天气数据服务

# Clone the repository
git clone https://github.com/Achrefjr1997/open-meteo-mcp.git
cd open-meteo-mcp

# Create virtual environment
python -m venv venv

# Activate virtual environment
# Windows:
venv\Scripts\activate
# Linux/Mac:
source venv/bin/activate

# Install dependencies
pip install -r requirements.txt

# Install the package
pip install -e .

pip install -e ".[dev]"

# Build the Docker image
docker build -t open-meteo-mcp .

# Run with Docker Compose (stdio transport)
docker compose up open-meteo-mcp

# Run with SSE transport (HTTP access on port 8000)
docker compose up open-meteo-sse

# Run test suite
docker compose --profile test up open-meteo-test

export OPEN_METEO_API_KEY=your_api_key
export OPEN_METEO_TIMEOUT=60.0
export OPEN_METEO_TIMEZONE=Africa/Tunis

$env:OPEN_METEO_API_KEY="your_api_key"
$env:OPEN_METEO_TIMEOUT="60.0"
$env:OPEN_METEO_TIMEZONE="Africa/Tunis"

OPEN_METEO_API_KEY=your_api_key
OPEN_METEO_TIMEOUT=60.0
OPEN_METEO_TIMEZONE=Africa/Tunis
# Custom API URLs (optional)
OPEN_METEO_API_URL=https://api.open-meteo.com
OPEN_METEO_AIR_QUALITY_API_URL=https://air-quality-api.open-meteo.com
OPEN_METEO_MARINE_API_URL=https://marine-api.open-meteo.com

# Run directly
python -m src.server

# Or use the installed command
open-meteo-mcp

# Run with SSE for remote access
python -m src.server --transport sse --port 8000

# With custom host
python -m src.server --transport sse --host 0.0.0.0 --port 8080

{
  "mcpServers": {
    "open-meteo": {
      "command": "python",
      "args": ["-m", "src.server"],
      "cwd": "/path/to/open-meteo-mcp",
      "description": "Weather data from Open-Meteo API"
    }
  }
}

{
  "mcpServers": {
    "open-meteo": {
      "command": "python",
      "args": ["-m", "src.server"],
      "cwd": "/path/to/open-meteo-mcp"
    }
  }
}

{
  "mcpServers": {
    "open-meteo": {
      "command": "docker",
      "args": ["run", "-i", "--rm", "-e", "OPEN_METEO_API_KEY=your_key", "open-meteo-mcp"],
      "description": "Weather data via Docker"
    }
  }
}

What's the current weather in London?

Show me the 7-day forecast for Tokyo with temperature and precipitation.

What was the weather like in Paris during January 2024?

Compare the ECMWF and GFS models for New York this week.

What's the air quality index in Beijing right now? Is it safe for outdoor exercise?

Find coordinates for Barcelona, Spain and get the marine forecast for sailing.

What's the elevation of Denver, Colorado?

List all available weather variables for solar energy applications.

I have allergies - what's the pollen forecast for Berlin this week?

Plan my outdoor wedding in Amsterdam on Saturday - give me hour-by-hour weather from 2 PM to 10 PM.

# Install test dependencies
pip install pytest pytest-asyncio

# Run all tests
pytest tests/ -v

# Run with coverage
pytest tests/ --cov=src --cov-report=html

# Run specific test file
pytest tests/test_client.py -v

# Run tests in Docker
docker compose --profile test up open-meteo-test

============================= test session starts =============================
collected 118 items

tests/test_client.py ...................ss...ss........                 [ 28%]
tests/test_prompts/test_prompts.py .............                         [ 39%]
tests/test_resources/test_resources.py ...................               [ 55%]
tests/test_server.py .......................                             [ 75%]
tests/test_tools/test_tools.py ............ssss...ssss......             [100%]

====================== 106 passed, 12 skipped in 39.50s ======================

# Format code
black src/ tests/

# Lint code
ruff check src/ tests/

# Type checking
mypy src/

# All quality checks
black --check src/ tests/ && ruff check src/ tests/ && mypy src/

open-meteo-mcp/
├── src/
│   ├── __init__.py              # Package metadata
│   ├── server.py                # Main MCP server entry point
│   ├── client.py                # Open-Meteo API client (async)
│   ├── tools/
│   │   ├── __init__.py
│   │   ├── forecast.py          # 5 forecast tools
│   │   ├── historical.py        # 5 historical tools
│   │   ├── air_quality.py       # 5 air quality tools
│   │   ├── geocoding.py         # 5 geocoding tools
│   │   ├── ensemble.py          # 7 ensemble/model tools
│   │   ├── marine.py            # 3 marine tools
│   │   └── specialized.py       # 3 utility tools
│   ├── resources/
│   │   ├── __init__.py
│   │   ├── variables.py         # 13 variable resources
│   │   └── models.py            # 12 model resources
│   └── prompts/
│       ├── __init__.py
│       └── weather_assistant.py # 4 prompts
├── tests/
│   ├── __init__.py
│   ├── conftest.py              # Pytest fixtures
│   ├── test_client.py           # API client tests (38 tests)
│   ├── test_server.py           # Server tests (23 tests)
│   ├── test_tools/
│   │   ├── __init__.py
│   │   └── test_tools.py        # Tool tests (28 tests)
│   ├── test_resources/
│   │   ├── __init__.py
│   │   └── test_resources.py    # Resource tests (19 tests)
│   └── test_prompts/
│       ├── __init__.py
│       └── test_prompts.py      # Prompt tests (13 tests)
├── .github/
│   └── workflows/
│       └── ci.yml               # GitHub Actions CI
├── docker-compose.yml           # Docker orchestration
├── Dockerfile                   # Multi-stage build
├── DOCKER.md                    # Docker documentation
├── pyproject.toml               # Project configuration
├── requirements.txt             # Python dependencies
├── README.md                    # This file
├── QUICKSTART.md                # 5-minute setup guide
└── TEST_PROMPTS.md              # Comprehensive test prompts

# Clone your fork
git clone https://github.com/Achrefjr1997/open-meteo-mcp.git
cd open-meteo-mcp

# Create virtual environment
python -m venv venv
source venv/bin/activate  # or venv\Scripts\activate on Windows

# Install with dev dependencies
pip install -e ".[dev]"

# Run tests to verify setup
pytest tests/ -v

Weather data provided by Open-Meteo.com