mcp-weather-server
Enables MCP clients like Kiro and Claude to access current weather conditions and forecasts for any location using the OpenWeatherMap API.
README
MCP Weather Server
A Model Context Protocol (MCP) server that provides weather data through OpenWeatherMap API. This server enables MCP clients like Kiro and Claude to access current weather conditions and forecasts for any location.
Features
- Current Weather: Get real-time weather data including temperature, conditions, humidity, wind speed, and more
- Weather Forecasts: Retrieve weather forecasts for up to 8 days
- Flexible Location Input: Support for both city names and latitude/longitude coordinates
- Comprehensive Data: Includes UV index, sunrise/sunset times, atmospheric pressure, and visibility
- Error Handling: Robust error management with descriptive messages
- MCP Protocol: Full compliance with Model Context Protocol specification
Prerequisites
- Python 3.10 or higher
- OpenWeatherMap API key (free tier available at openweathermap.org)
uvanduvxinstalled (see installation guide)
Installation
For Use with Kiro or Other MCP Clients
No manual installation required! The server will be automatically downloaded and run via uvx.
For Development
- Clone the repository:
git clone <repository-url>
cd mcp-weather-server
- Install dependencies:
uv pip install -e ".[dev]"
- Copy the example environment file and add your API key:
cp .env.example .env
# Edit .env and add your OPENWEATHER_API_KEY
Configuration
Get an OpenWeatherMap API Key
- Sign up at OpenWeatherMap
- Navigate to your API keys section
- Generate a new API key (free tier includes 1,000 calls/day)
Configure in Kiro
Add the following to your .kiro/settings/mcp.json file:
{
"mcpServers": {
"weather": {
"command": "uvx",
"args": ["mcp-weather-server"],
"env": {
"OPENWEATHER_API_KEY": "your_api_key_here"
},
"disabled": false,
"autoApprove": ["get_current_weather", "get_weather_forecast"]
}
}
}
Replace your_api_key_here with your actual OpenWeatherMap API key.
Environment Variables
OPENWEATHER_API_KEY(required): Your OpenWeatherMap API keyLOG_LEVEL(optional): Logging level (DEBUG, INFO, WARNING, ERROR). Default: INFOAPI_TIMEOUT(optional): Timeout for API requests in seconds. Default: 10
Usage
Available Tools
get_current_weather
Get current weather conditions for a location.
Parameters:
location(string, required): City name (e.g., "Paris") or coordinates (e.g., "48.8566,2.3522")units(string, optional): "metric" (default) or "imperial"
Example:
Get the current weather in Tokyo
get_weather_forecast
Get weather forecast for upcoming days.
Parameters:
location(string, required): City name or coordinatesdays(integer, optional): Number of days (1-8). Default: 7units(string, optional): "metric" (default) or "imperial"
Example:
Show me the 5-day forecast for London
Using with Kiro
Once configured, simply ask Kiro natural language questions:
- "What's the weather like in Paris?"
- "Give me a 3-day forecast for New York"
- "What's the temperature in Tokyo right now?"
- "Show me the weather forecast for coordinates 51.5074,-0.1278"
Testing
For detailed testing instructions, see TESTING.md.
Quick Structure Validation
python3 test_structure.py
Integration Tests (requires valid API key)
OPENWEATHER_API_KEY=your_key python3 test_integration.py
Development
Running the Server Locally
python -m mcp_weather_server
Project Structure
mcp-weather-server/
├── src/
│ └── mcp_weather_server/
│ ├── __init__.py
│ ├── __main__.py # Entry point
│ ├── server.py # MCP server implementation
│ ├── weather_service.py # OpenWeatherMap API client
│ ├── config.py # Configuration management
│ ├── models.py # Data models
│ ├── tools/ # MCP tool handlers
│ │ ├── current_weather.py
│ │ └── forecast.py
│ └── utils/ # Utilities
│ ├── errors.py
│ └── formatters.py
├── tests/ # Test suite
├── pyproject.toml # Project configuration
├── README.md # This file
└── .env.example # Example environment configuration
API Rate Limits
The free tier of OpenWeatherMap includes:
- 1,000 API calls per day
- 60 calls per minute
The server handles rate limit errors gracefully and will inform you if limits are exceeded.
Troubleshooting
"API key is invalid"
- Verify your API key is correct in the configuration
- Ensure the API key is activated (can take a few hours after creation)
"Location not found"
- Check the spelling of the city name
- Try using coordinates instead: "latitude,longitude"
"Service temporarily unavailable"
- OpenWeatherMap API may be experiencing issues
- Check OpenWeatherMap status
License
MIT License - See LICENSE file for details
Contributing
Contributions are welcome! Please feel free to submit a Pull Request.
Support
For issues and questions:
- Check the OpenWeatherMap API documentation
- Review the MCP specification
- Open an issue in this repository
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。