Weather MCP Server
Provides weather forecasts for US locations using OpenStreetMap geocoding and the National Weather Service API, enabling natural language queries like city names or addresses.
README
Weather MCP Server
An MCP (Model Context Protocol) server that provides weather forecasts using OpenStreetMap Nominatim for geocoding and the National Weather Service (Weather.gov) API for forecast data.
Features
- Single tool:
get_weather_forecast- Get weather forecasts for any city, state, or address - Uses OpenStreetMap Nominatim for free geocoding (no API key required)
- Uses Weather.gov API for accurate, free weather data (US locations only)
- Returns detailed forecast periods with temperature, wind, and conditions
Installation
- Install dependencies:
npm install
- Build the project:
npm run build
Configuration
Add this server to your Claude Desktop config file:
macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
Windows: %APPDATA%\Claude\claude_desktop_config.json
{
"mcpServers": {
"weather": {
"command": "node",
"args": ["/Users/atharvawadekar/Desktop/Projects/WeatherMCP/dist/index.js"]
}
}
}
Usage
Once configured, you can ask Claude:
- "What's the weather in Seattle?"
- "Get me the forecast for Miami, FL"
- "What's the weather like in Portland, Oregon?"
- "Tell me the weather for 1600 Pennsylvania Ave, Washington DC"
Tool Details
get_weather_forecast
Input:
location(string): City name, state, or full address
Output:
- Location name and coordinates
- NWS forecast office
- Multiple forecast periods with:
- Period name (Today, Tonight, Tomorrow, etc.)
- Temperature
- Wind speed and direction
- Short and detailed forecast descriptions
How It Works
- Takes a location string (city, state, or address)
- Geocodes it using OpenStreetMap Nominatim to get latitude/longitude
- Calls Weather.gov
/points/{lat},{lon}to get grid data - Fetches the forecast from the returned forecast URL
- Formats and returns the weather data
Limitations
- US locations only: Weather.gov only provides data for US locations
- Rate limits: Be respectful of Nominatim's usage policy (max 1 request/second)
- Geocoding accuracy: Results depend on OpenStreetMap's geocoding quality
Development
Run in development mode with auto-rebuild:
npm run dev
License
MIT
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。