Agent skill · software engineering · sundial-org

grounding-lite

Google Maps Grounding Lite MCP for location search, weather, and routes via mcporter.

Why this skill is useful

Adds specific commands and configurations for using Google Maps Grounding Lite with mcporter that the AI wouldn't reliably generate on its own.

What it needs

Requires mcporter installed locally. Requires google-cloud account access. About 1k tokens when loaded. Last updated 2026-03-07. 639 stars on the source repository.

What this skill does

Grounding Lite Google Maps Grounding Lite MCP provides AI-grounded location data. Experimental (pre-GA), free during preview. Setup 1. Enable the API: gcloud beta services enable mapstools.googleapis.com 2. Get an API key from Cloud Console 3. Set env: export GOOGLEMAPSAPIKEY="YOURKEY" 4. Configure mcporter: Tools searchplaces: Find places, businesses, addresses. Returns AI summaries with Google Maps links. lookupweather: Current conditions and forecasts (hourly 48h, daily 7 days). computeroutes: Travel distance and duration (no turn-by-turn directions). Commands Parameters searchplaces: textQuery (required), locationBias, languageCode, regionCode lookupweather: location (required: address/latLng/placeId), unitsSystem, date, hour computeroutes: origin, destination (required), travelMode (DRIVE/WALK) Notes Rate limits: searchplaces 100 QPM (1k/day), lookupweather 300 QPM, computeroutes 300 QPM Include Google Maps links in user-facing output (attribution required) Only use with models that don't train on input data

How to use it

Reference it in AdaL, Claude Code, Cursor or any coding agent — nothing to install:

@skills sundial-org/grounding-lite

View the source on GitHub

Browse the @skills marketplace