Weather MCP Server
Provides current weather conditions and 5-day forecasts for any location using the OpenWeatherMap API. Supports flexible location queries including city names, coordinates, and zip codes.
README
Weather MCP Server
A Model Context Protocol (MCP) server that provides weather information using the OpenWeatherMap API. This server primarily runs in stdio mode (the standard for MCP servers) with an experimental HTTP API mode for testing.
Features
- MCP Protocol Support: Full stdio mode support for MCP clients
- HTTP API Mode: Experimental simple HTTP API for testing
- Current Weather: Get current weather conditions for any location
- Weather Forecast: Get weather forecasts up to 5 days ahead
- Location Flexibility: Support for city names, coordinates (lat,lon), and zip codes
- Docker Support: Containerized deployment with docker-compose
- Configurable: YAML-based configuration with environment variable support
- Well Tested: Comprehensive test suite with pytest
Prerequisites
- Python 3.11 or higher
- OpenWeatherMap API key (free tier available at OpenWeatherMap)
- Docker (optional, for containerized deployment)
Installation
Using pip
# Clone the repository
git clone https://github.com/dangogh/weather-mcp.git
cd weather-mcp
# Install dependencies
pip install -r requirements.txt
# Install the package
pip install -e .
Using Docker
# Build the Docker image
docker build -t weather-mcp .
# Or use docker-compose (see Docker section below)
Configuration
The server uses a YAML configuration file (config.yaml) with the following structure:
server:
mode: stdio # or 'http'
http:
host: 0.0.0.0
port: 8080
weather_api:
provider: openweathermap
base_url: https://api.openweathermap.org/data/2.5
api_key: ${WEATHER_API_KEY} # Set via environment variable
units: metric # or 'imperial' or 'standard'
timeout: 10
logging:
level: INFO
format: "%(asctime)s - %(name)s - %(levelname)s - %(message)s"
Environment Variables
WEATHER_API_KEY: Your OpenWeatherMap API key (required)SERVER_MODE: Override server mode (optional, defaults to config file)
Usage
Running in stdio mode
# Set your API key
export WEATHER_API_KEY="your_api_key_here"
# Run the server
python -m weather_mcp
# Or use the CLI command
weather-mcp
Running in HTTP mode (Experimental)
Note: HTTP mode provides a simple REST API for testing. For production MCP usage, use stdio mode.
# Update config.yaml to set mode: http, or use environment variable
export WEATHER_API_KEY="your_api_key_here"
export SERVER_MODE=http
python -m weather_mcp
The HTTP server will start on http://localhost:8080 with the following endpoints:
GET /: Server informationGET /health: Health checkPOST /weather/current: Get current weather (JSON:{"location": "London"})POST /weather/forecast: Get forecast (JSON:{"location": "London", "days": 3})
Using with Docker
Stdio mode:
# Set your API key in .env file
echo "WEATHER_API_KEY=your_api_key_here" > .env
# Run with docker-compose
docker-compose --profile stdio run weather-mcp-stdio
HTTP mode:
# Run HTTP server
docker-compose --profile http up weather-mcp-http
# The server will be available at http://localhost:8080
Available Tools
get_current_weather
Get current weather conditions for a location.
Parameters:
location(string, required): City name, coordinates (lat,lon), or zip code
Example:
{
"location": "London"
}
Response includes:
- Temperature and "feels like" temperature
- Weather description
- Humidity percentage
- Atmospheric pressure
- Wind speed
get_weather_forecast
Get weather forecast for a location up to 5 days ahead.
Parameters:
location(string, required): City name, coordinates (lat,lon), or zip codedays(integer, optional): Number of days to forecast (1-5, default: 3)
Example:
{
"location": "New York",
"days": 3
}
Response includes:
- Forecast data in 3-hour intervals
- Same weather details as current weather for each interval
Development
Running Tests
# Install dev dependencies
pip install -r requirements-dev.txt
# Run tests
pytest
# Run with coverage
pytest --cov=src/weather_mcp --cov-report=html
Code Structure
weather-mcp/
├── src/
│ └── weather_mcp/
│ ├── __init__.py
│ ├── __main__.py # Entry point
│ ├── config.py # Configuration management
│ ├── server.py # MCP server implementation
│ ├── weather_client.py # Weather API client
│ └── http_server.py # HTTP streaming server
├── tests/
│ ├── __init__.py
│ ├── test_config.py
│ ├── test_weather_client.py
│ └── test_server.py
├── config.yaml # Configuration file
├── Dockerfile # Docker image definition
├── docker-compose.yml # Docker compose configuration
├── requirements.txt # Production dependencies
├── requirements-dev.txt # Development dependencies
├── setup.py # Package setup
└── README.md # This file
API Reference
OpenWeatherMap API
This server uses the OpenWeatherMap API. Key features:
- Free Tier: 60 calls/minute, 1,000,000 calls/month
- Current Weather: Real-time weather data
- 5-Day Forecast: Weather predictions in 3-hour intervals
- Location Support: City names, coordinates, zip codes
Get your free API key at: https://openweathermap.org/api
License
This project is licensed under the MIT License - see the LICENSE file for details.
Contributing
Contributions are welcome! Please feel free to submit a Pull Request.
Troubleshooting
API Key Issues
If you see "API key not configured" errors:
- Ensure
WEATHER_API_KEYenvironment variable is set - Check that the key is valid and active on OpenWeatherMap
- Verify the key is not expired (free tier keys don't expire but can be revoked)
Connection Issues
If you encounter connection errors:
- Check your internet connection
- Verify OpenWeatherMap API is accessible from your location
- Check if you've exceeded rate limits (60 calls/minute for free tier)
Docker Issues
If Docker containers fail to start:
- Ensure Docker and docker-compose are installed
- Check that port 8080 is not already in use (for HTTP mode)
- Verify the API key is properly set in the environment
Support
For issues and questions:
- Open an issue on GitHub: https://github.com/dangogh/weather-mcp/issues
- Check existing issues for solutions
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。