AI导哈

天气模型上下文协议服务器

一个基于FastMCP的简单模型上下文协议（MCP）服务器，用于向AI运行时暴露自定义工具，如获取天气数据。

  • by bhavesh-kalluru
  • Python
  • 本地部署
  • 更新于
在 GitHub 查看 bhavesh-kalluru/First-MCP-server-in-Claude

使用说明

🌤️ 基于FastMCP的气象MCP服务器

一个简单的 模型上下文协议（MCP） 服务器构建于 FastMCP 演示了如何将自定义工具暴露给AI运行时。
该示例定义了单个工具， get_weather，它返回给定位置的模拟天气数据。

🚀 特性

  • ✅ 最小、易于理解的MCP服务器
  • ⚙️ 实现a get_weather 工具
  • 🧩 已准备好与MCP兼容的客户端集成
  • 🐍 用干净、现代的Python编写

🧠 运作原理

这 FastMCP 类封装了MCP stdio服务器的样板设置和通信。
当服务器启动时，它会暴露 get_weather 作为其他代理或IDE可以调用的可调用MCP工具。

🧩 代码概述

from mcp.server.fastmcp import FastMCP

mcp = FastMCP("weather")

@mcp.tool()
def get_weather(location: str) -> str:
    """Get the current weather for a given location."""
    return f"The current weather in {location} is sunny with a temperature of 25°C."

if __name__ == "__main__":
    mcp.run()
⚡️ Getting Started
1️⃣ Clone the repo
bash
Copy code
git clone https://github.com/<your-username>/weather-mcp.git
cd weather-mcp
2️⃣ Create a virtual environment
bash
Copy code
uv venv
source .venv/bin/activate  # macOS/Linux
3️⃣ Install dependencies
bash
Copy code
uv pip install 'mcp[cli]'
4️⃣ Run the server
bash
Copy code
uv run python main.py
If everything is configured correctly, the server will start and listen for MCP stdio connections.

🔍 Example Usage
You can connect this MCP server to any MCP-compatible client (e.g., an IDE, LLM runtime, or agent).
When prompted, provide:

Setting	Value
Command	uv
Arguments	run --directory /path/to/weather-mcp python main.py

🧰 Project Structure
bash
Copy code
weather-mcp/
│
├── main.py          # MCP server source
├── pyproject.toml   # Project metadata (for uv/pdm)
└── README.md        # You are here
💡 Future Improvements
Integrate with a real weather API (e.g., OpenWeatherMap)

Add error handling and temperature units

Extend to multi-location forecasting and alerts

👨‍💻 Author
Bhavesh Kalluru
AI Engineer | Generative AI | LLM Applications | MCP Integrations
📍 Looking for full-time opportunities in the U.S.

相关 MCP