Travel times between every pair.

An N-by-M travel-time matrix between sources and destinations. The basis for assignment, dispatch, and ETA quotes.

mcp.footstep.ai / get_matrix

Why you need it

Why your agent needs this.

When the agent needs to answer 'which driver is closest to the pickup?', it shouldn't run a route per driver. get_matrix takes lists of sources and destinations and returns the full travel-time grid in one call. The agent reasons over the table, picks the best candidate, explains the choice.

What it does for you

What your agent gets back.

N sources × M destinations of travel-time and distance in a single response.
Indexed so the agent can quote 'driver 3 is 14 minutes away' without parsing geometry.
Driving, walking, or cycling modes.
Composes with optimize_stops for dispatch and get_isochrone for reach.
Token-lean: no geometry returned by default.

Built for

For public-safety GIS For integrators

Try it

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.

Read the full reference

Prompt that triggers get_matrix

"Travel-time matrix between these 5 warehouses and 12 customer locations."

claude_desktop_config.json

{
  "mcpServers": {
    "footstep": {
      "url": "https://mcp.footstep.ai",
      "headers": {
        "x-api-key": "sk_live_your_key_here"
      }
    }
  }
}

Related capabilities.

optimize_stops

Travelling salesman in milliseconds. Returns the optimised order, the savings, and per-leg breakdowns.

get_isochrone

Reachability polygons by time or distance from any starting point. Walking, cycling, or driving.

get_directions

Point-to-point or multi-stop routes with terrain analytics. Answer 'is this walkable?' without a second call.

Ready to call it?

£5 free credit on signup. One auth header, every major runtime.

Get an API key See the REST endpoint