Weather MCP Server
Provides weather data from OpenWeatherMap API through MCP tools and a REST API with OpenAPI support. Enables LLM agents to retrieve current weather, forecasts, and temperature ranges by city or coordinates.
README
Weather MCP Server
A Model Context Protocol (MCP) server for weather data with OpenAPI support. This server provides weather information from OpenWeatherMap API and can be used by LLM agents through MCP.
Features
- MCP stdio transport for LLM agent integration
- HTTP REST API with OpenAPI 3.0 specification
- 4 weather tools:
- Get current weather by city
- Get current weather by coordinates
- Get weather forecast (5-day, 3-hour intervals)
- Get temperature range summary
- Mock data support for testing without API key
- TypeScript implementation with full type safety
Installation
cd weather-mcp-server
npm install
npm run build
Usage
1. MCP Server (stdio transport)
Run the MCP server for LLM agents:
npm start
Or in development mode:
npm run dev
2. HTTP Server with OpenAPI
Run the HTTP server with REST API:
npm run dev:http
The server will start on http://localhost:3000 with:
/health- Health check endpoint/openapi- OpenAPI specification/api/v1/weather/current/{city}- Current weather by city/api/v1/weather/current/coordinates- Current weather by coordinates/api/v1/weather/forecast/{city}- Weather forecast
3. Configuration
Set your OpenWeatherMap API key (optional - mock data will be used if not provided):
export OPENWEATHER_API_KEY=your_api_key_here
Or create a .env file:
OPENWEATHER_API_KEY=your_api_key_here
MCP Tools
The server provides the following MCP tools:
| Tool Name | Description | Parameters |
|---|---|---|
weather_get_current_by_city |
Get current weather by city | city: string |
weather_get_current_by_coords |
Get current weather by coordinates | latitude: number, longitude: number |
weather_get_forecast |
Get weather forecast | city: string, days?: number (1-10, default: 5) |
weather_get_temperature_range |
Get temperature range summary | city: string |
API Endpoints
HTTP REST API
All endpoints return JSON with the following structure:
{
"success": true,
"data": { ... }
}
1. Current Weather by City
GET /api/v1/weather/current/{city}
Example:
curl http://localhost:3000/api/v1/weather/current/London
2. Current Weather by Coordinates
GET /api/v1/weather/current/coordinates?lat={latitude}&lon={longitude}
Example:
curl "http://localhost:3000/api/v1/weather/current/coordinates?lat=51.5074&lon=-0.1276"
3. Weather Forecast
GET /api/v1/weather/forecast/{city}?days={days}
Example:
curl "http://localhost:3000/api/v1/weather/forecast/New%20York?days=3"
Testing
Run the test suite:
npm test
Run MCP inspector for debugging:
npm run inspect
Project Structure
weather-mcp-server/
├── src/
│ ├── index.ts # MCP stdio server
│ ├── http-server.ts # HTTP server with OpenAPI
│ ├── types/
│ │ └── weather.ts # TypeScript types and Zod schemas
│ ├── utils/
│ │ └── weather-client.ts # OpenWeatherMap API client
│ └── tools/
│ └── weather-tools.ts # MCP tool definitions
├── dist/ # Compiled JavaScript
├── test/
│ └── test.js # Test suite
├── package.json
├── tsconfig.json
└── README.md
Dependencies
@modelcontextprotocol/sdk- MCP SDK for TypeScriptexpress- HTTP server frameworkaxios- HTTP client for API callszod- Schema validationtypescript- TypeScript compiler
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。