asking a human, or blocking based on calibrated risk and policy.

A home for any agent on the internet: inbox, public memory, job board, rooms, human help. Free, no key.

Windows-local MCP for Steam Balatro: tool-calling AI reads player-visible state, chooses and executes native actions, confirms results, and saves local experience. Glama's Linux sandbox can introspect MCP and run game-independent tools such as calculate, but cannot connect to Balatro on the user's Windows machine. Without the local game, health reports disconnected.