MCP Weather Server

MCP Weather Server

Provides weather forecasts, alerts, and current conditions via the Model Context Protocol, using simulated data and supporting both stdio and HTTP transports.

Category
访问服务器

README

🌤️ MCP Weather Server

A production-ready Model Context Protocol weather server built with the official Anthropic FastMCP Python SDK. Provides weather forecasts, alerts, and current conditions through a standardized AI-agent interface.

License: MIT Python 3.10+ MCP SDK


✨ Features

  • 🔧 2 Tools: get_alerts (weather alerts by state) and get_forecast (5-day forecast by coordinates)
  • 📄 1 Resource: weather://{state}/current — formatted current conditions
  • 💬 1 Prompt: weather_assistant(state) — guided weather analysis template
  • 🔌 Dual Transport: stdio (local clients) and Streamable HTTP (remote clients)
  • 🪵 Structured Logging: All server logs go to stderr (compatible with stdio transport)
  • 📦 No API Keys Required: Uses realistic simulated weather data
  • 🧪 Test Client Included: Ready-to-run example client

🚀 Quick Start

Option 1: pip

python3 -m venv .venv
source .venv/bin/activate
pip install -r requirements.txt
python weather_server.py

Option 2: uv (recommended)

uv venv
source .venv/bin/activate
uv add "mcp[cli]>=1.27,<2" httpx
python weather_server.py

Option 3: Setup script

chmod +x setup.sh
./setup.sh
python weather_server.py

📋 Usage

stdio Transport (default)

python weather_server.py

The server listens on stdin/stdout, ready to connect to Claude Desktop, Cursor, or any MCP client.

Streamable HTTP Transport

python weather_server.py --transport streamable-http --port 8000

Now available at http://localhost:8000/mcp for HTTP-based clients.

Run the Test Client

# In one terminal:
python weather_server.py

# In another terminal:
source .venv/bin/activate
python client_example.py

🛠️ Tools Reference

get_alerts(state: str) -> list[dict]

Get active weather alerts for a US state.

Parameter Type Description Example
state str 2-letter US state code "CA", "TX", "FL"

Returns: List of alerts with type, severity, and area.

get_forecast(latitude: float, longitude: float) -> list[dict]

Get a 5-day weather forecast for coordinates.

Parameter Type Description
latitude float Decimal degrees (-90 to 90)
longitude float Decimal degrees (-180 to 180)

Returns: 5-day forecast with date, temperature_f, condition, humidity_pct, wind_mph.


📄 Resources Reference

weather://{state}/current

Returns formatted current weather conditions for a state as markdown.


💬 Prompts Reference

weather_assistant(state: str)

Creates a weather analysis assistant prompt template.

Parameter Type Description
state str 2-letter US state code

🔌 Connecting to Clients

Claude Desktop

Add to your claude_desktop_config.json:

{
  "mcpServers": {
    "weather": {
      "command": "python",
      "args": ["/ABSOLUTE/PATH/TO/mcp-weather-server/weather_server.py"]
    }
  }
}

Cursor

In Cursor Settings → Features → MCP Servers, add:

  • Name: weather
  • Type: command
  • Command: python /ABSOLUTE/PATH/TO/mcp-weather-server/weather_server.py

HTTP Client (Streamable HTTP)

curl -X POST http://localhost:8000/mcp \
  -H "Content-Type: application/json" \
  -d '{"jsonrpc":"2.0","id":"1","method":"tools/list","params":{}}'

📁 Project Structure

mcp-weather-server/
├── weather_server.py      # Main server implementation
├── client_example.py      # Example MCP client
├── requirements.txt       # Python dependencies
├── setup.sh              # Automated setup script
├── README.md             # This file
└── .gitignore

🧠 Architecture

┌─────────────┐     stdio/HTTP      ┌──────────────────┐
│  MCP Client  │ ◄──────────────►  │  Weather Server   │
│ (Claude, etc)│                    │  (FastMCP)        │
└─────────────┘                     └──────────────────┘
                                           │
                                    ┌──────┴──────┐
                                    │  Simulated   │
                                    │  Weather Data│
                                    └─────────────┘

📜 License

MIT — see LICENSE for details.

🙌 Contributing

PRs welcome! Please ensure tools have proper type hints and docstrings.

推荐服务器

Baidu Map

Baidu Map

百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。

官方
精选
JavaScript
Playwright MCP Server

Playwright MCP Server

一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。

官方
精选
TypeScript
Magic Component Platform (MCP)

Magic Component Platform (MCP)

一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。

官方
精选
本地
TypeScript
Audiense Insights MCP Server

Audiense Insights MCP Server

通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。

官方
精选
本地
TypeScript
VeyraX

VeyraX

一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。

官方
精选
本地
graphlit-mcp-server

graphlit-mcp-server

模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。

官方
精选
TypeScript
Kagi MCP Server

Kagi MCP Server

一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。

官方
精选
Python
e2b-mcp-server

e2b-mcp-server

使用 MCP 通过 e2b 运行代码。

官方
精选
Neon MCP Server

Neon MCP Server

用于与 Neon 管理 API 和数据库交互的 MCP 服务器

官方
精选
Exa MCP Server

Exa MCP Server

模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。

官方
精选