Mapbox Location Grounding

This teaches Claude to stop hallucinating location data by grounding answers in live Mapbox APIs. Instead of guessing at restaurant names or travel times from training data, it composes reverse geocoding, POI search, place details, and isochrones into cited responses with ratings, prices, and reachability polygons. The single ground_location_tool call handles most cases, but you can manually chain tools if needed. Especially useful for "what's near me" questions, travel time comparisons, and anything where stale POI data or made-up business hours would wreck the user experience. It pushes hard on always retrieving live data rather than answering from memory, which is the right default for location queries.

skills.sh installs: 1.3K
GitHub stars: 86
last updated: Aug 21, 2026

View on GitHub

Install

$ npx -y skills add mapbox/mapbox-agent-skills --skill mapbox-location-grounding --agent claude-code

Installs into .claude/skills of the current project.

Files

Mapbox Location Grounding Skill

Teaches AI assistants how to ground location-aware responses in live Mapbox data by composing MCP tools into a structured, cited answer. Use this instead of relying on training data for place names, POIs, ratings, or travel times — which are stale and prone to hallucination.

When to Use Grounding

Ground responses when the user asks about:

"What's near [location]?" or "What's around [coordinate]?"
"Describe this neighborhood / area"
"Find [category] within walking/driving distance"
"What can I do near [address]?"
"How long does it take to get from A to B?"
"What's within a 10-minute walk of here?"
"How far is it between these locations?"
Real estate, travel, mobility, or local discovery use cases
Any question where place accuracy, recency, or travel time matters

Never answer location questions from training data alone. Always retrieve live data.

Grounding Tool Composition

Preferred: single tool call

If ground_location_tool is available, use it — it handles reverse geocoding, POI search, place details enrichment, isochrone, and a static map image in one call:

SKILL.md on GitHub