MCP server exposing 3 tools for foursquare.
This URL is a JSON-RPC 2.0 endpoint over HTTP. Issue POST requests with a JSON-RPC body. Browsers and search crawlers land here on GET.
POST https://gateway.pipeworx.io/foursquare/mcp
Content-Type: application/json
{"jsonrpc":"2.0","id":1,"method":"tools/list"}
search_places — Search Foursquare places (keyless — Pipeworx supplies the key). Combine `query` (e.g., "coffee", "hardware store") with a location anchor — either `near` ("Brooklyn, NY", "San Francisco, CA") or `latitude`+`longitude`. sort:"RATING" orders results by Foursquare rating (best first); the rating NUMBER itself is a Foursquare Premium field and is returned only where enabled — check `rating_included` / `rating_reason` in the response, and read `rating_note` before telling a caller a place is unrated. Returns name, fsq_place_id, categories, address, distance, lat/lon, tel, website.get_place — Full place details by fsq_place_id. Returns name, categories, address, lat/lon, social media, website, tel. hours/rating/price/popularity are Foursquare Premium fields — present only where enabled (see `rating_included` / `rating_note` in the response).nearby_places — Return POIs sorted by distance from a lat/lon without a text query. Requires latitude+longitude; optional radius_m (default 500m) and numeric fsq_category_ids filter. Returns name, categories, address, distance, tel, website. rating/hours/popularity are Foursquare Premium fields — present only where enabled (see `rating_included` / `rating_note`).Code samples (curl / TypeScript / one-click client install), schemas, and the live playground are on the pack page:
https://pipeworx.io/packs/foursquare/
Pipeworx is an open MCP gateway connecting AI agents to live data. pipeworx.io