MCP Server Project

This project demonstrates how to build and connect to Model Context Protocol (MCP) servers using fastmcp and langchain.

Overview

The project consists of three main components:

1. Calculator MCP Server (Calculator_MCP_Server.py): A FastMCP server exposing basic arithmetic operations (add, subtract, multiply, divide).
2. Weather MCP Server (Weather_MCP_Server.py): A FastMCP server that fetches current weather information for a given city using the OpenWeather API.
3. LLM Client (client.py): A LangChain-powered conversational agent that connects to both MCP servers and can intelligently invoke their tools based on user prompts.

Prerequisites

• Python 3.10+
• An OpenRouter API Key for the LLM client.
• An OpenWeather API Key for the Weather server.

Setup

1. Clone the repository:

   git clone <repository-url>
   cd MCP_Server_Project

2. Create a virtual environment and install dependencies:

   python -m venv .venv
   source .venv/bin/activate  # On Windows use: .venv\Scripts\activate
   pip install -r requirements.txt

3. Configure Environment Variables: Create a .env file in the root directory and add your API keys:

   OPENWEATHER_API_KEY=your_openweather_api_key
   OPENROUTER_API_KEY=your_openrouter_api_key
   MODEL=your_preferred_model_name

Running the Project

To use the client, you first need to start the MCP servers on their respective ports.

1. Start the Calculator Server:

   python Calculator_MCP_Server.py

   (Runs on http://127.0.0.1:8001)

2. Start the Weather Server:

   python Weather_MCP_Server.py

   (Runs on http://127.0.0.1:8002)

3. Start the Client (in a new terminal):

   python client.py

You can now chat with the agent and ask it to perform calculations or fetch weather data!