Walk, cycle, or drive. Which one fits?

Run multiple travel modes through the same A to B and get a side-by-side comparison plus a natural-language summary.

mcp.footstep.ai / compare_routes

Why you need it

Why your agent needs this.

When the user asks 'should I walk or cycle?', the agent shouldn't make three separate routing calls and stitch the answer together. compare_routes returns the comparison plus a one-sentence summary the agent can repeat back verbatim. The recommendation is one tool call away.

What it does for you

What your agent gets back.

Render envelope with one LineString layer per mode, each carrying its own colour hint.
Side-by-side distance, duration, ascent, and difficulty per mode.
Pre-written natural-language summary so the agent can quote it instead of synthesising.
2 to 4 modes per call: driving, walking, cycling.
Composes with find_and_route when the user gives place names rather than coordinates.

Built for

For AI developers 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 compare_routes

"Should I walk or cycle? Compare both options."

claude_desktop_config.json

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

Related capabilities.

get_directions

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

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_elevation

Heights in metres above sea level, with summary statistics for total ascent and descent.

Ready to call it?

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

Get an API key See the REST endpoint