Langchain MCP Client

🚀 🦜 🔗 LangChain MCP Client

This simple Model Context Protocol (MCP) client demonstrates the use of LangChain ReAct agents with MCP server tools.

🚀 Quick Start

The LangChain MCP Client is designed to seamlessly integrate with MCP servers and leverage LangChain ReAct agents. It offers several key features:

• 🌐 Smoothly connect to any MCP server.
• 🤖 Flexibly select any LangChain-compatible LLM for model usage.
• 💬 Interact via CLI, supporting dynamic conversations.

✨ Features

Convert to LangChain Tools

It utilizes a utility function convert_mcp_to_langchain_tools(). This function handles the simultaneous initialization of multiple specified MCP servers and converts their available tools into a list of LangChain-compatible tools (List[BaseTool]).

📦 Installation

The Python version should be 3.11 or higher.

pip install langchain_mcp_client

📚 Documentation

Configuration

Create a .env file containing all the necessary API_KEYS to access your LLM. Configure the LangChain LLM, MCP servers, and example prompts in the llm_mcp_config.json5 file:

1. LLM Configuration: Set the LangChain LLM parameters.
2. MCP Servers: Specify the MCP servers to connect to.
3. Example Queries: Define example queries for invoking MCP server tools. After pressing Enter, these example queries will be used for prompting.

💻 Usage Examples

Basic Usage

Here is an example with the Jupyter MCP Server: Check the llm_mcp_config.json5 configuration (the command depends on whether you are running on Linux, macOS, or Windows).

# Start jupyterlab.
make jupyterlab

# Launch the CLI.
make cli

Here is an example prompt.

Create many variants of a matplotlib example

📄 License

The initial code for this project is from hideya/mcp-client-langchain-py (MIT License) and from langchain_mcp_tools (MIT License).