Weather MCP Server
Provides weather information tools including alerts for US states and forecasts by coordinates using the National Weather Service API. Uses streamable HTTP transport for scalable, multi-session connections.
README
Weather MCP Server
A Node.js Model Context Protocol (MCP) server that provides weather information tools using Streamable HTTP Transport.
Features
- get-alerts: Get weather alerts for a US state
- get-forecast: Get weather forecast for a location using latitude/longitude coordinates
- HTTP Transport: Uses streamable HTTP instead of stdio for better scalability
- Session Management: Supports multiple concurrent client sessions
- Health Check: Built-in health monitoring endpoint
Setup
- Install dependencies:
npm install
- Build the TypeScript code:
npm run build
- Start the HTTP server:
npm start
The server will start on port 3000 by default.
Usage
This server implements the Model Context Protocol using HTTP transport. It provides:
- MCP Endpoint:
http://localhost:3000/mcp - Health Check:
http://localhost:3000/health
get-alerts
Get weather alerts for a US state.
Parameters:
state(string): Two-letter state code (e.g., "CA", "NY")
HTTP Example:
curl -X POST http://localhost:3000/mcp \
-H "Content-Type: application/json" \
-H "mcp-session-id: your-session-id" \
-d '{
"jsonrpc": "2.0",
"id": 1,
"method": "tools/call",
"params": {
"name": "get-alerts",
"arguments": {
"state": "CA"
}
}
}'
get-forecast
Get weather forecast for a location using coordinates.
Parameters:
latitude(number): Latitude (-90 to 90)longitude(number): Longitude (-180 to 180)
HTTP Example:
curl -X POST http://localhost:3000/mcp \
-H "Content-Type: application/json" \
-H "mcp-session-id: your-session-id" \
-d '{
"jsonrpc": "2.0",
"id": 1,
"method": "tools/call",
"params": {
"name": "get-forecast",
"arguments": {
"latitude": 40.7128,
"longitude": -74.0060
}
}
}'
MCP Client Configuration
Use this configuration in your MCP client:
{
"mcpServers": {
"weather": {
"transport": {
"type": "http",
"url": "http://localhost:3000/mcp"
}
}
}
}
Development
- Run in development mode:
npm run dev
- Test the server:
npm test
- Health check:
curl http://localhost:3000/health
Transport Features
- Session Management: Each client gets a unique session ID
- Concurrent Connections: Multiple clients can connect simultaneously
- Server-Sent Events: Real-time notifications via GET requests
- Session Termination: Clean session cleanup via DELETE requests
- DNS Rebinding Protection: Disabled for local development (enable in production)
Security Note
For production deployments, enable DNS rebinding protection:
// In src/index.ts
enableDnsRebindingProtection: true,
allowedHosts: ['your-domain.com'],
allowedOrigins: ['https://your-domain.com'],
Environment Variables
PORT: Server port (default: 3000)
API Endpoints
POST /mcp: Main MCP communication endpointGET /mcp: Server-to-client notifications (SSE)DELETE /mcp: Session terminationGET /health: Health check endpoint
Requirements
- Node.js 18 or higher
- TypeScript 5.5 or higher
- Internet connection for weather API access
Directory Structure
weather-server/
├── src/
│ └── index.ts # Main HTTP server implementation
├── dist/ # Compiled JavaScript output
├── package.json # Node.js dependencies and scripts
├── tsconfig.json # TypeScript configuration
├── test.js # HTTP client test script
├── mcp-config.json # MCP client configuration
└── README.md # This file
Requirements
- Node.js 18 or higher
- TypeScript 5.5 or higher
- Internet connection for weather API access
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。