MCP 服务器

Weather MCP Server

Provides real-time weather alerts and forecasts for US locations by integrating with the National Weather Service API. Supports both server and client interactions with optional LLM summarization.

README

🌦️ Weather MCP Server and Client

Welcome to the Weather Model Context Protocol (MCP) Project! This project provides real-time weather intelligence by integrating with external APIs like the National Weather Service (NWS). It is built using the FastMCP framework and supports both server and client interactions.

🚀 Features

Weather Alerts: Fetch weather alerts for any US state.
Weather Forecasts: Get detailed weather forecasts for specific locations.
Asynchronous Operations: Fully asynchronous for high performance.
Modular Design: Clean separation of server, client, and utility logic.
LLM Integration: Summarize weather data using a language model (DistilGPT-2).

📂 Project Structure

server.py: The main server file that registers tools for fetching weather alerts and forecasts.
client.py: A command-line client to interact with the server.
app.py: A Streamlit-based web app for user-friendly interaction.
agent.py: An advanced client integrating a language model for summarizing weather data.

🛠️ Setup Instructions

Clone the Repository:
```
git clone <repository-url>
cd mcp
```
Install Dependencies: Ensure Python 3.8+ is installed, then run:
```
pip install -r requirements.txt
```
Run the Server: Start the FastMCP server:
```
python server.py
```
Interact with the Client: Use the command-line client or the Streamlit app to interact with the server.

🖥️ Usage

Command-Line Client

List Available Tools:
```
python client.py list_tools
```
Fetch Alerts:
```
python client.py get_alerts --state CA
```

Fetch Forecasts:

python client.py get_forecast --latitude 34.05 --longitude -118.25

Streamlit Web App

Run the app:
```
streamlit run app.py
```
Use the sidebar to select actions like "List Tools," "Get Alerts," or "Get Forecast."

LLM Integration

Summarize weather data using the language model:

python agent.py interact_with_llm --llm_action get_alerts --state CA
python agent.py interact_with_llm --llm_action get_forecast --latitude 34.05 --longitude -118.25

🎥 Video Demonstration

Watch a quick demonstration of the Weather MCP Project in action:

[Weather MCP Demo]

🌐 External Dependencies

FastMCP: Framework for building MCP servers and clients.
httpx: For making asynchronous HTTP requests.
Streamlit: For building the web app.
Transformers: For integrating the DistilGPT-2 language model.

📋 Notes

Ensure the server is running before using the client or web app.
Follow the asynchronous programming model to avoid blocking operations.

❤️ Acknowledgments

FastMCP for the server-client framework.
National Weather Service (NWS) for providing weather data.
Hugging Face Transformers for the DistilGPT-2 model.

🤝 Contributing

We welcome contributions to the Weather MCP Project! Here's how you can help:

Report Bugs: If you encounter any issues, please open an issue on the GitHub repository.
Suggest Features: Have an idea for a new feature? Let us know by creating a feature request.
Submit Pull Requests: Fork the repository, make your changes, and submit a pull request for review.
Improve Documentation: Help us enhance the documentation by fixing typos, adding examples, or clarifying instructions.