modelcontextprotocol/python-sdk
The official Python SDK for the Model Context Protocol (MCP) enabling developers to build standardized MCP servers and clients for LLM context and interaction.
tadata-org/fastapi_mcp
FastAPI-MCP is a specialized tool designed to expose FastAPI endpoints as Model Context Protocol (MCP) tools, integrating built-in authentication and preserving the schemas and documentation of the original API endpoints. It leverages FastAPI's native ASGI interface for efficient communication, allowing flexible deployment options such as mounting the MCP server directly onto the existing FastAPI app or deploying it separately. This tool is not merely a converter from OpenAPI to MCP but a native extension of FastAPI, which means it supports FastAPI's dependency injection system for authentication and authorization, ensuring seamless integration with existing FastAPI services. The project emphasizes minimal configuration, enabling developers to quickly add MCP capabilities to their FastAPI applications by simply pointing FastAPI-MCP at their app. It preserves the request and response models' schemas and the documentation as it appears in Swagger, maintaining consistency and clarity for API consumers. FastAPI-MCP supports Python 3.10 and above, with a recommendation for Python 3.12, and can be installed easily via pip or the fast Python package installer uv. The tool is developed and maintained by Tadata and is open-source under the MIT License. It includes comprehensive documentation and examples to help users get started and explore advanced features. The project encourages community contributions and engagement through GitHub and the MCParty Slack community. FastAPI-MCP is ideal for developers looking to integrate MCP capabilities into their FastAPI applications with minimal friction, leveraging native FastAPI features for authentication, deployment, and communication.
https://github.com/tadata-org/fastapi_mcp
Also in Python
PrefectHQ/fastmcp
FastMCP offers a Pythonic framework for developing and interacting with Model Context Protocol (MCP) servers and clients, facilitating efficient communication with LLMs.
mcp-use/mcp-use
mcp-use is an open-source client library that enables easy connection of any tool-capable LLM to MCP servers for building custom agents with diverse tool access.
golf-mcp/golf
Golf is a production-ready framework for building, deploying, and scaling secure MCP servers that power AI agents, featuring automatic component discovery, built-in authentication, observability, debugging, telemetry, and runtime management.
cognitivecomputations/dolphin-mcp
Dolphin MCP is a flexible Python library and CLI tool that enables conversational interaction with multiple Model Context Protocol (MCP) servers using various large language models.
rectalogic/langchain-mcp
langchain-mcp provides Model Context Protocol (MCP) tool support for the LangChain framework, enabling integration of MCP-compliant tools to enhance language model applications.
googleapis/mcp-toolbox-sdk-python
Google's Python SDK collection for MCP Toolbox, loading tools defined in a Toolbox server as plain Python functions or as ready-made tools for ADK, LangChain, LangGraph and LlamaIndex.
mkinf-io/mkinf
Python SDK that pulls hosted MCP servers from the mkinf hub and exposes them as LangChain-compatible tools through a single unified interface.