Overture Maps MCP server
# Overture Maps MCP server
Query [Overture Maps](https://www.overturemapsapi.com) data — places (POIs), buildings and administrative divisions — directly from Claude and other MCP-compatible LLM tools.
This is a local (stdio) MCP server that wraps the [Overture Maps API](https://www.overturemapsapi.com). Responses are compact summaries rather than full GeoJSON, so they stay token-efficient, and the tools steer toward cheap, well-scoped queries.
## Tools
| Tool | What it does |
|------|--------------|
| `search_places` | Search POIs/businesses by country or lat/lng+radius, filtered by category, taxonomy, brand or contact details. |
| `list_place_categories` | List available place categories (with counts) for a country or area — use to find valid `categories` values. |
| `list_place_countries` | List every country in the dataset with place/brand counts. |
| `search_divisions` | Look up administrative divisions (countries, regions, counties, localities) by name or location. |
| `find_buildings` | Find building footprints near a point (id, distance, height/levels). |
## Get an API key
Sign up at [overturemapsapi.com](https://www.overturemapsapi.com) for a free API key. The public `DEMO-API-KEY` also works for light testing. Set it as `OVERTURE_API_KEY`.
> Note: the Free tier is for non-commercial use. Commercial use needs a paid plan.
## Use with Claude Desktop
Add this to your `claude_desktop_config.json` (Settings → Developer → Edit Config):
```json
{
"mcpServers": {
"overture-maps": {
"command": "npx",
"args": ["-y", "@thatapicompany/overture-maps-mcp"],
"env": {
"OVERTURE_API_KEY": "your-api-key-here"
}
}
}
}
```
Restart Claude Desktop. You can then ask things like:
- "Find cafes within 500m of the Eiffel Tower."
- "List every used car dealer in the UK that has a website."
- "What administrative region is Springfield in?"
- "How many places does Overture have for Bermuda?"
## Use with other MCP clients
Any client that supports local stdio MCP servers works the same way — run `npx -y @thatapicompany/overture-maps-mcp` with `OVERTURE_API_KEY` in the environment.
## Local development
```bash
npm install
npm run build
OVERTURE_API_KEY=your-key node dist/index.js
```
## Environment variables
| Variable | Default | Purpose |
|----------|---------|---------|
| `OVERTURE_API_KEY` | `DEMO-API-KEY` | Your Overture Maps API key. |
| `OVERTURE_API_BASE` | `https://api.overturemapsapi.com` | Override for staging/self-hosted deployments. |
## License
MIT
TDQS
Scored across 5 tools
Each tool targets a distinct data type: buildings, place categories, place countries, administrative divisions, and places (POIs). There is no overlap in purpose, and descriptions clearly differentiate them.
All tool names follow a consistent verb_noun pattern using lowercase and underscores: 'find_buildings', 'list_place_categories', 'list_place_countries', 'search_divisions', 'search_places'. The verbs ('find', 'list', 'search') are appropriate for query operations.
With 5 tools covering building footprints, places, administrative divisions, and metadata lookups, the count is well-scoped for a geographic data query server. It provides essential functionality without being excessive or too sparse.
The tool surface covers key query operations for Overture Maps data, including listing metadata and searching for buildings, places, and divisions. However, there is no tool to retrieve full geometry for buildings or places, which may be a gap for some use cases.