How to Use the Foursquare MCP in OpenAI Agents SDK

Q: How does the OpenAI Agents SDK discover the tools in this Foursquare MCP server?

It's automatic. When you pass the server's URL to the MCPServerStreamableHttp constructor, the SDK queries the endpoint to get a list of all available tools, like searchplaces and getplacedetails. This happens when the agent initializes.

Build location-aware agents with built-in guardrails using the OpenAI Agents SDK and Foursquare's real-world place data.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Foursquare MCP to OpenAI Agents SDK

Create your Vinkius account to connect Foursquare to OpenAI Agents SDK and route execution through our secure gateway. The platform manages server hosting, runtime updates, and security layers. Configuration requires no manual server provisioning.

GDPR Free for Subscribers

Setup Foursquare with OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Find and suggest places

Your agent can find any venue on the map. Use `search_places` to locate businesses by name or category, and `autocomplete_venues` to power a live typeahead for user input. It’s a direct line to Foursquare's point-of-interest graph. Because you're using the OpenAI Agents SDK, you can set guardrails that validate agent actions before they ever call the Foursquare API. This stops bad queries, controls costs, and gives you a full audit trail in the OpenAI dashboard.

Get the ground truth on any venue

Go beyond a name and address. Once your agent has a location, it can pull structured details with `get_place_details`, see the venue with `get_place_photos`, and read user reviews with `get_place_tips`. You get a complete, multi-faceted view of a place. This is where specialized agents shine. One agent can find a list of places, handing off to another agent that analyzes the tips for a specific vibe. The SDK manages the state and handoffs between them, letting you build complex, multi-agent logic.

Build with this MCP Server

Your agent can define and search custom geographic areas. It's not stuck with simple radius searches. Let it draw a custom delivery zone with `search_within_polygon` or confirm a location isn't a duplicate with `match_venue_exactly` before writing to your database. All tools are auto-discovered. Just point the SDK to this MCP Server endpoint and the agent knows what it can do. For production, set `cacheToolsList=True` so it doesn't need to fetch the tool list on every startup.

Setup guide

Set up Foursquare MCP in OpenAI Agents SDK

Prerequisites

Python 3.10+ installed
openai-agents package (pip install openai-agents)
Active Vinkius subscription with a valid endpoint token

1

Install the SDK

Run pip install openai-agents to install the OpenAI Agents SDK. The MCP integration is built-in — no extra dependencies needed.
2

Connect via SSE transport

Use MCPServerSse with your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. The SDK auto-discovers all Foursquare tools at runtime.
3

Create your Agent

Pass the MCP to Agent(mcp_servers=[server]). The agent receives Foursquare tools as native definitions — JSON schemas resolve automatically.
4

Run the agent

Call Runner.run(agent, prompt) to execute. The agent invokes the appropriate Foursquare tools and returns structured results. Copy the full example on the right to get started.

agent.py

import asyncio
from agents import Agent, Runner
from agents.mcp import MCPServerSse

async def main():
    async with MCPServerSse(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ) as server:
        agent = Agent(
            name="Foursquare Agent",
            instructions="You have access to Foursquare tools.",
            mcp_servers=[server],
        )
        result = await Runner.run(agent, "List recent transactions")
        print(result.final_output)

asyncio.run(main())

Get your connection token →

Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by Foursquare. All third-party trademarks, logos, and brand names are the property of their respective owners. Their use on this website is strictly for informational purposes to identify service compatibility and interoperability.

Why Choose Vinkius

Vinkius connects your tools to AI with real-time monitoring and automatic cost savings — all from one dashboard.

Connect Foursquare now

Real-time monitoring

Live

visibility into every interaction

Connect your favorite tools to your AI and see exactly what's happening — every request, every response, in real time.

Built-in savings

60%

lower AI costs

Vinkius compresses data between your apps and your AI automatically. Lower bills every month — no configuration required.

Single dashboard

One

place for every integration

Every tool your AI connects to, managed from a single screen. One account, complete control.

Common questions about Foursquare MCP in OpenAI Agents SDK

It's automatic. When you pass the server's URL to the `MCPServerStreamableHttp` constructor, the SDK queries the endpoint to get a list of all available tools, like `search_places` and `get_place_details`. This happens when the agent initializes.

Yes. The OpenAI Agents SDK has guardrails. You can write a function that inspects the agent's proposed action and reject it if it involves a tool you want to restrict, like `get_place_photos`, before the API call is ever made.

Use a two-step process. First, let the user type freely and have the agent use `autocomplete_venues` to suggest completions. Once the user selects one, use `search_places` or `get_place_details` to fetch the full record for the confirmed location.

Absolutely. The OpenAI platform provides full tracing for agent activity. You'll see every call to this MCP server, including the tool used and the parameters passed, right in your OpenAI dashboard.

Your agent will handle Foursquare place data, which includes names, addresses, categories, photo URLs, and user-generated tips. Security is managed by Vinkius; the server runs in a sandboxed, ephemeral environment. Your OpenAI agent interacts via a single, secure endpoint token.

Use it with your favorite AI tools

Connect this server to Cursor, Claude, VS Code, and more.

OpenAI Agents SDK sdk-python

Google ADK sdk-python

Pydantic AI sdk-python

Vercel AI SDK sdk-typescript