@pipeworx/overpass

Connect: https://pipeworx.io/mcp — every tool in the catalog, including @pipeworx/overpass’s. Install: one-click buttons

No MCP client? Skip the connection: POST https://gateway.pipeworx.io/v1/tools/search_packs {"query":"..."} to find a tool below, GET /v1/tools/<name> for its schema, POST the same URL with arguments for the data — see For AI agents.

Tools: 3

OpenStreetMap Overpass API MCP — programmatic OSM queries, no auth.

Tools

• query(qql) — raw Overpass QL for advanced queries.
• pois_near(latitude, longitude, tag, radius_m?, limit?) — POIs in a radius.
• places_in_bbox(south, west, north, east, tag, limit?) — POIs in a bounding box.

Data source

Public Overpass instances, POST Overpass QL, JSON back. Tried in order, and a host that refuses or hangs is skipped for five minutes:

1. https://overpass.kumi.systems/api/interpreter — fast when up; dark since ~2026-09-19 (hangs past 30s).
2. https://maps.mail.ru/osm/tools/overpass/api/interpreter — full planet, current data, but 13-17s per call.
3. https://overpass-api.de/api/interpreter — the canonical instance; 406s our egress today (an IP block, fleet #2036), kept in case that changes.

The order, the measurements and the mirrors ruled out live in shared/src/overpass.ts (fleet #2451). When every host fails, the error names what each one did.

Tools

• query — Run a raw Overpass QL query against OpenStreetMap. Use for complex spatial queries the helper tools can’t express. Example: `[out:json][timeout:25]; area[“name”=“Berlin”][admin_level=4]->.a; node[“ame
• pois_near — Find OpenStreetMap points of interest (shops, amenities, businesses) near a location. Give a location either as latitude+longitude OR as a place name via “place” (e.g. place: “Göttingen, Germany” — au
• places_in_bbox — Find OSM POIs inside a bounding box. Use for “every park in this area” or “all restaurants in this neighborhood”. Bounding box is (south, west, north, east) in degrees.