langchain-mcp-tools 0.2.0

Model Context Protocol (MCP) To LangChain Tools Conversion Utility

MCP To LangChain Tools Conversion Utility

This package is intended to simplify the use of Model Context Protocol (MCP) server tools with LangChain / Python.

Model Context Protocol (MCP), an open source technology announced by Anthropic, dramatically expands LLM’s scope by enabling external tool and resource integration, including Google Drive, Slack, Notion, Spotify, Docker, PostgreSQL, and more…

Over 2000 functional components available as MCP servers:

• MCP Server Listing on the Official Site
• MCP.so - Find Awesome MCP Servers and Clients
• Smithery: MCP Server Registry

The goal of this utility is to make these 2000+ MCP servers readily accessible from LangChain.

It contains a utility function convert_mcp_to_langchain_tools().
This async function handles parallel initialization of specified multiple MCP servers and converts their available tools into a list of LangChain-compatible tools.

For detailed information on how to use this library, please refer to the following document:

• "Supercharging LangChain: Integrating 2000+ MCP with ReAct"

A typescript equivalent of this utility is available here

Prerequisites

• Python 3.11+

Installation

pip install langchain-mcp-tools

Quick Start

convert_mcp_to_langchain_tools() utility function accepts MCP server configurations that follow the same structure as Claude for Desktop, but only the contents of the mcpServers property, and is expressed as a dict, e.g.:

mcp_servers = {
    "filesystem": {
        "command": "npx",
        "args": ["-y", "@modelcontextprotocol/server-filesystem", "."]
    },
    "fetch": {
        "command": "uvx",
        "args": ["mcp-server-fetch"]
    }
}

tools, cleanup = await convert_mcp_to_langchain_tools(
    mcp_servers
)

This utility function initializes all specified MCP servers in parallel, and returns LangChain Tools (tools: list[BaseTool]) by gathering available MCP tools from the servers, and by wrapping them into LangChain tools. It also returns an async callback function (cleanup: McpServerCleanupFn) to be invoked to close all MCP server sessions when finished.

The returned tools can be used with LangChain, e.g.:

# from langchain.chat_models import init_chat_model
llm = init_chat_model(
    model='claude-3-7-sonnet-latest',
    model_provider='anthropic'
)

# from langgraph.prebuilt import create_react_agent
agent = create_react_agent(
    llm,
    tools
)

Find complete, minimal working usage examples here

For hands-on experimentation with MCP server integration, try this LangChain application built with the utility

For detailed information on how to use this library, please refer to the following document:
"Supercharging LangChain: Integrating 2000+ MCP with ReAct"

Experimental Features

Remote MCP Server Support

mcp_servers configuration for SSE and Websocket servers are as follows:

    "sse-server-name": {
        "url": f"http://{sse_server_host}:{sse_server_port}/..."
    },

    "ws-server-name": {
        "url": f"ws://{ws_server_host}:{ws_server_port}/..."
    },

Note that the key name "url" may be changed in the future to match the MCP server configurations used by Claude for Desktop once it introduces remote server support.

Working Directory Configuration for Local MCP Servers

The working directory that is used when spawning a local MCP server can be specified with the cwd key as follows:

    "local-server-name": {
        "command": "...",
        "args": [...],
        "cwd": "/working/directory"  # the working dir to be use by the server
    },

Configuration for MCP Server stderr Redirection

A new key errlog has been introduced in to specify a file-like object to which MCP server's stderr is redirected.

    log_path = f"mcp-server-{server_name}.log"
    log_file = open(log_path, "w")
    mcp_servers[server_name]["errlog"] = log_file

NOTE: Why the key name errlog for server_config was chosen:
Unlike TypeScript SDK's StdioServerParameters, the Python SDK's StdioServerParameters doesn't include stderr: int. Instead, it calls stdio_client() with a separate argument errlog: TextIO. I once included stderr: int for compatibility with the TypeScript version, but decided to follow the Python SDK more closely.

Limitations

• Currently, only text results of tool calls are supported.
• Fatures other than Tools are not supported.

Change Log

Can be found here