Driving, walking, and cycling directions.
Point-to-point or multi-stop routes with terrain analytics. Answer 'is this walkable?' without a second call.
mcp.footstep.ai / get_directionsWhy your agent needs this.
When the user asks the agent 'how do I walk to Tower Bridge', it needs more than a line on a map. get_directions returns the route with turn-by-turn legs, terrain rollups, and explicit-units fields so the agent can answer 'is this walkable?' or 'is it hilly?' without a follow-up call.
What your agent gets back.
- Render envelope with a LineString layer for the route, ready for direct drawing.
- Turn-by-turn steps in natural language the agent can read back to the user.
- Terrain block with a flat/rolling/hilly/mountainous classification.
- Explicit units in field names (distance_meters, duration_seconds) so the model never guesses.
- Composes with find_and_route for name-based requests and search_along_route for corridor stops.
Plug it into your agent.
Add Footstep to your MCP-aware runtime. Your model picks the tool at runtime; you wrote none of the orchestration.
"Walking directions from Kings Cross to Tower Bridge. Is the route hilly?"{
"mcpServers": {
"footstep": {
"url": "https://mcp.footstep.ai",
"headers": {
"x-api-key": "sk_live_your_key_here"
}
}
}
}Related capabilities.
find_and_routeGeocode both ends and compute the route in one call. The agent says 'how do I get from Kings Cross to Tower Bridge'. The tool handles the rest.
compare_routesRun multiple travel modes through the same A to B and get a side-by-side comparison plus a natural-language summary.
search_along_routeCoffee, charging, fuel, food. Ranked by how little detour they add to the existing route.
Ready to call it?
£5 free credit on signup. One auth header, every major runtime.