766 mcps available in the ChatGPT directory
Model Context Protocol servers that extend AI capabilities with real-time data, tool access, and external integrations. Install an MCP to give the AI access to databases, APIs, file systems, and more.
Unified LLM API with automatic model discovery and provider configuration
OpenCode plugin for ChatGPT Plus/Pro OAuth with Codex/GPT-5 routing, multi-account rotation, account switching, health checks, diagnostics, and recovery tools
630 professional Agent Skills (SKILL.md) + subagents + slash commands for Claude, ChatGPT, Gemini, Cursor, Codex & Hermes. It's a CLI, not a library: run npx pm-claude-skills add --agent <tool> to install into your AI tool — no npm install needed. Or
Local-first, agent-native control plane for ComfyUI — MCP server + autonomous sidebar agent that drives your live graph in natural language on ANY LLM: Claude/ChatGPT/Gemini on your subscription (no API key), free local models via Ollama (fully offline)
JSDoc linting rules for ESLint.
Stateless, task-oriented AI agent core
A-Team MCP Server — build, validate, and deploy multi-agent solutions from any AI environment
Run autonomous agent workflows, host an MCP server over HTTP, and manage workflow definitions and run history from the terminal.
Stealth browser automation MCP server powered by Patchright. 64 tools, HTTP/SSE/Streamable HTTP transports, persistent profiles, multi-page support, CDP attach, network interception, granular cookie/local/session storage, virtual passkeys, storage import/
A composable stream processing pipeline for parsing OpenRouter/OpenAI streaming API responses. Each transform stream handles one layer of parsing and emits typed messages that flow through the pipeline.
MCP server exposing recall + load_memory over a markdown vault.
Dynamic MCP servers + agent skills as uniform tools for any LLM (opencode-style).
AI DevOps Framework - AI-assisted development workflows, code quality, and deployment automation
Unified LLM streaming API for Anthropic, OpenAI, and Gemini
Provider-agnostic realtime voice orchestration for GG tools and agents
Unified LLM API with automatic model discovery and provider configuration
Kolbo AI MCP Server - Generate images, videos, music, speech, and sound effects from Claude Code
Veryfront first-party extension package for ext-llm-openai
MCP server for image recognition via vision models (extensible to multiple providers), with an HTTP image-intercepting proxy that lets text-only LLMs accept image input in Claude Code.
Self-hosted AI router: many providers, one OpenAI-compatible /v1 endpoint and dashboard
Unified LLM API with automatic model discovery and provider configuration
Modern and scalable routing for React applications
OMK (Open Multi-Agent Kit) coding agent CLI with read, bash, edit, write tools and session management
ESLint React's ESLint plugin for interacting with Web APIs