Outdoor Intelligence
Worldwide outdoor intelligence, for your apps and AI agents
Give your product and team deep knowledge of terrain, weather, trails, and routes across every continent. Connect through an MCP server, Agent Skills, or GraphQL, and get a precise answer ready to ship.
Works with the tools you already use
Challenges we solve
Built for your team
The unified outdoor data catalog
Billions of geospatial data points, historical, live, and forecast weather observations, elevation models, and search & geocoding. All queryable from a single platform.
One API, exact data
Fetch exactly the fields your app needs: routes, weather, elevation, POIs. Strictly typed schema with built-in introspection.
AI-ready schema
Structured, self-documenting types that AI agents and copilots can discover and query without handholding. Feed outdoor context straight into your LLM pipelines.
Activity-aware outdoor intelligence
Billions of data points, one question away
Activity-aware itineraries and itinerary suggestions, terrain analysis, weather, trails, POIs, etc. Worldwide coverage, refreshed every month. Ask your AI agent through MCP or Agent Skills, or query via GraphQL.
- Routing, directions, and route suggestions
- Weather: historical, live, and forecast
- Elevation, terrain, search, and POIs
Agents & API
The questions your product asks every day
Connect through an MCP server, Agent Skills, or GraphQL, and ask in plain language. Outdoor Intelligence answers.
Suggest three trail-running loops from Chamonix, around 14 km with 600 m of climbing.
3 loops · closest 13.8 km / +615 m
Three loops from Chamonix, each close to 14 km and +600 m. The tightest lands at 13.8 km with 615 m of climbing; the other two trade a little distance for a cleaner ascent. Every candidate returns with full GeoJSON geometry, an elevation profile, and its surface breakdown, ready to preview or export as GPX.
Trace the fastest trail line from Chamonix to Argentière and tell me what's underfoot.
10.8 km · ~2h51 · asphalt → ground → gravel
A 10.8 km trail line up the valley to Argentière, about 2h51 on foot. It leaves town on asphalt, then runs on natural ground and gravel singletrack. Full GeoJSON geometry and the surface breakdown come back with it.
Break down the surface and gradient of this drawn segment before I send runners on it.
+1364 m · 27.1° max · asphalt → ground → gravel
The segment climbs 1,364 m to a high point of 1,545 m with a 27.1° max gradient, so it is a serious pitch. Surface moves from asphalt to natural ground to gravel; way type runs street, footway, path, then track. Per-point elevations come back for the profile.
Autocomplete every 'Col du' around Chamonix, with coordinates for each.
5 places · Brévent, Belvédère, Mont Lachat, Passon, Chardonnet
Five passes near Chamonix: Col du Brévent [6.844, 45.941], Col du Belvédère [6.876, 45.990], Col du Mont Lachat [6.796, 45.868], Col du Passon [6.983, 45.976], and Col du Chardonnet [7.012, 45.966] over the Swiss border. Each with its OSM reference and admin context.
Find the Refuge du Goûter and confirm which one is the current hut.
3 matches · Goûter Refuge (alpine_hut)
Three matches on the Goûter ridge above Les Houches: the current Goûter Refuge, tagged alpine_hut, at [6.831, 45.851], plus the historic Refuge d'Hiver and the Ancien Refuge du Goûter. Returned with OSM reference, layer, and full admin path.
How much ground can a runner cover on foot from the Chamonix aid station in 30, 60, and 120 minutes?
3 polygons · 9.1 / 22.4 / 60.1 km² · reach 0.72 → 0.30
Reachable ground from the aid station: 9.1 km² within 30 minutes, 22.4 km² within an hour, and 60.1 km² within two. The reach factor falls from 0.72 to 0.30 as the valley walls steepen. Each ring returns as a GeoJSON polygon you can overlay on the course.
Give me the on-foot travel-time grid between our four aid stations for the ops plan.
4×4 grid · Chamonix → Argentière 10.8 km / 2h51
Full grid returned. Chamonix to Argentière is 10.8 km, about 2h51 on foot; the Courmayeur post sits 65 km and roughly 16h out over the massif, so it needs a vehicle transfer, not a runner relay. Durations in seconds, distances in meters, unreachable pairs flagged.
Why outdoor teams switch to Mountaya
- Stitching weather, terrain, and elevation from five vendors
- Road-network routing that sends trail users onto highways
- Building and hosting your own tile pipeline
- Hand-written glue code for every AI agent
- One typed GraphQL API for routing, weather, terrain, and elevation
- Activity-aware routing across nine outdoor activities
- Drop-in vector and raster tiles for Mapbox GL and MapLibre, 99.9% SLA
- A remote MCP server and Agent Skills your agents use out of the box
Use case
How Campus Coach empowers 600,000 runners with unified terrain and weather maps from Mountaya, for greater training impact.
The depth of Mountaya's mapping ecosystem transforms the experience on our mobile apps. By integrating their contextual data, we give our users the terrain insight they need to anticipate and prepare their races in the best possible conditions.
Jonathan Levy
Frequently asked questions
Outdoor Intelligence is Mountaya's geospatial data engine for the outdoors: the same routing, weather, terrain, and elevation primitives that power Map Studio, exposed to your apps and AI agents.
Three ways: a remote-hosted MCP server at mcp.mountaya.com for Claude, Cursor, and any MCP client, open-source Agent Skills for 30+ AI coding agents, and a typed GraphQL API for your own apps. All three read from the same engine.
Activity-aware directions across nine outdoor activities, route suggestions from a brief, per-meter elevation and surface analysis, isochrones, time-distance matrices, geocoding, outdoor POIs, and historical, live, and forecast weather.
Purely per request, with graduated tiers and no base fee. The first 20,000 requests each month are billed at 0.005€ each, the next 30,000 at 0.0025€, and the rate keeps dropping at every tier above that.
Yes. Production tiers carry a 99.9% uptime SLA. The schema is strictly typed and introspectable, so agents and apps discover it without reading docs.