Clean up a GPS trace.

Map-match a noisy GPS recording to the road network. Returns the corrected path plus per-segment road attributes.

mcp.footstep.ai / snap_trace

Why you need it

Why your agent needs this.

When the agent receives a GPS log and the user asks 'what roads did I take?' or 'how was the ride?', it shouldn't try to reconstruct geometry from raw coordinates. snap_trace returns the cleaned path with the road class, surface, and speed limits the agent can narrate directly.

What it does for you

What your agent gets back.

Render envelope with a clean LineString of the snapped trace.
Per-segment attributes the agent can read: 'gravel for 300m', 'speed limit 30'.
Confidence score per snap so the agent can flag low-confidence sections.
Composes with get_elevation to add ascent/descent commentary.
Useful for ride replay, post-hoc trip analysis, and trace validation.

Built for

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 snap_trace

"Clean up this GPS trace from my bike ride and show me the terrain."

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.

get_elevation

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

search_along_route

Coffee, 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.

Get an API key See the REST endpoint