Geocode a thousand addresses at once.

Run up to 1,000 addresses through geocoding in a single call. Returns coordinates and confidence for each.

mcp.footstep.ai / batch_geocode

Why you need it

Why your agent needs this.

When the user hands the agent a CSV and asks 'add coordinates to this', the agent shouldn't loop a thousand calls. batch_geocode is one tool call: pass the list, get back the coordinates plus per-row confidence so the agent can flag dodgy rows for review.

What it does for you

What your agent gets back.

Up to 1,000 addresses per single tool call.
Per-row coordinates plus structured components.
Per-row confidence score so the agent can route low-confidence rows to a review path.
Failed rows return typed errors (timeout, rate_limited, invalid_input) the agent can explain.
Composes with parse_address upstream when the input is dirty free text.

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 batch_geocode

"Clean up this messy CSV of customer addresses before geocoding them."

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.

parse_address

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

reverse_geocode

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

Ready to call it?

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

Get an API key See the REST endpoint