langchain-to-mcp-tool-adapter

# LangChain to MCP Tool Adapter [](https://badge.fury.io/py/langchain-to-mcp-tool-adapter) [](https://opensource.org/licenses/MIT) A Python package for converting LangChain tools to FastMCP tools, making it easy to use your existing LangChain tools with Anthropic's MCP server. ## Why Use This Package? - **Simpler Implementation**: While LangChain offers an MCP-to-LangChain adapter, it requires a running MCP server either remotely or co-located with an agent, which can be finicky. LangChain tools have a simpler implementation and are more lightweight. - **Use in Multiple Environments**: When creating tools (especially for open source), you might want to make them available in both LangChain and MCP implementations without duplicating code. - **Handle Artifacts Properly**: Automatic conversion between LangChain's `content_and_artifact` format and MCP's content format for images, PDFs, and other binary data. - **Preserve Metadata**: Tool descriptions, argument schemas, and other metadata are preserved during conversion. ## Installation ```bash pip install langchain-to-mcp-tool-adapter ``` ## Quick Start ```python from mcp.server import FastMCP from langchain.tools import Tool from langchain_to_mcp_tool_adapter import add_langchain_tool_to_server # Create a LangChain tool def multiply(a: int, b: int) -> int: """Multiply two numbers.""" return a * b calculator_tool = Tool( name="calculator", description="Multiply two numbers together", func=multiply ) # Create a FastMCP server and add the tool server = FastMCP() add_langchain_tool_to_server(server, calculator_tool) # Run the server server.run() ``` ## Working with Argument Schemas ### Type Annotations ```python from typing import Annotated, List from langchain.tools import tool @tool("multiplication-tool") def multiply_type_annotation( a: A…