SIGN UPLOG IN
X (Twitter)LinkedInGitHubDiscordYouTube

How to integrate Foursquare MCP with Autogen

Connect Autogen to Foursquare MCP. Find coffee shops open near me now, show photos of central park attractions, and more using natural language, with authentication handled for you.

Get started for freeGet a demo
Foursquare logoFoursquare
Api Key

Foursquare is a global location platform for searching places and place recommendations. It helps users discover restaurants, shops, and venues with rich, up-to-date data.

8 Tools

Introduction

This guide walks you through connecting Foursquare to AutoGen using the Composio tool router. By the end, you'll have a working Foursquare agent that can search places, find nearby venues, autocomplete place names, fetch place photos and tips, and get trending venues through natural language commands.

This guide will help you understand how to give your AutoGen agent real control over a Foursquare account through Composio's Foursquare MCP server.

Before we dive in, let's take a quick look at the key ideas and tools involved.

Also integrate Foursquare with

Claude CodeClaude CoworkOpenAI Agents SDKClaude Agent SDKCodexOpenClawHermesAtomic AgentGoogle ADKLangChainVercel AI SDKMastra AILlamaIndexCrewAIPydantic AI

TL;DR

Here's what you'll learn:
  • Get and set up your OpenAI and Composio API keys
  • Install the required dependencies for Autogen and Composio
  • Initialize Composio and create a Tool Router session for Foursquare
  • Wire that MCP URL into Autogen using McpWorkbench and StreamableHttpServerParams
  • Configure an Autogen AssistantAgent that can call Foursquare tools
  • Run a live chat loop where you ask the agent to perform Foursquare operations

What is AutoGen?

Autogen is a framework for building multi-agent conversational AI systems from Microsoft. It enables you to create agents that can collaborate, use tools, and maintain complex workflows.

Key features include:

  • Multi-Agent Systems: Build collaborative agent workflows
  • MCP Workbench: Native support for Model Context Protocol tools
  • Streaming HTTP: Connect to external services through streamable HTTP
  • AssistantAgent: Pre-built agent class for tool-using assistants

What is the Foursquare MCP server, and what's possible with it?

The Foursquare MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Foursquare account. It provides structured and secure access to the powerful Foursquare Places database, so your agent can search for venues, recommend places, retrieve detailed location data, surface user tips, and even fetch photos—all on your behalf.

  • Comprehensive place search and discovery: Let your agent find places or points of interest nearby or in any area using keywords, categories, or specific criteria.
  • Retrieve rich place details: Instantly pull in-depth information about a specific venue, including its name, address, ratings, categories, and more.
  • Access user-generated tips and reviews: Have your agent surface real user insights, tips, and experiences for any place to help guide your decisions.
  • Fetch location photos: Enhance your applications by retrieving and displaying user-contributed images for any venue in the Foursquare database.
  • Explore lesser-known and trending spots: Use Foursquare's broader search to discover new, up-and-coming, or hidden places that might not appear in standard searches.

What is the Composio tool router, and how does it fit here?

What is Composio SDK?

Composio's Composio SDK helps agents find the right tools for a task at runtime. You can plug in multiple toolkits (like Gmail, HubSpot, and GitHub), and the agent will identify the relevant app and action to complete multi-step workflows. This can reduce token usage and improve the reliability of tool calls. Read more here: Getting started with Composio SDK

The tool router generates a secure MCP URL that your agents can access to perform actions.

How the Composio SDK works

The Composio SDK follows a three-phase workflow:

  1. Discovery: Searches for tools matching your task and returns relevant toolkits with their details.
  2. Authentication: Checks for active connections. If missing, creates an auth config and returns a connection URL via Auth Link.
  3. Execution: Executes the action using the authenticated connection.

Step-by-step Guide

Step by step08 STEPS
1

Prerequisites

You will need:

  • A Composio API key
  • An OpenAI API key (used by Autogen's OpenAIChatCompletionClient)
  • A Foursquare account you can connect to Composio
  • Some basic familiarity with Autogen and Python async
2

Getting API Keys for OpenAI and Composio

OpenAI API Key
  • Go to the OpenAI dashboard and create an API key. You'll need credits to use the models, or you can connect to another model provider.
  • Keep the API key safe.
Composio API Key
  • Log in to the Composio dashboard.
  • Navigate to your API settings and generate a new API key.
  • Store this key securely as you'll need it for authentication.
3

Install dependencies

bash
pip install composio python-dotenv
pip install autogen-agentchat autogen-ext-openai autogen-ext-tools

Install Composio, Autogen extensions, and dotenv.

What's happening:

  • composio connects your agent to Foursquare via MCP
  • autogen-agentchat provides the AssistantAgent class
  • autogen-ext-openai provides the OpenAI model client
  • autogen-ext-tools provides MCP workbench support

4

Set up environment variables

bash
COMPOSIO_API_KEY=your-composio-api-key
OPENAI_API_KEY=your-openai-api-key
USER_ID=your-user-identifier@example.com

Create a .env file in your project folder.

What's happening:

  • COMPOSIO_API_KEY is required to talk to Composio
  • OPENAI_API_KEY is used by Autogen's OpenAI client
  • USER_ID is how Composio identifies which user's Foursquare connections to use
5

Import dependencies and create Tool Router session

python
import asyncio
import os
from dotenv import load_dotenv
from composio import Composio

from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient
from autogen_ext.tools.mcp import McpWorkbench, StreamableHttpServerParams

load_dotenv()

async def main():
    # Initialize Composio and create a Foursquare session
    composio = Composio(api_key=os.getenv("COMPOSIO_API_KEY"))
    session = composio.create(
        user_id=os.getenv("USER_ID"),
        toolkits=["foursquare"]
    )
    url = session.mcp.url
What's happening:
  • load_dotenv() reads your .env file
  • Composio(api_key=...) initializes the SDK
  • create(...) creates a Tool Router session that exposes Foursquare tools
  • session.mcp.url is the MCP endpoint that Autogen will connect to
6

Configure MCP parameters for Autogen

python
# Configure MCP server parameters for Streamable HTTP
server_params = StreamableHttpServerParams(
    url=url,
    timeout=30.0,
    sse_read_timeout=300.0,
    terminate_on_close=True,
    headers={"x-api-key": os.getenv("COMPOSIO_API_KEY")}
)

Autogen expects parameters describing how to talk to the MCP server. That is what StreamableHttpServerParams is for.

What's happening:

  • url points to the Tool Router MCP endpoint from Composio
  • timeout is the HTTP timeout for requests
  • sse_read_timeout controls how long to wait when streaming responses
  • terminate_on_close=True cleans up the MCP server process when the workbench is closed
7

Create the model client and agent

python
# Create model client
model_client = OpenAIChatCompletionClient(
    model="gpt-5",
    api_key=os.getenv("OPENAI_API_KEY")
)

# Use McpWorkbench as context manager
async with McpWorkbench(server_params) as workbench:
    # Create Foursquare assistant agent with MCP tools
    agent = AssistantAgent(
        name="foursquare_assistant",
        description="An AI assistant that helps with Foursquare operations.",
        model_client=model_client,
        workbench=workbench,
        model_client_stream=True,
        max_tool_iterations=10
    )

What's happening:

  • OpenAIChatCompletionClient wraps the OpenAI model for Autogen
  • McpWorkbench connects the agent to the MCP tools
  • AssistantAgent is configured with the Foursquare tools from the workbench
8

Run the interactive chat loop

python
print("Chat started! Type 'exit' or 'quit' to end the conversation.\n")
print("Ask any Foursquare related question or task to the agent.\n")

# Conversation loop
while True:
    user_input = input("You: ").strip()

    if user_input.lower() in ["exit", "quit", "bye"]:
        print("\nGoodbye!")
        break

    if not user_input:
        continue

    print("\nAgent is thinking...\n")

    # Run the agent with streaming
    try:
        response_text = ""
        async for message in agent.run_stream(task=user_input):
            if hasattr(message, "content") and message.content:
                response_text = message.content

        # Print the final response
        if response_text:
            print(f"Agent: {response_text}\n")
        else:
            print("Agent: I encountered an issue processing your request.\n")

    except Exception as e:
        print(f"Agent: Sorry, I encountered an error: {str(e)}\n")
What's happening:
  • The script prompts you in a loop with You:
  • Autogen passes your input to the model, which decides which Foursquare tools to call via MCP
  • agent.run_stream(...) yields streaming messages as the agent thinks and calls tools
  • Typing exit, quit, or bye ends the loop

Complete Code

Here's the complete code to get you started with Foursquare and AutoGen:

python
import asyncio
import os
from dotenv import load_dotenv
from composio import Composio

from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient
from autogen_ext.tools.mcp import McpWorkbench, StreamableHttpServerParams

load_dotenv()

async def main():
    # Initialize Composio and create a Foursquare session
    composio = Composio(api_key=os.getenv("COMPOSIO_API_KEY"))
    session = composio.create(
        user_id=os.getenv("USER_ID"),
        toolkits=["foursquare"]
    )
    url = session.mcp.url

    # Configure MCP server parameters for Streamable HTTP
    server_params = StreamableHttpServerParams(
        url=url,
        timeout=30.0,
        sse_read_timeout=300.0,
        terminate_on_close=True,
        headers={"x-api-key": os.getenv("COMPOSIO_API_KEY")}
    )

    # Create model client
    model_client = OpenAIChatCompletionClient(
        model="gpt-5",
        api_key=os.getenv("OPENAI_API_KEY")
    )

    # Use McpWorkbench as context manager
    async with McpWorkbench(server_params) as workbench:
        # Create Foursquare assistant agent with MCP tools
        agent = AssistantAgent(
            name="foursquare_assistant",
            description="An AI assistant that helps with Foursquare operations.",
            model_client=model_client,
            workbench=workbench,
            model_client_stream=True,
            max_tool_iterations=10
        )

        print("Chat started! Type 'exit' or 'quit' to end the conversation.\n")
        print("Ask any Foursquare related question or task to the agent.\n")

        # Conversation loop
        while True:
            user_input = input("You: ").strip()

            if user_input.lower() in ['exit', 'quit', 'bye']:
                print("\nGoodbye!")
                break

            if not user_input:
                continue

            print("\nAgent is thinking...\n")

            # Run the agent with streaming
            try:
                response_text = ""
                async for message in agent.run_stream(task=user_input):
                    if hasattr(message, 'content') and message.content:
                        response_text = message.content

                # Print the final response
                if response_text:
                    print(f"Agent: {response_text}\n")
                else:
                    print("Agent: I encountered an issue processing your request.\n")

            except Exception as e:
                print(f"Agent: Sorry, I encountered an error: {str(e)}\n")

if __name__ == "__main__":
    asyncio.run(main())

Conclusion

You now have an Autogen assistant wired into Foursquare through Composio's Tool Router and MCP. From here you can:
  • Add more toolkits to the toolkits list, for example notion or hubspot
  • Refine the agent description to point it at specific workflows
  • Wrap this script behind a UI, Slack bot, or internal tool
Once the pattern is clear for Foursquare, you can reuse the same structure for other MCP-enabled apps with minimal code changes.
TOOLS

Supported Tools

Every Foursquare action and event your agent gets out of the box.

Autocomplete places

Returns autocomplete suggestions for places as the user types their search query.

Get trending venues

Searches for places around specified coordinates, sorted by popularity.

Retrieve nearby places v3

The GetNearbyPlaces endpoint retrieves a list of places near a specified location, primarily supporting check-in use cases and local discovery.

Retrieve place photos by id

Retrieves photos associated with a specific place in Foursquare's database.

Retrieve places by id

Retrieves detailed information about a specific place using its unique Foursquare ID (FSQ ID).

Retrieve place tips using fsq id

Retrieves user-generated tips for a specific Foursquare place by its FSQ ID.

Search places api request

The GetPlacesSearch endpoint allows you to search for places in the Foursquare database based on various criteria such as location, keywords, and categories.

Validate API credentials

Validates Foursquare API credentials by performing a lightweight place search.

FRAMEWORKS

How to build Foursquare MCP Agent with another framework

Claude Code logo

Claude Code

Use Foursquare MCP with Claude Code

Claude Cowork logo

Claude Cowork

Use Foursquare MCP with Claude Cowork

OpenAI Agents SDK logo

OpenAI Agents SDK

Use Foursquare MCP with OpenAI Agents SDK

Claude Agent SDK logo

Claude Agent SDK

Use Foursquare MCP with Claude Agent SDK

Codex logo

Codex

Use Foursquare MCP with Codex

OpenClaw logo

OpenClaw

Use Foursquare MCP with OpenClaw

Hermes logo

Hermes

Use Foursquare MCP with Hermes

Atomic Agent logo

Atomic Agent

Use Foursquare MCP with Atomic Agent

Google ADK logo

Google ADK

Use Foursquare MCP with Google ADK

LangChain logo

LangChain

Use Foursquare MCP with LangChain

Vercel AI SDK logo

Vercel AI SDK

Use Foursquare MCP with Vercel AI SDK

Mastra AI logo

Mastra AI

Use Foursquare MCP with Mastra AI

LlamaIndex logo

LlamaIndex

Use Foursquare MCP with LlamaIndex

CrewAI logo

CrewAI

Use Foursquare MCP with CrewAI

Pydantic AI logo

Pydantic AI

Use Foursquare MCP with Pydantic AI

FAQ

Frequently asked questions

With a standalone Foursquare MCP server, the agents and LLMs can only access a fixed set of Foursquare tools tied to that server. However, with the Composio Tool Router, agents can dynamically load tools from Foursquare and many other apps based on the task at hand, all through a single MCP endpoint.

Yes, you can. Autogen fully supports MCP integration. You get structured tool calling, message history handling, and model orchestration while Tool Router takes care of discovering and serving the right Foursquare tools.

Yes, absolutely. You can configure which Foursquare scopes and actions are allowed when connecting your account to Composio. You can also bring your own OAuth credentials or API configuration so you keep full control over what the agent can do.

All sensitive data such as tokens, keys, and configuration is fully encrypted at rest and in transit. Composio is SOC 2 Type 2 compliant and follows strict security practices so your Foursquare data and credentials are handled as safely as possible.

Start with Foursquare.It takes 30 seconds.

Managed auth, hosted MCP servers, and every Foursquare tool your agent needs.Free to start.

Start building