How to integrate Polymarket US MCP with Autogen

This guide walks you through connecting Polymarket US to AutoGen using the Composio tool router. By the end, you'll have a working Polymarket US agent that can list active polymarket us election markets, show your polymarket us open positions, check polymarket us market order books through natural language commands. This guide will help you understand how to give your AutoGen agent real control over a Polymarket US account through Composio's Polymarket US MCP server. Before we dive in, let's take a quick look at the key ideas and tools involved.

Polymarket US logoPolymarket US
Api Key

Polymarket US is the CFTC-compliant Polymarket product for verified United States users. Use it to access regulated prediction market data and account workflows through official API credentials.

44 Tools

Introduction

This guide walks you through connecting Polymarket US to AutoGen using the Composio tool router. By the end, you'll have a working Polymarket US agent that can list active polymarket us election markets, show your polymarket us open positions, check polymarket us market order books through natural language commands.

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

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

Also integrate Polymarket US with

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 Polymarket US
  • Wire that MCP URL into Autogen using McpWorkbench and StreamableHttpServerParams
  • Configure an Autogen AssistantAgent that can call Polymarket US tools
  • Run a live chat loop where you ask the agent to perform Polymarket US 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 Polymarket US MCP server, and what's possible with it?

The Polymarket US MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Polymarket US account. It provides structured and secure access to your markets, orders, balances, positions, and activity, so your agent can discover markets, inspect prices, place or cancel orders, and monitor your portfolio on your behalf.

  • Market and event discovery: Have your agent find Polymarket US markets, events, subjects, series, and featured topics that match your interests.
  • Price and order book research: Let the agent check the best bid and offer, review market order books, inspect market details, and look up settlement information.
  • Order creation and management: Direct your agent to place one or several live orders, review open orders, close a position, or cancel selected or all open orders.
  • Portfolio monitoring: Instruct your agent to check account balances, review current positions, and summarize trades, deposits, withdrawals, resolutions, bonuses, and transfers.
  • Sports market exploration: Have your agent browse sports, leagues, teams, and related events, including markets for leagues such as the NBA or NFL.

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 Polymarket US 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 Polymarket US 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 Polymarket US 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 Polymarket US session
    composio = Composio(api_key=os.getenv("COMPOSIO_API_KEY"))
    session = composio.create(
        user_id=os.getenv("USER_ID"),
        toolkits=["polymarket_us"]
    )
    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 Polymarket US 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 Polymarket US assistant agent with MCP tools
    agent = AssistantAgent(
        name="polymarket_us_assistant",
        description="An AI assistant that helps with Polymarket US 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 Polymarket US 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 Polymarket US 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 Polymarket US 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 Polymarket US 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 Polymarket US session
    composio = Composio(api_key=os.getenv("COMPOSIO_API_KEY"))
    session = composio.create(
        user_id=os.getenv("USER_ID"),
        toolkits=["polymarket_us"]
    )
    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 Polymarket US assistant agent with MCP tools
        agent = AssistantAgent(
            name="polymarket_us_assistant",
            description="An AI assistant that helps with Polymarket US 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 Polymarket US 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 Polymarket US 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 Polymarket US, you can reuse the same structure for other MCP-enabled apps with minimal code changes.
TOOLS

Supported Tools

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

Cancel All Open Orders

Cancel all authenticated Polymarket US open orders, optionally scoped to specific market slugs.

Cancel Multiple Orders

Cancel up to 20 Polymarket US open orders in one request.

Cancel Order

Cancel one Polymarket US open order by exchange-assigned order ID.

Close Position Order

Create a live Polymarket US order intended to close an existing position in one market.

Create Multiple Orders

Submit up to 20 live Polymarket US orders in one request.

Create Order

Submit one live Polymarket US order.

Get Account Balances

Get the authenticated user's Polymarket US account balances.

Get Activities

Get authenticated Polymarket US portfolio activities such as trades, resolutions, deposits, withdrawals, referral bonuses, and transfers.

Get Event By ID

Get one Polymarket US event by numeric ID from the public gateway API.

Get Event By Slug

Get one Polymarket US event by slug from the public gateway API.

Get League By Slug

Get a current Polymarket US v2 league by slug.

Get Market BBO

Get the best bid and offer for one Polymarket US market by slug.

Get Market Book

Get the public order book for one Polymarket US market by slug.

Get Market By ID

Get one Polymarket US market by numeric ID from the public gateway API.

Get Market By Slug

Get one Polymarket US market by slug from the public gateway API.

Get Market Settlement

Get settlement information for one Polymarket US market by slug.

Get Markets For Subject

Discover Polymarket US markets associated with a subject ID.

Get Markets For Subject By Slug

Discover Polymarket US markets associated with a subject slug.

Get Open Orders

Get all open orders for the authenticated Polymarket US user.

Get Order

Get an authenticated user's Polymarket US order by exchange-assigned order ID.

Get Series By ID

Get a Polymarket US series by numeric ID.

Get Sport By Slug

Get a current Polymarket US v2 sport by slug.

Get Subject By ID

Get a Polymarket US subject entity by numeric ID.

Get Subject By Slug

Get a Polymarket US subject entity by slug.

Get Tag By ID

Get a Polymarket US topic, sport, or league tag by numeric ID.

Get Tag By Slug

Get a Polymarket US topic, sport, or league tag by slug.

Get User Positions

Get the authenticated user's Polymarket US trading positions across all markets or filtered by a specific market slug.

List Events

Discover Polymarket US events from the public gateway API.

List Events For League

List Polymarket US events for a current v2 league slug such as "nba" or "nfl".

List Events For Series

List Polymarket US sports events for a legacy v1 series ID.

List Events For Sport

List Polymarket US events for a current v2 sport slug such as "football" or "basketball".

List Featured Tags

List featured Polymarket US tag sections from the public gateway API.

List Leagues

List current Polymarket US sports leagues from the v2 public gateway API.

List Markets

Discover Polymarket US markets from the public gateway API.

List Series

List Polymarket US series from the public gateway API.

List Sports

List Polymarket US sports from the current v2 public gateway API.

List Sports Teams

List Polymarket US sports teams from the legacy v1 public gateway API.

List Sports Teams For Provider

List Polymarket US legacy v1 sports team mappings for a data provider.

List Subjects

List Polymarket US subject entities from the public gateway API.

List Tags

List ranked Polymarket US tags from the public gateway API.

Modify Multiple Orders

Modify up to 20 Polymarket US open orders in one request.

Modify Order

Modify one existing Polymarket US open order.

Preview Order

Preview a Polymarket US order without submitting it to the market.

Search Markets And Events

Search public Polymarket US markets and events for discovery.

FAQ

Frequently asked questions

With a standalone Polymarket US MCP server, the agents and LLMs can only access a fixed set of Polymarket US tools tied to that server. However, with the Composio Tool Router, agents can dynamically load tools from Polymarket US 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 Polymarket US tools.

Yes, absolutely. You can configure which Polymarket US 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 Polymarket US data and credentials are handled as safely as possible.

Start with Polymarket US.It takes 30 seconds.

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

Start building