← MCP serverMCP tool

Find stops along the way.

Coffee, charging, fuel, food. Ranked by how little detour they add to the existing route.

Get an API keySee the REST endpoint
mcp.footstep.ai / search_along_route
Why you need it

Why your agent needs this.

When the driver's already moving and the user asks 'find me a coffee shop', the closest one as the crow flies is the wrong answer. search_along_route ranks candidates by detour cost so the agent recommends the right pit stop: two minutes off route, not five blocks back.

What it does for you

What your agent gets back.

  • Render envelope with the route LineString plus Point layers for each candidate.
  • Ranked by added detour time so the agent picks the right one without reading every result.
  • Pass a category (cafe, fuel, charging) or a specific brand name.
  • Tunable detour budget so the agent can ask 'find me something under 5 minutes off route'.
  • Composes with get_directions when the user is already on a journey.
Built for
For AI developersFor 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 search_along_route
"Are there any petrol stations on my way to Cambridge?"
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.

search_places

Points of interest near a location, by category or by venue name. Sorted by distance.

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.

Ready to call it?

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

Get an API keySee the REST endpoint