How to integrate Composio MCP with Autogen

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

Introduction

This guide walks you through connecting Composio to AutoGen using the Composio tool router. By the end, you'll have a working Composio agent that can generate a step-by-step workflow plan, check active connections for all toolkits, download public s3 file to local path, show tool dependencies for workflow setup through natural language commands.

This guide will help you understand how to give your AutoGen agent real control over a Composio account through Composio's Composio 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 Composio
  • Wire that MCP URL into Autogen using McpWorkbench and StreamableHttpServerParams
  • Configure an Autogen AssistantAgent that can call Composio tools
  • Run a live chat loop where you ask the agent to perform Composio 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 Composio MCP server, and what's possible with it?

The Composio MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Composio account. It provides structured and secure access to your connected tools, so your agent can plan workflows, orchestrate complex actions, manage integrations, and execute cross-tool automations on your behalf.

  • Automated workflow planning and execution: The agent can generate and run step-by-step plans for complex, multi-tool use cases—ensuring tasks are completed reliably, even when they span multiple services.
  • Connection management and discovery: Effortlessly check the status of multiple toolkit connections, discover what integrations are active, and manage how your agent connects to different services.
  • Tool and dependency exploration: Ask your agent to map out tool dependencies, discover related tools, and understand which tools work best together for your workflow.
  • Direct code and command execution: Let the agent run code snippets or shell commands in supported environments, tying together automation across your stack.
  • Bulk and parallel operations: Use specialized tools for parallel execution or to handle many similar tasks at once—speeding up large automations by making multiple calls in a single workflow.

Supported Tools & Triggers

Tools
Ask OracleStatic helper that returns a comprehensive system prompt describing how to plan and execute tasks using the available composio tools and workflows.
Check active connection (deprecated)Deprecated: use check active connections instead for bulk operations.
Check multiple active connectionsCheck active connection status for multiple toolkits or specific connected account ids.
Create PlanThis is a workflow builder that ensures the LLM produces a complete, step-by-step plan for any use case.
Download S3 FileDownload a file from a public s3 (or r2) url to a local path.
Enable triggerEnable a specific trigger for the authenticated user.
Execute agentExecute complex workflows using ai agent reasoning between multiple tool calls.
Execute Composio ToolExecute a tool using the composio api.
Get Tool Dependency GraphGet the dependency graph for a given tool, showing related parent tools that might be useful.
Get required parameters for connectionGets the required parameters for connecting to a toolkit via initiate connection.
Get response schemaRetrieves the response schema for a specified composio tool.
Initiate connectionInitiate a connection to a toolkit with comprehensive authentication support.
List toolkitsList all the available toolkits on composio with filtering options.
List triggersList available triggers and their configuration schemas.
Manage connectionManage a connection to a toolkit with comprehensive authentication support.
Manage connectionsCreate or manage connections to user's apps.
Multi Execute Composio ToolsFast and parallel tool executor for tools discovered through COMPOSIO_SEARCH_TOOLS.
Run bash commandsExecute bash commands in a REMOTE sandbox for file operations, data processing, and system tasks.
Execute Code remotely in work benchProcess REMOTE FILES or script BULK TOOL EXECUTIONS using Python code IN A REMOTE SANDBOX.
Retrieve ToolkitsToolkits are like github, linear, gmail, etc.
Search agentDiscover tools and analyze dependencies for complex workflows using ai agent.
Search Composio ToolsMCP Server Info: COMPOSIO MCP connects 500+ apps—Slack, GitHub, Notion, Google Workspace (Gmail, Sheets, Drive, Calendar), Microsoft (Outlook, Teams), X, Figma, Web Search, Meta apps (WhatsApp, Instagram), TikTok, AI tools like Nano Banana & Veo3, and more—for seamless cross-app automation.
Wait for connectionWait for the user to complete authentication AFTER you have given them an auth URL from COMPOSIO_MANAGE_CONNECTIONS.
Create / Update Recipe from WorkflowConvert the executed workflow into a notebook.
Execute RecipeExecutes a Recipe
Create / Update Skill from WorkflowConvert the executed workflow into a skill using Python Pydantic code.
Get Existing Recipe DetailsGet the details of the existing recipe for a given recipe id.

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

How to build Composio MCP Agent with another framework

OpenAI Agents SDK

OpenAI Agents SDK

Use Composio MCP with OpenAI Agents SDK

Claude Agent SDK

Claude Agent SDK

Use Composio MCP with Claude Agent SDK

Google ADK

Google ADK

Use Composio MCP with Google ADK

LangChain

LangChain

Use Composio MCP with LangChain

Vercel AI SDK

Vercel AI SDK

Use Composio MCP with Vercel AI SDK

Mastra AI

Mastra AI

Use Composio MCP with Mastra AI

LlamaIndex

LlamaIndex

Use Composio MCP with LlamaIndex

CrewAI

CrewAI

Use Composio MCP with CrewAI

FAQ

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

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

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

Yes, absolutely. You can configure which Composio 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 Composio 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