The fastest order to visit your stops.

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

mcp.footstep.ai / optimize_stops

Why you need it

Why your agent needs this.

When the user gives the agent a list of stops and asks for the best order, the agent shouldn't write a heuristic. optimize_stops is one call: pass the stops, get back the optimised tour with savings against the input order. The agent reports the result; the maths happens server-side.

What it does for you

What your agent gets back.

Render envelope with an ordered LineString and Point layers carrying order_index per stop.
Savings against the input order, in plain numbers the agent can quote back.
Per-leg distance and duration for the agent to narrate.
Composes with find_and_route when the user names the stops rather than passing coordinates.
3 to roughly 30 stops per call.

Built for

For integrators For AI developers

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 optimize_stops

"Best order to visit these 8 delivery stops."

claude_desktop_config.json

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

Related capabilities.

get_matrix

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

find_and_route

Geocode 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.

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