Access Foursquare Places Data
Gives AI agents access to Foursquare's Places API - 100M+ locations, GeoTagging Place Snap, and rich place metadata like photos and popularity.
Maintainer of this project? Claim this page to edit the listing.
1.0.0Add to Favorites
Why it matters
Leverage the Foursquare Places API to enrich AI applications with detailed location context. Access a vast database of places and transform GPS data into actionable insights for context-aware agents.
Outcomes
What it gets done
Connect to the Foursquare Places API.
Utilize GeoTagging and Search APIs for location data.
Extract rich metadata including photos, reviews, and ratings.
Transform GPS data into meaningful location insights.
Install
Add it to your toolbox
Run in your project directory:
curl -fsSL https://spark.entire.vc/get/vb-foursquare | bash Capabilities
Tools your agent gets
Search for places using the Foursquare Places API with filtering by categories, amenities, and other criteria.
Retrieve detailed metadata for a specific place including photos, reviews, ratings, and real-time popularity.
Identify and tag locations from GPS data using Foursquare's Place Snap technology for accurate location identification.
Overview
Foursquare MCP Server
This MCP server exposes Foursquare's Places API - 100M+ locations across 1,500+ categories - with GeoTagging for GPS-to-place resolution and Search/Data APIs returning rich place metadata. Use it to give an AI agent location-aware context about a user's surroundings. It's currently local-only via Claude Desktop, with no hosted production server option yet.
What it does
This MCP server exposes the Foursquare Places API to AI agents, giving them access to a global, open-source database of 100 million places across more than 1,500 categories. It converts raw GPS coordinates into meaningful location context via GeoTagging (using Foursquare's Place Snap technology to pinpoint exact locations like coffee shops or parks with high accuracy), and its Search & Data APIs let an agent filter places by category, features, hours, and more, with each result carrying rich metadata such as photos, reviews, ratings, and real-time popularity.
When to use - and when NOT to
Use this when building an AI agent that needs situational, location-aware context - understanding where a user is and what's nearby, searching for places matching specific criteria, or converting GPS data into a recognizable named location. It requires a Foursquare Service API Key (free basic developer account with starter credit) obtained from the Foursquare developer portal. As of this writing, MCP support here is local-only via Claude Desktop - there's no remote/production-hosted server option yet, so this is intended for local development and testing rather than a hosted production integration.
How to install
- Create a free Foursquare developer account and generate a Service API Key (Foursquare Docs > Manage Your Service API Keys) - copy it immediately, as it can't be viewed again later.
- Download Claude Desktop (local MCP support only at this stage).
- Set up the Python-based MCP server using
uv, following the instructions in the project'sfsq-server-python/README.md.
Who it's for
Developers building location-aware AI agents that need to understand a user's surroundings - nearby places, categories, hours, ratings - using Foursquare's global places database.
Source README
MCP Server enabling access to the Foursquare API
The Foursquare Places API provides detailed location context for apps that need to understand
where a user is and what's around them. Powered by a global, open source database of 100
million places across more than 1500 categories, they convert raw GPS data into meaningful insights.
The GeoTagging API pinpoints exact locations-from coffee shops to parks-with high accuracy
using Foursquare's Place Snap technology, while the Search & Data APIs go beyond basic proximity,
allowing developers to filter places by category, features, hours, and more. Each result includes
rich metadata like photos, reviews, ratings, and real-time popularity.
These tools make it possible to build AI Agents that are situationally aware and tailored to
the user's surroundings for a highly personalized experience.
What is MCP?
Model Context Protocol is a new standard from Anthropic for connecting AI systems with data sources.
Read more about it at Anthropic.
MCP allows you to set up servers that expose functions that an LLM can understand and call directly.
In this project, we implement an MCP server that can access the Foursquare API in order to support
local search for places.
Getting Started
Foursquare Service API Key
You will need a Foursquare Service API Key to allow your AI agent to access Foursquare API endpoints.
If you do not already have one, follow the instructions on
Foursquare Doc - Manage Your Service API Keys
to create one.
You will need to log in to your Foursquare developer account or create one if you do not have one
(creating a basic account is free and includes starter credit for your project). Be sure to copy the
Service API key upon creation as you will not be able to see it again.
Download Claude Desktop
Currently MCP is only supported for local use, so you should download the
Claude Desktop App (remote production MCP servers are still in the works).
Set up MCP Server
- Python: follow the directions in fsq-server-python/README.md for instructions on setting up a python based MCP server using uv.
FAQ
Common questions
Discussion
Questions & comments · 0
Sign In Sign in to leave a comment.