mcp-weather-server
Provides real-time weather, 5-day forecasts, and weather alerts for US states via NWS and WeatherAPI.com, accessible through natural language queries.
README
Weather MCP Server 🌤️ written in TypeScript
A Model Context Protocol (MCP) server that provides real-time weather information, forecasts, and alerts using the National Weather Service API and WeatherAPI.com.
Features
- 🌤️ Current Weather - Get real-time weather conditions for any location worldwide
- 📅 5-Day Forecasts - Detailed weather forecasts with temperature, wind, and conditions
- ⚠️ Weather Alerts - Active weather alerts and warnings for US states
- 🌍 Global Support - Location search via geocoding (city names, landmarks, etc.)
- 🔒 Type-Safe - Built with TypeScript for reliability
Prerequisites
- Node.js 18+
- npm or yarn
- A free API key from WeatherAPI.com
Installation
# Clone the repository
git clone https://github.com/YOUR_USERNAME/weather-mcp-server.git
cd weather-mcp-server
# Install dependencies
npm install
# Create environment file
cp .env.example .env
Configuration
Sign up for a free API key at WeatherAPI.com
Edit .env and add your API key:
env
WEATHER_API_KEY=your_api_key_here
Usage
Development Mode (TypeScript)
bash
npm run dev
Production Build
bash
# Build the project
npm run build
# Run the built version
npm start
Testing with MCP Inspector
bash
# Test with TypeScript source
npm run inspect
# Test with built JavaScript
npm run inspect-built
Integration
Cline (VS Code Extension)
Add to %APPDATA%\Code\User\globalStorage\cline.cline\settings\cline_mcp_settings.json:
json
{
"mcpServers": {
"weather-server": {
"command": "node",
"args": [
"C:\\path\\to\\weather-server\\build\\index.js"
],
"env": {
"WEATHER_API_KEY": "your_api_key_here"
}
}
}
}
Claude Desktop
Add to %APPDATA%\Claude\claude_desktop_config.json:
json
{
"mcpServers": {
"weather": {
"command": "node",
"args": [
"C:\\path\\to\\weather-server\\build\\index.js"
],
"env": {
"WEATHER_API_KEY": "your_api_key_here"
}
}
}
}
Available Tools
get_current_weather
Get current weather conditions for any location.
Input:
json{
"name": "London"
}
Output:
json
{
"location": "London",
"coordinates": { "lat": 51.5074, "lon": -0.1278 },
"temperature": 72,
"temperatureUnit": "F",
"windSpeed": "10 mph",
"windDirection": "SW",
"shortForecast": "Partly Cloudy",
"detailedForecast": "Partly cloudy with a high near 72..."
}
get_forecast
Get 5-day weather forecast for any location.
Input:
json
{
"name": "New York"
}
Output:
json
{
"location": "New York",
"coordinates": { "lat": 40.7128, "lon": -74.0060 },
"forecast": [
{
"name": "Tonight",
"temperature": 45,
"temperatureUnit": "F",
"windSpeed": "5 mph",
"windDirection": "N",
"shortForecast": "Clear",
"detailedForecast": "Clear skies with low around 45..."
}
// ... more periods
]
}
get-alerts
Get active weather alerts for US states.
Input:
json
{
"state": "CA"
}
Output:
json
{
"state": "CA",
"alerts": [
{
"event": "Heat Advisory",
"headline": "Heat Advisory issued June 15...",
"severity": "Moderate",
"urgency": "Expected",
"certainty": "Likely",
"areaDesc": "Los Angeles County"
}
]
}
Development
Project Structure
weather-server/
├── src/
│ └── index.ts # TypeScript source code
├── build/
│ └── index.js # Compiled JavaScript (generated)
├── .env # Environment variables (not in git)
├── .env.example # Example environment file
├── .gitignore # Git ignore rules
├── package.json # Dependencies and scripts
├── tsconfig.json # TypeScript configuration
└── README.md # This file
Scripts
bash
npm run dev # Run in development mode with tsx
npm run build # Build TypeScript to JavaScript
npm start # Run built JavaScript version
npm run inspect # Test with MCP Inspector (TypeScript)
npm run inspect-built # Test with MCP Inspector (JavaScript)
APIs Used
- National Weather Service API - Free US weather data
- WeatherAPI.com - Global geocoding and location search
Limitations
- Weather alerts (get-alerts) only work for US locations (NWS limitation)
- Current weather and forecasts are US-focused but work globally via geocoding
- Rate limits apply based on your WeatherAPI.com plan (free tier: 1M calls/month)
Troubleshooting
"WEATHER_API_KEY environment variable is required"
- Make sure .env file exists with valid API key
- Check that the key is not expired
"This location might not be supported by the NWS API"
- NWS only covers US locations for detailed forecasts
- Try a US city or use the geocoding to verify location
Type errors in development
- Run npm install to ensure all dependencies are installed
- Check that TypeScript version is 5.7+ with npx tsc --version
## Cline/Claude Desktop Integration
### Cline (VS Code Extension)
**Config Location (depends on Cline version):**
- **Newer versions:** `%APPDATA%\Code\User\globalStorage\cline.cline\settings\cline_mcp_settings.json`
- **Older versions:** `%APPDATA%\Code\User\globalStorage\saoudrizwan.claude-dev\settings\cline_mcp_settings.json`
**Configuration:**
```json
{
"mcpServers": {
"weather-server": {
"command": "node",
"args": [
"C:\\path\\to\\weather-server\\build\\index.js"
],
"env": {
"WEATHER_API_KEY": "your_api_key_here"
},
"autoApprove": [
"get_current_weather",
"get_forecast",
"get-alerts"
]
}
}
}
Contributing
Contributions are welcome! Please feel free to submit a Pull Request.
- Fork the repository
- Create your feature branch (git checkout -b feature/AmazingFeature)
- Commit your changes (git commit -m 'Add some AmazingFeature')
- Push to the branch (git push origin feature/AmazingFeature)
- Open a Pull Request
License
This project is licensed under the MIT License - see the LICENSE file for details.
Author
Herman Adu
Acknowledgments
- Model Context Protocol by Anthropic
- National Weather Service API
- WeatherAPI.com
Support
If you have questions or need help:
- Open an issue on GitHub
- Check the MCP Documentation
Built with ❤️ using the Model Context Protocol
---
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。