What's near here?

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

mcp.footstep.ai / search_places

Why you need it

Why your agent needs this.

'Find me a cafe near Kings Cross' is two operations under the hood: geocode 'Kings Cross', then find cafes. The agent shouldn't have to chain them. search_places takes 'near' as a place name (geocoded internally) and a category or venue name, and returns the ranked list in one tool call.

This tool bundles Geocoding + Place search in a single call.

What it does for you

What your agent gets back.

Pass 'near' as a place name. The geocoding happens inside the tool.
Categories expand internally to multilingual synonyms ('cafe' also catches 'coffee', 'café').
Specific brand names work too: Costa, Tesco, Tower Bridge.
Shared admin fields hoisted into a places_context block so the agent doesn't burn tokens on repeated 'United Kingdom'.
Composes with search_along_route when the user is already moving.

Built for

For AI developers For SAR teams 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 search_places

"Find coffee shops near my hotel."

claude_desktop_config.json

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

Related capabilities.

geocode

Turn an address, landmark, or place name into coordinates. Returns ranked candidates with confidence scores.

reverse_geocode

Given a coordinate, return the address or place label. Useful for labelling pins and incident reports.

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