What is Langchain ReAct Agent

This is a simple Command Line Interface (CLI) client for the Model Context Protocol (MCP) utilizing the LangChain ReAct Agent. It demonstrates how to interact with multiple MCP servers, converting their tools into a format compatible with LangChain.

Use cases

The MCP client can be used to access and leverage various language models from providers like Anthropic, OpenAI, and Groq. It’s suitable for executing tasks that involve tool invocation through a CLI, making it versatile for development and testing of MCP server functionalities.

How to use

To use the client, install the required dependencies, set up your API keys in the provided .env file, and configure the MCP server settings in the llm_mcp_config.json5 file. After setting up, run the application using make start, and interact with the tool via command line prompts.

Key features

Key features include parallel initialization of MCP servers, conversion of MCP tools into LangChain-compatible tools, support for multiple language models, and ease of use through a command-line interface.

Where to use

This client can be used in development environments for interacting with various models and testing functionalities provided by MCP servers. It is particularly useful for developers and researchers working on projects that require model context protocols.

Simple CLI MCP Client Using LangChain / Python

This simple Model Context Protocol (MCP)
client with command line interface demonstrates the use of MCP server tools by the LangChain ReAct Agent.

It leverages a utility function convert_mcp_to_langchain_tools() from
langchain_mcp_tools.
This function handles parallel initialization of specified multiple MCP servers
and converts their available tools into a list of LangChain-compatible tools
(list[BaseTool]).

LLMs from Anthropic, OpenAI and Groq are currently supported.

A typescript version of this MCP client is available
here

Prerequisites

• Python 3.11+
• [optional] uv (uvx)
  installed to run Python package-based MCP servers
• [optional] npm 7+ (npx)
  to run Node.js package-based MCP servers
• API keys from Anthropic,
  OpenAI, and/or
  Groq
  as needed

Setup

1. Install dependencies:

   make install
   

2. Setup API keys:

   cp .env.template .env
   

   • Update .env as needed.
   • .gitignore is configured to ignore .env
     to prevent accidental commits of the credentials.

3. Configure LLM and MCP Servers settings llm_mcp_config.json5 as needed.

   • The configuration file format
     for MCP servers follows the same structure as
     Claude for Desktop,
     with one difference: the key name mcpServers has been changed
     to mcp_servers to follow the snake_case convention
     commonly used in JSON configuration files.
   • The file format is JSON5,
     where comments and trailing commas are allowed.
   • The format is further extended to replace ${...} notations
     with the values of corresponding environment variables.
   • Keep all the credentials and private info in the .env file
     and refer to them with ${...} notation as needed.

Usage

Run the app:

make start

It takes a while on the first run.

Run in verbose mode:

make start-v

See commandline options:

make start-h

At the prompt, you can simply press Enter to use example queries that perform MCP server tool invocations.

Example queries can be configured in llm_mcp_config.json5