Get future weather forecast for a location (global coverage). Use this for upcoming weather predictions (e.g., "tomorrow", "this week", "next 7 days", "hourly forecast"). Returns forecast data including temperature, precipitation, wind, conditions, and sunrise/sunset times. Supports both daily an...
AI agents call get_forecast to retrieve information from Weather Data MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
| Parameter | Type | Required | Description |
|---|---|---|---|
days | number | — | Number of days to include in forecast (1-16 for global, 1-7 for US NOAA, default: 7) |
source | string | — | Data source: "auto" (default, selects NOAA for US or Open-Meteo for international), "noaa" (US only), or "openmeteo" (global) |
latitude | number | — | Latitude of the location (-90 to 90). Not required if location_name is provided. |
longitude | number | — | Longitude of the location (-180 to 180). Not required if location_name is provided. |
granularity | string | — | Forecast granularity: "daily" for day/night periods or "hourly" for hour-by-hour detail (default: "daily") |
location_name | string | — | Name of a saved location (e.g., "home", "cabin"). Use this instead of latitude/longitude to reference a saved location. List saved locations with list_saved_loc |
include_normals | boolean | — | Include climate normals (30-year averages) for comparison with forecasted temperatures (default: false, daily forecasts only). Shows normal high/low and departu |
include_severe_weather | boolean | — | Include severe weather probabilities such as thunderstorm chance, wind gust probabilities, and tropical storm/hurricane risks (default: false, US/NOAA only) |
include_precipitation_probability | boolean | — | Include precipitation probability in the forecast output (default: true) |
Parameters from the server's own tool schema.
This tool purely queries and retrieves weather forecast data from external APIs (NOAA and Open-Meteo) without any side effects. It does not create, modify, delete, or execute arbitrary operations. The blast radius of misuse is minimal—an attacker could only retrieve weather information, which is public data. No financial, destructive, or system-altering consequences are possible.
From the tool's definition The tool 'get_future weather forecast for a location' retrieves 'forecast data including temperature, precipitation, wind, conditions, and sunrise/sunset times' with no capability to modify, delete, or execute operations.
Attacks that exploit this kind of access
Get future weather forecast for a location (global coverage). Use this for upcoming weather predictions (e.g., "tomorrow", "this week", "next 7 days", "hourly forecast"). Returns forecast data including temperature, precipitation, wind, conditions, and sunrise/sunset times. Supports both daily and hourly granularity. Automatically selects best data source: NOAA for US locations (more detailed), Open-Meteo for international locations. For current weather, use get_current_conditions. For past weather, use get_historical_weather. Can use either coordinates OR a saved location name (e.g., location_name="home"). If this tool returns an error, check the error message for status page links and consider using check_service_status to verify API availability. It is categorised as a Read tool in the Weather Data MCP Server MCP Server, which means it retrieves data without modifying state.
get_forecast accepts 9 parameters: days, source, latitude, longitude, granularity, location_name, include_normals, include_severe_weather, include_precipitation_probability. The full parameter table on this page comes from the server's own tool schema.
Register the Weather Data MCP Server MCP server in PolicyLayer and add a rule for get_forecast: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Weather Data MCP Server. Nothing to install.
get_forecast is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the get_forecast rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for get_forecast. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
get_forecast is provided by the Weather Data MCP Server MCP server (@dangahagan/weather-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →