How to integrate Polygon MCP with Autogen

BOOK A CALLGET STARTED FOR FREE
Framework Integration Gradient
Polygon Logo
AutoGen Logo
divider

Introduction

This guide walks you through connecting Polygon to AutoGen using the Composio tool router. By the end, you'll have a working Polygon agent that can show the latest closing price for btc-usd, list all stock tickers traded on nasdaq, get the crypto rsi for eth over 14 days, check if u.s. stock markets are open right now through natural language commands.

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

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

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

The Polygon MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Polygon account. It provides structured and secure access to real-time and historical financial market data, so your agent can retrieve market status, analyze price indicators, track dividends, and monitor crypto and stock tickers on your behalf.

  • Market status and holiday tracking: Instantly check if U.S. exchanges are open or closed and retrieve upcoming market holidays or early closures to plan trading activities.
  • Comprehensive ticker retrieval: Ask your agent to fetch all available ticker symbols across asset classes, including stocks, crypto, forex, and options, filtered by market or exchange.
  • Crypto technical analysis: Have your agent calculate moving averages (EMA, SMA), MACD, and RSI indicators for specific cryptocurrencies to support informed trading decisions.
  • Daily and historical price fetching: Let your agent retrieve daily open/close prices, previous day’s close, or detailed price history for cryptocurrencies and stocks with just a prompt.
  • Dividend data extraction: Effortlessly access up-to-date corporate dividend information for stocks, enabling portfolio reviews and income analysis.

Supported Tools & Triggers

Tools
Get All TickersTool to retrieve all ticker symbols across asset classes.
Get Crypto Exponential Moving Average (EMA)Tool to retrieve exponential moving average (ema) for a cryptocurrency ticker.
Get Crypto MACD IndicatorTool to retrieve the macd (moving average convergence/divergence) for a crypto ticker.
Get Crypto RSI IndicatorTool to retrieve the relative strength index (rsi) for a crypto ticker.
Get Crypto Simple Moving Average (SMA)Tool to retrieve the simple moving average (sma) for a given crypto ticker.
Get Crypto Open/CloseTool to fetch daily open and close prices for a given crypto pair on a specified date.
Get Crypto Previous CloseTool to retrieve previous day’s close for a crypto ticker.
Get DividendsTool to retrieve dividend data for stocks.
Get Upcoming Market HolidaysTool to retrieve upcoming market holidays and half-day closures.
Get Market StatusTool to retrieve current market status.
Get NewsTool to retrieve recent news articles related to a ticker.
Get reference conditionsTool to retrieve market condition code mappings.
Get reference exchangesTool to retrieve supported exchanges and their details.
Get Stock SplitsTool to retrieve stock split events.
Get Exponential Moving Average (EMA)Tool to fetch exponential moving average (ema) for a given stock ticker.
Get Simple Moving Average (SMA)Tool to fetch simple moving average (sma) for a given stock ticker.
Get Ticker DetailsTool to retrieve detailed information for a ticker.
Get Ticker TypesTool to retrieve all ticker types supported by polygon.

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

What is Tool Router?

Composio's Tool Router 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 Tool Router

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

How the Tool Router works

The Tool Router 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

Prerequisites

You will need:

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

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.

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 Polygon via MCP
  • autogen-agentchat provides the AssistantAgent class
  • autogen-ext-openai provides the OpenAI model client
  • autogen-ext-tools provides MCP workbench support

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 Polygon connections to use

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 Polygon session
    composio = Composio(api_key=os.getenv("COMPOSIO_API_KEY"))
    session = composio.create(
        user_id=os.getenv("USER_ID"),
        toolkits=["polygon"]
    )
    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 Polygon tools
  • session.mcp.url is the MCP endpoint that Autogen will connect to

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

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 Polygon assistant agent with MCP tools
    agent = AssistantAgent(
        name="polygon_assistant",
        description="An AI assistant that helps with Polygon 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 Polygon tools from the workbench

Run the interactive chat loop

python
print("Chat started! Type 'exit' or 'quit' to end the conversation.\n")
print("Ask any Polygon 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 Polygon 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 Polygon 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 Polygon session
    composio = Composio(api_key=os.getenv("COMPOSIO_API_KEY"))
    session = composio.create(
        user_id=os.getenv("USER_ID"),
        toolkits=["polygon"]
    )
    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 Polygon assistant agent with MCP tools
        agent = AssistantAgent(
            name="polygon_assistant",
            description="An AI assistant that helps with Polygon 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 Polygon 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 Polygon 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 Polygon, you can reuse the same structure for other MCP-enabled apps with minimal code changes.

How to build Polygon MCP Agent with another framework

OpenAI Agents SDK

OpenAI Agents SDK

Use Polygon MCP with OpenAI Agents SDK

Claude Agent SDK

Claude Agent SDK

Use Polygon MCP with Claude Agent SDK

Google ADK

Google ADK

Use Polygon MCP with Google ADK

LangChain

LangChain

Use Polygon MCP with LangChain

Vercel AI SDK

Vercel AI SDK

Use Polygon MCP with Vercel AI SDK

Mastra AI

Mastra AI

Use Polygon MCP with Mastra AI

LlamaIndex

LlamaIndex

Use Polygon MCP with LlamaIndex

CrewAI

CrewAI

Use Polygon MCP with CrewAI

FAQ

What are the differences in Tool Router MCP and Polygon MCP?

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

Can I use Tool Router MCP with Autogen?

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 Polygon tools.

Can I manage the permissions and scopes for Polygon while using Tool Router?

Yes, absolutely. You can configure which Polygon 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.

How safe is my data with Composio Tool Router?

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 Polygon data and credentials are handled as safely as possible.

Used by agents from

Context
ASU
Letta
glean
HubSpot
Agent.ai
Altera
DataStax
Entelligence
Rolai
Context
ASU
Letta
glean
HubSpot
Agent.ai
Altera
DataStax
Entelligence
Rolai
Context
ASU
Letta
glean
HubSpot
Agent.ai
Altera
DataStax
Entelligence
Rolai

Never worry about agent reliability

We handle tool reliability, observability, and security so you never have to second-guess an agent action.

Book a call↗Get started for free