jlowin/fastmcp A better MCP Python framework

FastMCP is a fast, Pythonic framework designed for building Model Context Protocol (MCP) servers and clients with minimal boilerplate code, enabling developers to quickly define tools, resources, and prompt templates. Compared to the official MCP SDK, its API is more concise, offering multiple transport modes (Stdio, SSE, memory) and a resource templating mechanism, with one-click generation of MCP services via OpenAPI/FastAPI to streamline development. Version 2.0 adds powerful features such as server proxying, composition patterns, and enhanced client capabilities, supporting the creation of modular and reusable AI application architectures. Licensed under Apache-2.0 and backed by an active community, FastMCP is continuously updated, making it an indispensable tool for AI practitioners.

Source code：https://github.com/jlowin/fastmcp

Documentation：https://gofastmcp.com/getting-started/welcome

The MCP protocol is powerful but implementing it involves a lot of boilerplate – server setup, protocol handlers, content types, error management. FastMCP handles all the complex protocol details and server management, so you can focus on building great tools. It’s designed to be high-level and Pythonic; in most cases, decorating a function is all you need.

While the core server concepts of FastMCP 1.0 laid the groundwork and were contributed to the official MCP SDK, FastMCP 2.0 (this project) is the actively developed successor, adding significant enhancements and entirely new capabilities like a powerful client library, server proxying, composition patterns, OpenAPI/FastAPI integration, and much more.

FastMCP aims to be:

🚀 Fast: High-level interface means less code and faster development

🍀 Simple: Build MCP servers with minimal boilerplate

🐍 Pythonic: Feels natural to Python developers

🔍 Complete: FastMCP aims to provide a full implementation of the core MCP specification for both servers and clients