MCP Hge

🚀 MCP Weather Tool

A simple command-line tool implementation of the MCP protocol that allows access to US weather data through a client-server architecture. This tool uses Google's Gemini AI to provide a natural language interface.

🚀 Quick Start

The MCP Weather Tool connects a Python client application with a weather data server, enabling users to query weather information in natural language. The server communicates with the National Weather Service API via the Model Context Protocol (MCP) to obtain weather alerts and forecasts.

✨ Features

• Query current weather alerts for US states using state codes.
• Get detailed weather forecasts for specific locations using latitude and longitude.
• Provide a natural language interface powered by Google's Gemini AI.
• Implement a client-server architecture through the Model Context Protocol (MCP).

📦 Installation

Prerequisites

• Python 3.8+
• Node.js (if running the JavaScript server)
• Google Gemini API key

Steps

1. Clone the repository:

   git clone https://github.com/Abhinavexists/MCP_Server.git
   cd weather-tool
   

2. Install uv if you don't have it:

   pip install uv
   

3. Create and activate a virtual environment:
   • On Windows: .venv\Scripts\activate
   • On macOS/Linux: source .venv/bin/activate
4. Install dependencies using uv (the project uses uv.lock and pyproject.toml):

   uv pip sync
   

5. Create a .env file in the project root directory and add your Gemini API key:

   GEMINI_API_KEY=your_gemini_api_key_here
   

💻 Usage Examples

Basic Usage

1. Run the client and connect to the weather server:

   python client.py server.py
   

2. After connecting, you can ask questions about weather information:
   • Query: What are the current weather alerts in California?
   • Query: What is the weather forecast for the location at latitude 37.7749 and longitude -122.4194?
3. Enter quit to exit the application.

Advanced Usage

The server provides the following tools:

• get_alerts: Retrieve weather alerts for a specified US state (using two-letter state codes).
• get_forecast: Retrieve a weather forecast for a specific location based on latitude and longitude.

📚 Documentation

Project Structure

• client.py: The MCP client that connects to the server and uses Gemini AI to process user queries.
• server.py: The MCP server that implements weather data tools and communicates with the National Weather Service API.

Error Handling

The application includes the following error handling features:

• Invalid server script path.
• Connection issues with the NWS API.
• Missing or invalid data in API responses.

Future Improvements

• Add additional weather data endpoints.
• Implement caching for frequently used data.
• Support location name queries (instead of requiring latitude and longitude).
• Create a web interface.

📄 License

MIT License

Resources

For more information about the Model Context Protocol (MCP), refer to the official Claude MCP documentation:

• Claude MCP Official Documentation