ThinAir Geo is the geospatial intelligence layer behind ThinAir fleet workflows: geocoding, routing context, address search, service-area visibility, map intelligence, traffic, weather, and…
thinair-geo is an MCP project maintained in the thinairtelematics/thinair-geo repository. The maintainer describes its purpose as “ThinAir Geo is the geospatial intelligence layer behind ThinAir fleet workflows: geocoding, routing context, address search, service-area visibility, map intelligence, traffic, weather, and reachability”. Read the project documentation for the complete scope.
The maintainer’s configuration uses https://geo.thinair.co/mcp. Check the project’s account and authentication instructions when adding the endpoint to your client.
Project documentation · Repository · Discovery listing. This profile records the public documentation checked on 2026-10-08.
Check the linked publisher documentation and your connected client's tool list. Names and availability can vary with the server version and account permissions.
| Tool | What it does |
|---|---|
| geocode | Convert addresses, place names, or intersections to coordinates |
| reverse_geocode | Convert coordinates to addresses |
| batch_geocode | Geocode up to 50 addresses in one call (returns geojson FeatureCollection) |
| directions | Turn-by-turn routing — auto, truck, bicycle, pedestrian, motorcycle |
| isochrone | Travel-time / -distance reachability polygons (multi-band) |
| traffic | Real-time traffic conditions |
| weather | Current conditions and forecasts |
| search_places | Find nearby POIs by category (gas, charging, food, lodging, …) |
| explore | Browse cities, neighborhoods, and venues by region |
| geocode_structured | Geocode from discrete address components (form / CRM fields) instead of free text |
| resolve_intersection | Resolve a named cross-street (street1 × street2) to a coordinate with a confidence score |
| distance_matrix | Road distances + travel times for every origin → destination pair (≤ 625 pairs) |
| locate | Snap a coordinate to the road network — road name, class, speed limit, legality, timezone, point elevation |
| map_match | Snap a raw GPS trace (2–100 points) to the road-accurate route actually driven |
| trace_attributes | Per-segment road attributes (names, classes, speed limits, surfaces) along a matched trace |
| geofence_contains | Point-in-polygon test against a GeoJSON polygon (one boolean per point) |
| place_get | Look up a place by its stable ThinAir id (ta_place_… / ta_intersection_…) |
| quota | Inspect your current plan, daily usage, and remaining capacity (free, never debits) |
| issue_api_key | Mint a fresh API key for the current tenant (counts as 1 query) |
{
"mcpServers": {
"thinair-geo": {
"url": "https://geo.thinair.co/mcp"
}
}
}From the project documentation. Replace placeholders and example paths before connecting.
Put 6,000+ pre-built scrapers at your assistant's fingertips through one MCP endpoint.
MCP server for the Geomelon geographic API. Exposes cities, countries, regions, and languages as tools any MCP-compatible AI client can call.
An MCP server for accessibility testing using Axe-core
Connect AI assistants to Acumatica ERP — 28 tools for queries, mutations, GIs, attachments.
Address validation & geocoding for AI agents: 240+ countries, UK PAF, free US/CA enrichment
ADIF 3.1.7 spec engine for amateur radio logs: validation, parsing, enumerations, geospatial.