Weather MCP App
An MCP server that provides current weather, hourly and 7-day forecasts, and air quality data for any city or zip code, with an interactive React UI and support for both stdio and HTTP transports.
README
Weather MCP App
<p align="center"> <img src="https://img.shields.io/badge/Version-0.0.1-blue" alt="Version"> <img src="https://img.shields.io/badge/License-MIT-green" alt="License"> <img src="https://img.shields.io/badge/TypeScript-5.9+-3178c6" alt="TypeScript"> <img src="https://img.shields.io/badge/React-19-61dafb" alt="React"> </p>
A Model Context Protocol (MCP) server with an interactive React UI for fetching weather data. Works with Claude Desktop, ChatGPT, and any MCP-compatible client.
Features
- Current Weather - Real-time temperature, feels-like, humidity, wind speed/direction
- Hourly Forecast - 24-hour forecast with weather icons
- 7-Day Forecast - Daily high/low temperatures and conditions
- Air Quality - US AQI, PM2.5, PM10, and ozone levels
- Unit Toggle - Switch between Celsius and Fahrenheit
- Dual Transport - Works with stdio (Claude Desktop) and HTTP (ChatGPT)
- Rate Limiting - 100/hour, 1000/day, 30000/month
Installation
# Clone the repository
git clone <repository-url>
cd weather-mcp-app
# Install dependencies
npm install
# Build the project
npm run build
Quick Start
Claude Desktop (Stdio)
# Run with stdio transport
npm run start:stdio
ChatGPT (HTTP)
# Run HTTP server (listens on http://localhost:3001/mcp)
npm run start
# Or in development with hot reload
npm run dev
Configuration
Claude Desktop
Add to your Claude Desktop settings (~/Library/Application Support/Claude/settings.json):
{
"mcpServers": {
"weather-mcp-app": {
"command": "npx",
"args": ["-y", "weather-mcp-app", "--stdio"]
}
}
}
Or if running locally:
{
"mcpServers": {
"weather-mcp-app": {
"command": "node",
"args": ["path/to/weather-mcp-app/dist/main.js", "--stdio"]
}
}
}
ChatGPT
Use the HTTP endpoint: http://localhost:3001/mcp
Usage
Tool: get_weather
name: get_weather
description: Get current weather, hourly forecast, 7-day forecast, and air quality for a city name or zip code.
Input Parameters
| Parameter | Type | Required | Description |
|---|---|---|---|
location |
string | Yes | City name (e.g., "London") or zip code (e.g., "10001,US") |
unit |
string | No | "celsius" or "fahrenheit" (default: "celsius") |
Example Request
{
"name": "get_weather",
"arguments": {
"location": "San Francisco, CA",
"unit": "celsius"
}
}
Example Response
{
"content": [
{
"type": "text",
"text": "Weather in San Francisco:\nMainly clear, 18°C\nFeels like 17°C\nHumidity: 65%\nWind: WNW 15 km/h\nAir Quality: Good (AQI: 35)\n\nHourly Forecast:\nNow: 18°C ☀️\n1PM: 19°C 🌤️\n...\n\n7-Day Forecast:\nToday: 15° - 20°, Mainly clear\nTue: 14° - 19°, Partly cloudy\n..."
}
],
"structuredContent": {
"current": { ... },
"hourly": [ ... ],
"daily": [ ... ],
"location": { ... },
"airQuality": { ... }
}
}
Project Structure
weather-mcp-app/
├── src/
│ ├── api/
│ │ └── weather-client.ts # Open-Meteo API client
│ ├── constants/
│ │ └── weather.ts # Weather codes & utilities
│ ├── handlers/
│ │ └── weather-handler.ts # MCP tool handler
│ ├── services/
│ │ └── weather-formatter.ts # Text formatting
│ ├── types/
│ │ └── weather.ts # Zod schemas & types
│ ├── errors/
│ │ └── index.ts # Custom errors
│ ├── utils/
│ │ └── logger.ts # Logging utilities
│ ├── components/ui/ # shadcn/ui components
│ ├── App.tsx # Main React UI
│ ├── server.ts # MCP server setup
│ ├── main.ts # Entry point
│ └── config.ts # Configuration
├── dist/ # Built output
│ ├── main.js # Compiled server
│ └── mcp-app.html # Compiled UI
├── package.json
├── tsconfig.json
├── vite.config.ts
└── README.md
Environment Variables
| Variable | Description | Default |
|---|---|---|
PORT |
HTTP server port | 3001 |
NODE_ENV |
Environment mode | development |
ALLOWED_ORIGINS |
CORS origins (production) | - |
Development Commands
# Build the project
npm run build
# Build server only
npm run build:server
# Run with stdio transport
npm run start:stdio
# Run with HTTP server
npm run start
# Development mode with watch
npm run dev
# Type checking
npm run typecheck
# Run tests
npm run test
# Run unit tests
npm run test:unit
# Run e2e tests
npm run test:e2e
API Reference
Uses free Open-Meteo APIs (no API key required):
- Geocoding:
https://geocoding-api.open-meteo.com/v1/search - Weather:
https://api.open-meteo.com/v1/forecast - Air Quality:
https://air-quality-api.open-meteo.com/v1/air-quality
Security
- HSTS headers enabled in production
- CORS restricted to localhost in development
- Request body limit: 10KB
- Input validation with Zod schemas
- Rate limiting on all requests
- Structured logging with Pino
Changelog
See CHANGELOG.md for detailed changes.
Acknowledgments
- Open-Meteo API - Free weather and air quality data API. This project uses their Geocoding, Weather Forecast, and Air Quality APIs.
- MCP Apps SDK - For enabling interactive UI capabilities in MCP servers.
- shadcn/ui - For the beautiful and accessible React components.
- Lucide - For the icon library.
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。