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.
golf-mcp/golf
Golf is a comprehensive and production-ready framework designed specifically for building, deploying, and scaling secure Model Context Protocol (MCP) servers that power AI agents. It simplifies the development process by allowing developers to define server capabilities such as tools, prompts, and resources as straightforward Python files organized within a conventional directory structure. Golf automatically discovers, parses, and compiles these components into a runnable FastMCP server, significantly reducing boilerplate code and accelerating development workflows. The framework is tailored for developers who want to focus on implementing their AI agent's logic without the complexities of server setup and integration. It supports automatic component discovery, built-in authentication, observability, debugging, telemetry, and runtime management, making it a robust solution for production environments. Golf projects are structured with clear directories for tools, resources, and prompts, each containing Python files that define individual components. The framework uses the module docstring as the component's description and derives component IDs automatically based on file paths. This organization facilitates modular development and easy code sharing within subdirectories. The configuration of a Golf server is managed through a `golf.json` file, which allows customization of server name, port, transport protocols (such as Server-Sent Events, streamable HTTP, or standard I/O), telemetry settings, and health check endpoints. This flexibility enables deployment in various environments, including local development, cloud, and Kubernetes. Golf also provides a command-line interface (CLI) for project initialization, building, and running the development server, streamlining the setup process. The framework's design emphasizes ease of use, scalability, and security, making it an ideal choice for developers building MCP servers to power AI-driven applications and agents.
https://github.com/golf-mcp/golf
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.
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.
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.