How to Use the Foursquare MCP in Google ADK

Q: How do I connect the Google ADK to this MCP server for Foursquare?

You'll use the McpToolset class. Instantiate it with the server's URL and pass the resulting toolset object into the tools argument of your LlmAgent. The ADK handles the connection and tool registration.

Q: Can I limit which Foursquare tools my Google ADK agent can use from this MCP toolset?

Yes, you can. When creating the McpToolset, you can pass an optional toolnames filter. This lets you expose only a specific subset of the Foursquare tools, like getplacedetails and getplacetips, to a particular agent.

Connect Gemini agents to Foursquare's location data inside your Google Cloud environment with the Google ADK.

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 Google ADK

Create your Vinkius account to connect Foursquare to Google ADK 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 Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Query Foursquare, analyze in BigQuery

Let your agent find points of interest using `search_places`. The Google ADK makes it simple to take the IDs from that search and write them to a BigQuery table for large-scale analysis or long-term storage. This connects live place data to your data warehouse. Gemini's long context window changes the game. Your agent can reason over thousands of results from Foursquare's `search_nearby_venues` at once. It can compare options across an entire city, not just a handful of results.

Enrich data with Vertex AI

Don't just get data, get understanding. Your agent can pull user reviews with `get_place_tips` and pass them to a Vertex AI model for sentiment analysis. Now you have a qualitative score, not just a 1-5 star rating. You can do the same for images. Use `get_place_photos` to get image URLs and send them to the Vertex AI Vision API. Your agent can now 'see' if a restaurant has outdoor seating or if a park looks safe at night, all within your GCP project.

Build enterprise-grade location logic

This MCP Server gives your agent tools for real business problems. Use `search_within_polygon` for logistics planning inside custom delivery zones or `list_venue_categories` to normalize your own location data against Foursquare's taxonomy. The Google ADK's `McpToolset` lets you control which Foursquare tools are available. You can create a specialized logistics agent that only has access to `search_within_radius`, ensuring it can't perform other actions. You define these permissions in your Python code.

Setup guide

Set up Foursquare MCP in Google ADK

Prerequisites

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

1

Install Google ADK

Run pip install google-adk to install the Agent Development Kit. MCP support is included via the McpToolset class.
2

Connect via SSE transport

Use McpToolset.from_server() with SseServerParams pointing to your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Create an LlmAgent

Pass the returned mcp_tools list directly to LlmAgent(tools=mcp_tools). The ADK maps each MCP tool to a native Gemini function call — no manual schema definitions required.
4

Run with any Gemini model

The agent works with any Gemini model (gemini-2.0-flash, gemini-2.5-pro, etc.). Copy the full example on the right to get started with Foursquare tools in your ADK agent.

agent.py

from google.adk.agents import LlmAgent
from google.adk.tools.mcp_tool.mcp_toolset import McpToolset
from google.adk.tools.mcp_tool.mcp_session_manager import SseServerParams

# Connect to the MCP via SSE
mcp_tools, exit_stack = await McpToolset.from_server(
    connection_params=SseServerParams(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    )
)

# Create your agent with auto-discovered tools
agent = LlmAgent(
    name="Foursquare_agent",
    model="gemini-2.0-flash",
    instruction="You have access to Foursquare tools via MCP.",
    tools=mcp_tools,
)

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 Google ADK

You'll use the `McpToolset` class. Instantiate it with the server's URL and pass the resulting toolset object into the `tools` argument of your `LlmAgent`. The ADK handles the connection and tool registration.

Yes. This is a key benefit of using the Google ADK. A model like Gemini 1.5 Pro has a massive context window, so your agent can analyze and compare thousands of venue details returned from tools like `search_places` in a single prompt.

Definitely. A common pattern is to have your Google ADK agent use `search_places` to find locations, then use a custom tool to write those place IDs and details into a BigQuery table for analysis. The agent acts as the bridge between the two systems.

Yes, you can. When creating the `McpToolset`, you can pass an optional `tool_names` filter. This lets you expose only a specific subset of the Foursquare tools, like `get_place_details` and `get_place_tips`, to a particular agent.

The agent processes location data from Foursquare, including Place IDs, photo URLs, and text from user tips. The Vinkius-managed server provides the data over a secure connection. Since your agent is running on Google Cloud, that data is then handled within your project's IAM and data governance policies.

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