Skip to main content

MCP Foursquare API server

Project description

Python Server for Foursquare API

Getting Started

Prerequisites

Follow getting started steps in the project guide.

Python Environment

Ensure that you're running Python 3.10 or higher.

Next install uv, a fast python project manager:

curl -LsSf https://astral.sh/uv/install.sh | sh

or alternatively if you are on a mac you can install with homebrew

brew install uv

(if you already have it installed, make sure it is up to date)

Clone the Repo

This project currently must be cloned locally and run with uv. Clone using:

git clone git@github.com:foursquare/fsq-ai-mcp.git

Then set up the project:

cd fsq-ai-mcp/fsq-server-python
uv venv
uv sync

Configure MCP

You will need to update the ~/Library/Application\ Support/Claude/claude_desktop_config.json configuration. If the file doesn't exit, you can copy paste claude_desktop_config.json from this folder into Claude.

Based on the example claude_desktop_config.json, update the values with correct local paths and your Service API key and add to claude_desktop_config.json.

  • "command": "/path/to/uv/bin/uv",
  • "args": [...,"/path/to/git/clone/fsq-ai-mcp/fsq-server-python/", ...],
  • "FOURSQUARE_SERVICE_TOKEN": "YOUR FOURSQUARE SERVICE TOKEN"

If the file already exists because you have other local MCP servers, just insert the foursquare sub-object into the existing config.

Run MCP

Open Claude Desktop. You should see a hammer icon appear in the lower right part of the chat input that says "5 MCP tools available" (or more, if you have installed other MCP servers). There should not be any popup dialogs with errors. Verify by clicking on the hammer that 5 tools from server: foursquare are listed as available.

Finally test it out by asking Claude for place recommendations!

hi claude, can you suggest some good coffee shops near Prospect Heights, Brooklyn?

(It will ask you to allow access to running the foursquare tools)

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

iflow_mcp_foursquare_foursquaremcp-0.1.1.tar.gz (3.5 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

File details

Details for the file iflow_mcp_foursquare_foursquaremcp-0.1.1.tar.gz.

File metadata

  • Download URL: iflow_mcp_foursquare_foursquaremcp-0.1.1.tar.gz
  • Upload date:
  • Size: 3.5 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: uv/0.10.2 {"installer":{"name":"uv","version":"0.10.2","subcommand":["publish"]},"python":null,"implementation":{"name":null,"version":null},"distro":{"name":"Debian GNU/Linux","version":"13","id":"trixie","libc":null},"system":{"name":null,"release":null},"cpu":null,"openssl_version":null,"setuptools_version":null,"rustc_version":null,"ci":null}

File hashes

Hashes for iflow_mcp_foursquare_foursquaremcp-0.1.1.tar.gz
Algorithm Hash digest
SHA256 5184ed3885cb96d6cc63756b006f259f49b7601a6a9402b354b334501ab6c53f
MD5 826618abd9b1684ab68bc44c5c4f60de
BLAKE2b-256 3715ab42b872668a75f226d058d4fea841708b9282f13bded7ddc9bba2fedc4f

See more details on using hashes here.

File details

Details for the file iflow_mcp_foursquare_foursquaremcp-0.1.1-py3-none-any.whl.

File metadata

  • Download URL: iflow_mcp_foursquare_foursquaremcp-0.1.1-py3-none-any.whl
  • Upload date:
  • Size: 4.1 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: uv/0.10.2 {"installer":{"name":"uv","version":"0.10.2","subcommand":["publish"]},"python":null,"implementation":{"name":null,"version":null},"distro":{"name":"Debian GNU/Linux","version":"13","id":"trixie","libc":null},"system":{"name":null,"release":null},"cpu":null,"openssl_version":null,"setuptools_version":null,"rustc_version":null,"ci":null}

File hashes

Hashes for iflow_mcp_foursquare_foursquaremcp-0.1.1-py3-none-any.whl
Algorithm Hash digest
SHA256 07f665bdc7804936c3d55b11c2f18111d1272043cc046b5135859715505968fd
MD5 ddd26a8ddfa2a09e4ae133c007900975
BLAKE2b-256 f4cdae608f21a984947f6300c629c908058efc3b7ca30cc371ca29bf9e2b146f

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page