MCP Servers
Official reference implementations of the Model Context Protocol -- the open standard now adopted across OpenAI, Google, Microsoft and Anthropic for connecting agents to tools and data.
- Actively maintained
- Well documented
- Permissive license
Overview
This repository hosts the official reference server implementations for the Model Context Protocol (MCP), a standardized way for AI applications to connect to external tools, data sources, and systems -- avoiding the need for every agent framework to build bespoke integrations for every tool. MCP has since been adopted well beyond its originating team, with implementations and support across most major AI platforms.
MCP Servers is a fit for anyone building agent tooling who wants to speak (or expose) a genuinely cross-platform protocol rather than a proprietary integration format -- the reference implementations here are the starting point for both consuming and building MCP-compatible tools.
- Categories
- AI Agents & Agent Tools
- Keywords
- agent-toolsmcpprotocoltool-use
- Languages
- TypeScript, Python
- License
- MIT
Related Projects
Composio
MITPowers 1000+ toolkits, tool search, context management and authentication so AI agents can actually take action, not just plan it.
Actively maintained
- AI Agents & Agent Tools
browser-use
MITA library that lets AI agents control a real web browser -- clicking, typing, navigating and reading pages -- to complete tasks that require the open web.
Actively maintained
- AI Agents & Agent Tools
CLI-Anything
Apache-2.0Turns any professional software into an agent-native CLI tool via a single pip install, so AI agents can control real applications without fragile UI automation.
Actively maintained
- AI Agents & Agent Tools
LangGraph
MITBuild resilient, stateful agents as graphs -- explicit nodes and edges for control flow, rather than an implicit agent loop, for reliable long-running or multi-step workflows.
Actively maintained
- AI Agents & Agent Tools
Spotted an error? Suggest an edit on GitHub.