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.
rectalogic/langchain-mcp
The project langchain-mcp is designed to provide support for the Model Context Protocol (MCP) within the LangChain framework. LangChain is a popular framework used for building applications with language models, and this project enhances its capabilities by enabling integration with MCP-compliant tools. MCP is a protocol that facilitates tool calling and interaction in language model applications, allowing for more dynamic and context-aware functionalities. The core functionality of langchain-mcp involves creating an MCPToolkit using an MCP ClientSession. This toolkit can be initialized asynchronously and then used to retrieve a list of tools that conform to the LangChain core tool interface. These tools can then be leveraged within LangChain applications to extend their capabilities by incorporating MCP-compliant tool interactions. The project includes a demo that demonstrates how to use the MCPToolkit with a language model from Groq, specifically the llama-3.1-8b-instant model. The demo shows how to run a command that reads and summarizes a file, illustrating the practical application of MCP tool support in LangChain. This example highlights the ability to securely interact with files and perform tasks such as summarization using the integrated MCP tools. Overall, langchain-mcp serves as a bridge between the Model Context Protocol and the LangChain framework, enabling developers to build more powerful and contextually aware language model applications by leveraging MCP-compliant tools. The project is relevant for those interested in enhancing language model interactions through standardized protocols and tool integrations.
https://github.com/rectalogic/langchain-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.
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.
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.