What's at this location?
Given a coordinate, return the address or place label. Useful for labelling pins and incident reports.
mcp.footstep.ai / reverse_geocodeWhy your agent needs this.
When the user shares a location pin and asks 'where is that?', the agent needs the human-readable label, not the lat/lon it already has. reverse_geocode returns the closest address or place name with structured components the agent can speak back: '12 Bridge Street, Camden, London NW1'.
What your agent gets back.
- Closest address or place label for a coordinate, ready to read out loud.
- Structured components (street, locality, district, country) the agent can quote individually.
- Distance and bearing from the input point on each result.
- Filter by place_types when the agent needs 'the nearest street' vs 'the locality I'm in'.
- For 'what's near here' / 'find X near me' queries, use search_places instead.
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.
"What address is at 51.5014, -0.1419?"{
"mcpServers": {
"footstep": {
"url": "https://mcp.footstep.ai",
"headers": {
"x-api-key": "sk_live_your_key_here"
}
}
}
}Related capabilities.
geocodeTurn an address, landmark, or place name into coordinates. Returns ranked candidates with confidence scores.
search_placesPoints of interest near a location, by category or by venue name. Sorted by distance.
parse_addressFree-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.