Weather MCP Server
Provides real-time weather forecasts and alerts for US locations using the National Weather Service API. Supports querying forecasts by coordinates and retrieving active weather alerts by state.
README
Weather MCP Server
A Model Context Protocol (MCP) server that provides weather information using the National Weather Service API. This server exposes tools for getting weather forecasts and alerts for US locations.
Features
- 🌤️ Weather Forecasts: Get detailed weather forecasts for any US location using latitude/longitude coordinates
- 🚨 Weather Alerts: Retrieve active weather alerts for any US state
- 🔌 MCP Integration: Works seamlessly with Claude for Desktop and other MCP-compatible clients
- 📡 Real-time Data: Fetches live data from the National Weather Service API
Tools Available
get-forecast
Get weather forecast for a specific location.
Parameters:
latitude(float): Latitude of the location (-90 to 90)longitude(float): Longitude of the location (-180 to 180)
Example usage:
- "What's the weather forecast for San Francisco?" (Claude will use coordinates ~37.7749, -122.4194)
- "Give me the weather forecast for latitude 47.6062, longitude -122.3321" (Seattle)
get-alerts
Get active weather alerts for a US state.
Parameters:
state(string): Two-letter US state code (e.g., "CA", "NY", "TX")
Example usage:
- "What are the active weather alerts in California?"
- "Are there any weather warnings in Texas?"
Prerequisites
- Python 3.10 or higher
uvpackage manager- Access to the internet (for NWS API calls)
Installation
-
Install uv (if not already installed):
# macOS/Linux curl -LsSf https://astral.sh/uv/install.sh | sh # Windows powershell -ExecutionPolicy ByPass -c "irm https://astral.sh/uv/install.ps1 | iex" -
Clone or navigate to the project directory:
cd weather -
Install dependencies:
uv sync
Running the Server
Standalone Testing
To test the server directly:
uv run weather.py
The server will start and listen on standard input/output. You can test it using the MCP inspector or other MCP clients.
With Claude for Desktop
-
Install Claude for Desktop from claude.ai/download
-
Configure Claude for Desktop by editing the configuration file:
macOS/Linux:
code ~/Library/Application\ Support/Claude/claude_desktop_config.jsonWindows:
code $env:AppData\Claude\claude_desktop_config.json -
Add the weather server configuration:
macOS/Linux:
{ "mcpServers": { "weather": { "command": "uv", "args": [ "--directory", "/ABSOLUTE/PATH/TO/YOUR/weather", "run", "weather.py" ] } } }Windows:
{ "mcpServers": { "weather": { "command": "uv", "args": [ "--directory", "C:\\ABSOLUTE\\PATH\\TO\\YOUR\\weather", "run", "weather.py" ] } } } -
Restart Claude for Desktop completely
-
Verify the integration by looking for the "Search and tools" icon in Claude for Desktop
Usage Examples
Once configured with Claude for Desktop, you can ask questions like:
- "What's the weather forecast for Sacramento?"
- "Give me the weather forecast for New York City"
- "What are the active weather alerts in Florida?"
- "Are there any severe weather warnings in Texas?"
- "What's the weather like at coordinates 40.7128, -74.0060?" (NYC)
API Details
This server uses the National Weather Service API (api.weather.gov), which:
- Provides free access to US weather data
- Requires no API key
- Returns data in JSON format
- Only covers US locations
Project Structure
weather/
├── main.py # Entry point (if needed)
├── weather.py # Main MCP server implementation
├── pyproject.toml # Project configuration and dependencies
├── uv.lock # Dependency lock file
└── README.md # This file
Troubleshooting
Server Not Showing Up in Claude
-
Check the configuration file syntax - Ensure valid JSON
-
Verify the absolute path - Use full paths, not relative ones
-
Check Claude's logs:
# macOS/Linux tail -f ~/Library/Logs/Claude/mcp*.log # Windows # Check logs in %AppData%\Claude\logs\ -
Restart Claude for Desktop completely
Tool Calls Failing
- Verify the server runs standalone:
uv run weather.py - Check for rate limiting - The NWS API has rate limits
- Ensure coordinates are for US locations - The NWS API only covers the US
- Check internet connectivity - Server needs to reach api.weather.gov
Common Error Messages
- "Failed to retrieve grid point data": Usually means coordinates are outside the US
- "No active alerts for this state": Not an error - just means no current alerts
- "Unable to fetch forecast data": Network issue or invalid coordinates
Development
Adding New Tools
To add new weather-related tools:
- Add the tool using the
@mcp.tool()decorator - Implement the async function with proper type hints
- Add error handling and validation
- Test with
uv run weather.py
Dependencies
Key dependencies (managed by uv):
mcp: Model Context Protocol SDKhttpx: HTTP client for API requestsfastmcp: Simplified MCP server framework
License
This project is part of the Model Context Protocol ecosystem. Check individual dependencies for their licenses.
Contributing
Feel free to submit issues and pull requests to improve the weather server functionality.
Related Resources
推荐服务器
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。
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。
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。
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。
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。
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。
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。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
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。