get_forecast
Retrieve weather forecast data for any location using latitude and longitude coordinates to plan activities and prepare for weather conditions.
Instructions
Get weather forecast for a location.
Args:
latitude: Latitude of the location
longitude: Longitude of the location
Input Schema
TableJSON Schema
| Name | Required | Description | Default |
|---|---|---|---|
| latitude | Yes | ||
| longitude | Yes |
Implementation Reference
- weather.py:78-112 (handler)The handler function for the 'get_forecast' tool. It uses the National Weather Service API to retrieve and format the weather forecast for the next 5 periods based on latitude and longitude.@mcp.tool() async def get_forecast(latitude: float, longitude: float) -> str: """Get weather forecast for a location. Args: latitude: Latitude of the location longitude: Longitude of the location """ # First get the forecast grid endpoint points_url = f"{NWS_API_BASE}/points/{latitude},{longitude}" points_data = await make_nws_request(points_url) if not points_data: return "Unable to fetch forecast data for this location." # Get the forecast URL from the points response forecast_url = points_data["properties"]["forecast"] forecast_data = await make_nws_request(forecast_url) if not forecast_data: return "Unable to fetch detailed forecast." # Format the periods into a readable forecast periods = forecast_data["properties"]["periods"] forecasts = [] for period in periods[:5]: # Only show next 5 periods forecast = f""" {period["name"]}: Temperature: {period["temperature"]}°{period["temperatureUnit"]} Wind: {period["windSpeed"]} {period["windDirection"]} Forecast: {period["detailedForecast"]} """ forecasts.append(forecast) return "\n---\n".join(forecasts)
- weather.py:16-29 (helper)Helper function used by get_forecast to make async HTTP requests to the NWS API with error handling.async def make_nws_request(url: str) -> dict[str, Any] | None: """Make a request to the NWS API with proper error handling.""" headers = {"User-Agent": USER_AGENT, "Accept": "application/geo+json"} # Creates an HTTP client using httpx library (async alternative to requests) # async with ensures client closes properly async with httpx.AsyncClient() as client: try: response = await client.get(url, headers=headers, timeout=30.0) response.raise_for_status() # Raises error if status code is 4xx/5xx return response.json() # If anything fails, returns None instead of crashing except Exception: return None
- weather.py:78-78 (registration)The @mcp.tool() decorator registers the get_forecast function as an MCP tool.@mcp.tool()