Weather MCP Server Ujh

🚀 Weather MCP Project

This project implements a weather-related service based on the Model Context Protocol (MCP). The service provides functions to obtain weather alerts and forecasts, and also includes system tools that can execute shell commands and view system resources.

✨ Features

• Weather Alerts: Obtain weather alert information for a specified area by entering the state code (e.g., "CA", "NY", "FL").
• Weather Forecasts: Get weather forecast data for a specific location by providing latitude and longitude coordinates.
• System Tools: Execute any shell command and view the results.
• Resource Browsing: View available system resources and their current states.

🚀 Quick Start

📦 Installation

Install the required dependencies using pip:

pip install "mcp[server]" requests

Initialization

Create a new MCP server instance and register weather tools and system resources:

from mcp import Server
import subprocess
import requests

server = Server()

# Register weather tools
@server.tool()
async def get_weather_alerts(state: str) -> dict:
    """
    Get weather alert information for a specified state.
    
    Args:
        state: State code (e.g., "CA", "NY", "FL")
        
    Returns:
        Detailed information about weather alerts
    """
    # Implement the specific logic to get weather alerts
    return {"state": state, "alerts": []}

@server.tool()
async def get_forecast(latitude: float, longitude: float) -> dict:
    """
    Get the weather forecast for a specified latitude and longitude.
    
    Args:
        latitude: Latitude coordinate
        longitude: Longitude coordinate
        
    Returns:
        Weather forecast data
    """
    # Implement the specific logic to get the weather forecast
    return {"latitude": latitude, "longitude": longitude, "forecast": []}

# Register system resources
@server.resource()
def top_processes() -> str:
    """
    Get system process information.
    
    Returns:
        String representation of process information
    """
    # Implement the specific logic to get process information
    return subprocess.run("ps aux", capture_output=True, text=True).stdout

# Start the server
server.start()

Run the Server

Start the MCP server:

python your_server_script.py

💻 Usage Examples

Test Tools

Use the MCP CLI tool to test registered tools and resources:

1. List all available tools:

   mcp list-tools http://localhost:8000
   

2. Call the weather alert tool:

   mcp call-tool http://localhost:8000 get_weather_alerts --args '{"state": "CA"}'
   

3. Get the weather forecast:

   mcp call-tool http://localhost:8000 get_forecast --args '{"latitude": 37.7749, "longitude": -122.4194}'
   

4. View system resources:

   mcp list-resources http://localhost:8000
   

5. Get process information:

   mcp get-resource http://localhost:8000 top_processes
   

Debug with MCP Inspector

The MCP Inspector is a web interface tool that helps developers explore and test the functions of the MCP server:

1. Start the MCP Inspector:

   make dev-server
   

2. Open your browser and visit http://localhost:5173.
3. Explore tools, call tools, browse resources, and debug issues in the Inspector.

📚 Documentation

Add New Tools

To add a new tool, follow these steps:

1. Create a function in the corresponding tool module.
2. Register the function using the @server.tool() decorator.
3. Update the tool registration information in tools/__init__.py.

Example code:

@server.tool()
async def my_new_tool(param1: str, param2: int) -> str:
    """
    Tool description.
    
    Args:
        param1: Description of parameter 1
        param2: Description of parameter 2
        
    Returns:
        Description of the return value
    """
    # Implement the specific logic of the tool
    return result

Add New Resources

To add a new resource, follow these steps:

1. Create a function in the corresponding resource module.
2. Register the function using the @server.resource() decorator.
3. Update the resource registration information in resources/__init__.py.

Project Structure

your_project/
├── server.py          # MCP server implementation
├── tools/            # Tool modules
│   ├── weather.py    # Weather tools
│   └── system.py     # System tools
├── resources/        # Resource modules
│   ├── weather_data.py  # Weather data resources
│   └── system_info.py   # System information resources
└── requirements.txt  # Dependency management file

Dependency Management

The project's dependencies are included in the requirements.txt file. Install them using pip:

pip install -r requirements.txt

📄 License

This project is licensed under the MIT License. See the LICENSE file for details.

Contribution Guidelines

Contributions are welcome! Refer to CONTRIBUTING.md for detailed guidelines on how to participate in the development.

This project demonstrates how to quickly build a functional platform integrating weather services and system tools using the MCP protocol. By extending the tool and resource modules, its functionality and applicable scenarios can be further enhanced.