Where is this place?

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

mcp.footstep.ai / geocode

Why you need it

Why your agent needs this.

When the user says 'where is Buckingham Palace' or 'find Costa near here', the agent needs to turn a string into a coordinate it can plot or feed to another tool. geocode is the canonical primitive: take text, return the location. Top match by default in the render envelope; alternatives stay in results for disambiguation when the agent needs to ask the user.

What it does for you

What your agent gets back.

Render envelope contains the top match as a Point, ready to plot.
Alternative candidates with confidence scores stay in results for disambiguation.
Place type on each match (venue, address, street, locality) so the agent can reason.
Multilingual place name handling.
Composes with parse_address upstream for messy input, and find_and_route for direction asks.

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 geocode

"Where is Buckingham Palace?"

claude_desktop_config.json

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

Related capabilities.

reverse_geocode

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

search_places

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

parse_address

Free-text in, structured out. Fixes typos, expands abbreviations, infers missing fields, and scores confidence.

Ready to call it?

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

Get an API key See the REST endpoint