Project Setup Guide

This guide will help you set up and run the Learn_MCP project, which demonstrates using a Model Context Protocol (MCP) math server with LangChain.

Prerequisites

• Python 3.8 or higher (recommended: use a virtual environment)

• uv (a fast Python package manager)

• A valid GROQ API key (for ChatGroq)

Related MCP server: LaTeX to MathML MCP Server

1. Clone the Repository

2. Create and Activate a Virtual Environment (optional but recommended)

3. Install Dependencies with uv

Or, to use the lockfile (if present):

4. Set Up Environment Variables

Create a .env file in the project root with your GROQ API key:

5. Run the Math Server

The math server will be started automatically by the client script as a subprocess (mathserver.py). You do not need to start it manually.

6. Run the Client

Or simply:

7. Troubleshooting

• If you see ImportError: langchain_mcp_adapters.fastapi could not be resolved, ensure the package is installed or available in your environment.

• If you get errors about missing modules, check your requirements.txt and install any missing dependencies.

• Make sure your .env file is present and contains a valid GROQ_API_KEY.

8. Project Structure

• client.py — Main client that connects to the math MCP server

• mathserver.py — Math MCP server (started by the client)

• requirements.txt — Python dependencies

• .env — Environment variables (not committed to version control)

Feel free to update this README with additional details as your project evolves.