PrefectHQ/fastmcp
FastMCP offers a Pythonic framework for developing and interacting with Model Context Protocol (MCP) servers and clients, facilitating efficient communication with LLMs.
modelcontextprotocol/python-sdk
The project "modelcontextprotocol/python-sdk" is the official Python SDK implementing the Model Context Protocol (MCP) specification. MCP is designed to enable developers to build MCP servers and clients that provide standardized context and interaction for large language models (LLMs). This SDK fully implements the MCP specification, allowing easy creation of MCP clients that can connect to any MCP server and MCP servers that expose resources, prompts, and tools. It supports standard transports such as stdio, Server-Sent Events (SSE), and Streamable HTTP, and handles all MCP protocol messages and lifecycle events. The SDK provides a FastMCP server interface that manages connection, protocol compliance, and message routing. Developers can define resources, which are akin to GET endpoints that expose data to LLMs without side effects, and tools, which are like POST endpoints that perform computations or side effects. The SDK also supports prompts, images, context management, completions, elicitation, sampling, logging, notifications, and authentication as part of the MCP specification. Installation is straightforward via pip or using the uv project manager. The SDK includes standalone MCP development tools accessible via command line. The README provides quickstart examples demonstrating how to create a simple MCP server exposing a calculator tool and a dynamic greeting resource. It also shows how to run the server in development mode or install it in Claude Desktop for immediate interaction. Advanced usage includes low-level server customization, writing MCP clients, and defining server capabilities. The SDK is well-documented and encourages contributions. It is licensed under MIT and integrates with existing Python projects easily. Overall, this SDK is a comprehensive toolkit for developers aiming to build interoperable, standardized LLM context providers and interaction servers using the Model Context Protocol in Python.
https://github.com/modelcontextprotocol/python-sdk
Also in Python
tadata-org/fastapi_mcp
FastAPI-MCP is a tool that exposes FastAPI endpoints as Model Context Protocol (MCP) tools with built-in authentication, preserving schemas and documentation, and supporting flexible deployment using FastAPI's native ASGI interface.
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.