MCP Weather Server
Exposes weather forecast APIs as MCP tools, allowing LLMs to retrieve current weather conditions and multi-day forecasts for any location using latitude and longitude coordinates.
README
MCP Weather Server
A lightweight, self‑hosted Model Context Protocol (MCP) server that exposes your weather‑forecast API as MCP tools.
This allows LLMs and agent frameworks to call your weather data directly through a standardized interface.
Clients run this server inside their own environment and connect it to their preferred MCP‑compatible LLM (e.g., Claude Desktop, Cursor, etc.).
🚀 Features
- MCP‑compatible WebSocket server
- Tools for:
- Current weather by latitude/longitude
- Multi‑day forecast
- JSON Schema–validated tool inputs
- Simple configuration via environment variables
- No external dependencies required to run the server (beyond Node.js)
- Ready for Docker, CI, and cloud deployment
📦 Project Structure
``` mcp-weather-server/ ├── src/ │ ├── api/ # Weather API client wrapper │ ├── tools/ # MCP tool implementations │ ├── schemas/ # JSON Schemas for tool inputs │ ├── types/ # MCP type definitions │ ├── server.ts # MCP WebSocket server │ ├── config.ts # Environment config loader │ └── index.ts # Entrypoint ├── test/ # Jest test placeholders ├── sdk-js/ # Optional JS SDK (client helper) ├── package.json ├── tsconfig.json ├── .env.example └── README.md ```
🛠️ Requirements
- Node.js 20+
- A valid API key for your weather service
- Access to your weather API base URL
⚙️ Configuration
Copy the example environment file:
```bash cp .env.example .env ```
Then edit `.env`:
``` WEATHER_API_KEY=your_api_key_here WEATHER_API_URL=https://api.yourweather.com PORT=3001 LOG_LEVEL=info ```
▶️ Running the Server
Development mode
```bash npm run dev ```
Build & run
```bash npm run build npm start ```
The server will start on:
``` ws://localhost:3001 ```
🌤️ Available MCP Tools
`getCurrentWeather`
Retrieve current weather conditions for a specific latitude/longitude.
Input:
```json { "lat": 38.9, "lon": -77.0 } ```
Output (example):
```json { "summary": "Current weather at (38.9, -77)", "data": { ... } } ```
`getForecast`
Retrieve a multi‑day forecast for a location.
Input:
```json { "lat": 38.9, "lon": -77.0, "days": 5 } ```
Output (example):
```json { "summary": "5‑day forecast for (38.9, -77)", "data": { ... } } ```
🧪 Testing
```bash npm test ```
🐳 Docker (Optional)
A Dockerfile is included.
Build:
```bash docker build -t mcp-weather-server . ```
Run:
```bash docker run -p 3001:3001 \ -e WEATHER_API_KEY=your_api_key \ -e WEATHER_API_URL=https://api.yourweather.com \ mcp-weather-server ```
🔒 Security Notes
- Host this server inside your network or VPC
- Protect access with firewall rules or mTLS if exposing externally
- Rotate API keys regularly
- Avoid exposing your weather API key in logs or client‑side code
📄 License
MIT License.
Feel free to fork, modify, and integrate into your own systems.
🤝 Contributing
Pull requests and issues are welcome.
If you extend the toolset or add new weather endpoints, feel free to contribute back.
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。