MCP servers

The official Python implementation of the Model Context Protocol, for building MCP servers that expose tools, resources and prompts, and MCP clients that connect to them.

• MCP servers

An open-source, self-hostable workflow automation platform, positioned as an alternative to Zapier, whose integrations double as MCP servers usable from Claude Desktop, Cursor or Windsurf.

• MCP servers
• Workflow automation

A Python framework for building Model Context Protocol servers, clients and interactive apps, generating tool schemas, validation and documentation automatically from ordinary Python functions.

• MCP servers

An MCP server and matching Blender add-on that connect Blender to any large language model for prompt-assisted 3D modeling, scene creation and manipulation.

• MCP servers
• Design tools

An MCP toolkit that gives a coding agent IDE-level semantic code tools -- symbol-level retrieval, editing, refactoring and navigation -- instead of relying on line numbers or plain text search.

• MCP servers

An SDK and CLI that gives AI agents access to more than 1,000 pre-authenticated toolkits across external apps, with per-user sessions, authentication, triggers and a sandbox for turning an agent's intent into action.

• Agent frameworks
• MCP servers

A browser automation agent, reachable over MCP or a standalone chat UI, that drives a stealth Firefox build to carry out web tasks such as checking flight prices across dates while aiming to avoid detection by anti-bot and captcha systems.

• MCP servers
• Browser automation

GitHub's official Model Context Protocol server, giving AI agents and assistants the ability to read repositories, manage issues and pull requests, analyze code and automate GitHub workflows through natural language.

• MCP servers
• Git

A Model Context Protocol server that gives large language models browser automation through Playwright's accessibility tree, so agents can interact with web pages without screenshots or vision models.

• MCP servers
• Browser automation

codebase-memory-mcp is a native MCP server that indexes a codebase into a persistent knowledge graph in milliseconds, giving a coding agent structural queries instead of repeated grep and file-read cycles.

• MCP servers
• Agent memory

Chrome DevTools for agents lets a coding agent control and inspect a live Chrome browser through an MCP server, giving it DevTools-level automation, debugging and performance analysis.

• MCP servers
• Browser automation

Context7 fetches up-to-date, version-specific documentation and code examples for a library directly into an LLM prompt, instead of the model relying on outdated training data or invented APIs.

• MCP servers
• RAG

A small set of reference server implementations for the Model Context Protocol, maintained by the MCP steering group to demonstrate MCP features and SDK usage for developers building their own servers.

• MCP servers

A curated list of Model Context Protocol servers that give AI models access to local and remote tools and data, organized by category such as databases, file systems, browser automation and coding agents.

• MCP servers
• Curated lists