How to integrate Make MCP with Autogen

Connect Autogen to Make MCP. Get all available make operations, show supported languages for make automations, and more using natural language, with authentication handled for you.

Get started for free Get a demo

Make

Api Key

Make is an automation platform that connects your favorite apps and services. Build powerful, custom workflows without writing code.

53 Tools

Managed auth

Connect Make without auth hassles

We manage OAuth, API keys, token refresh, and scopes — you just build.

Book a call

Explore the MCP Gateway

Introduction

This guide walks you through connecting Make to AutoGen using the Composio tool router. By the end, you'll have a working Make agent that can get all available make operations, show supported languages for make automations, list all timezones used in make through natural language commands.

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

The Make MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Make account. It provides structured and secure access to your Make workspace, so your agent can retrieve available operations, list supported languages, and fetch timezone data on your behalf.

Discover available operations: Let your agent fetch all possible workflow operations, making it easy to automate tasks and explore integration options.
Populate language selectors: Effortlessly retrieve a comprehensive list of supported language codes and names to use in multilingual workflows or app settings.
Fetch timezone information: Instantly obtain a list of supported timezone codes and names for accurate scheduling and automation across regions.
Seamless workflow setup: Enable your agent to gather essential configuration data before creating or customizing automations in Make.

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:

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

Step-by-step Guide

Step by step08 STEPS

Prerequisites

You will need:

A Composio API key
An OpenAI API key (used by Autogen's OpenAIChatCompletionClient)
A Make 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 Make 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 Make 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 Make session
    composio = Composio(api_key=os.getenv("COMPOSIO_API_KEY"))
    session = composio.create(
        user_id=os.getenv("USER_ID"),
        toolkits=["make"]
    )
    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 Make 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 Make assistant agent with MCP tools
    agent = AssistantAgent(
        name="make_assistant",
        description="An AI assistant that helps with Make 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 Make 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 Make 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 Make 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 Make 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 Make session
    composio = Composio(api_key=os.getenv("COMPOSIO_API_KEY"))
    session = composio.create(
        user_id=os.getenv("USER_ID"),
        toolkits=["make"]
    )
    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 Make assistant agent with MCP tools
        agent = AssistantAgent(
            name="make_assistant",
            description="An AI assistant that helps with Make 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 Make 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 Make 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 Make, you can reuse the same structure for other MCP-enabled apps with minimal code changes.

TOOLS

Supported Tools

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

Activate Scenario

Activate a Make scenario; a regularly scheduled scenario may run immediately, executing its configured automation and external effects.

Create Hook

Create a hook without exposing its bearer-like URL, UDID, or relay data.

Create Organization

Tool to create a new organization in Make.

Create Scenario

Create a Make scenario from JSON-encoded blueprint and scheduling data.

Create Password Reset Demand

Tool to create a password reset demand for a user by their email address.

Deactivate Scenario

Deactivate a Make scenario and stop it if it is currently running.

Delete Scenario

Move a Make scenario to trash, where it can be restored for 30 days.

Get Cashier Prices

Tool to retrieve a specific cashier price by its identifier.

Get Cashier Products

Tool to retrieve available cashier products from Make.

Get Connection

Retrieve one Make connection by ID.

Get Current Authorization

Tool to retrieve current authorization details for the authenticated user.

Get Enums Apps Review Statuses

Tool to retrieve available app review statuses in Make.

Get Enums IMT Regions

Tool to retrieve the list of Make regions and their regionId values.

Get Enums IMT Zones

Tool to retrieve available IMT zones in Make.

Get Enums LLM Models

Tool to retrieve available Large Language Models from Make.

Get Enums Module Types

Tool to retrieve available module types in Make.

Get Enums Organization Features

Tool to retrieve available organization features in Make.

Get Enums User API Token Scopes

Tool to retrieve all available API token scopes in Make.

Get Enums User Email Notifications

Tool to retrieve available email notification types for Make users.

Get Enums User Features

Retrieve the list of all existing user features and their descriptions.

Get Enums Variable Types

Tool to retrieve available variable types in Make.

Get Hook

Retrieve a hook without exposing its bearer-like URL, UDID, or relay data.

Get Hook Incoming Activity

Get hook queue statistics or safe metadata for one incoming event; payload values are not returned.

Get Hook Log

Retrieve safe status and timing diagnostics for one Make webhook execution log.

Get Operations

Retrieve daily operations usage for an organization over the past 30 days.

Get Organization

Retrieve detailed information about one Make organization by ID.

Get Public Template Blueprint

Retrieve the complete blueprint for a public approved Make template.

Get Scenario

Retrieve one Make scenario by ID with optional selected columns.

Get Scenario Blueprint

Retrieve a sanitized current, draft, or historical scenario blueprint; credential-bearing URL, auth, header, query, password, secret, and token fields are omitted.

Get Scenario Execution

Retrieve the status, outputs, pause metadata, or error for one execution.

Get Scenario Interface

Retrieve a Make scenario's declared input and output interface.

Get Scenario Logs

List scenario logs, list one module's operation logs, or retrieve one execution log according to the identifiers supplied.

Get Scenario Trigger

Retrieve safe trigger details without exposing its URL or UDID.

Get Team

Retrieve detailed information about a specific team by its ID.

Get Current User

Tool to retrieve information about the current authenticated user.

List Connections

List the connections belonging to a Make team.

List Enums Countries

Retrieve all supported countries in Make.

List Enums Languages

Tool to retrieve a list of language codes and names.

List Enums LLM Builtin Tiers

Retrieve all predefined LLM tiers (small, medium, large) with their associated models, providers, and pricing coefficients.

List Enums Locales

Retrieve all supported locales in Make.

List Enums Timezones

Retrieve all supported timezones in Make.

List Hook Logs

List safe summary metadata for a Make webhook's retained execution logs.

List Incomplete Executions

List failed or unfinished executions for a Make scenario.

List Organizations

Tool to list organizations the authenticated user belongs to (including organizationId, name, and timezoneId).

List Public Templates

Browse public approved Make templates with filters and offset pagination.

List Scenarios

List scenarios belonging to a Make team with offset pagination.

List Teams

Tool to list all teams within an organization.

Ping API

Tool to ping the Make API to verify connectivity and service availability.

Run Scenario

Run an already active Make scenario, executing its configured automation and external effects.

Set SDK Connection API

Replace the complete API definition for a Make SDK app connection.

Update Scenario

Partially update a Make scenario, leaving omitted properties unchanged; optionally authorize installation of an app newly used by the organization.

Update Scenario Interface

Replace an on-demand scenario's input specification; requires Make Pro+.

Verify Connection

Test whether a Make connection's saved credentials can reach its provider.

FRAMEWORKS

How to build Make MCP Agent with another framework

Claude Code

Use Make MCP with Claude Code

Cursor

Use Make MCP with Cursor

ChatGPT

Use Make MCP with ChatGPT

Claude Cowork

Use Make MCP with Claude Cowork

Antigravity

Use Make MCP with Antigravity

OpenAI Agents SDK

Use Make MCP with OpenAI Agents SDK

Claude Agent SDK

Use Make MCP with Claude Agent SDK

Codex

Use Make MCP with Codex

Kimi Code

Use Make MCP with Kimi Code

Grok Build

Use Make MCP with Grok Build

VS Code

Use Make MCP with VS Code

OpenCode

Use Make MCP with OpenCode

OpenClaw

Use Make MCP with OpenClaw

Hermes

Use Make MCP with Hermes

Atomic Agent

Use Make MCP with Atomic Agent

CLI

Use Make MCP with CLI

Google ADK

Use Make MCP with Google ADK

LangChain

Use Make MCP with LangChain

Vercel AI SDK

Use Make MCP with Vercel AI SDK

Mastra AI

Use Make MCP with Mastra AI

LlamaIndex

Use Make MCP with LlamaIndex

CrewAI

Use Make MCP with CrewAI

Pydantic AI

Use Make MCP with Pydantic AI

MORE TOOLKITS

Explore Other Toolkits

Toolkit marketplace

0CodeKit

Api Key

0CodeKit is a utility API platform for AI, document, image, and data workflows. Use it to convert, validate, generate, store, and automate data without custom backend code.

Airtop

Api Key

Airtop is a cloud browser platform for AI-powered web automation. Use it to navigate sites, extract data, and run reusable browser workflows.

Apify MCP

Dcr Oauth

Apify MCP is the official MCP server for Apify's web scraping and browser automation platform. Use it to run actors, collect structured web data, and automate crawling workflows.

Apilio

Api KeyBasic

Apilio is a home automation platform that lets you connect and control smart devices from different brands. It helps you build flexible automations with complex conditions, schedules, and integrations.

FAQ

Frequently asked questions

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

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

Start with Make.It takes 30 seconds.

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

Start building

How to integrate Make MCP with Autogen

Connect Make without auth hassles

Introduction

Also integrate Make with

TL;DR

What is AutoGen?

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

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

What is Composio SDK?

How the Composio SDK works

Step-by-step Guide

Prerequisites

Getting API Keys for OpenAI and Composio

Install dependencies

Set up environment variables

Import dependencies and create Tool Router session

Configure MCP parameters for Autogen

Create the model client and agent

Run the interactive chat loop

Complete Code

Conclusion

Supported Tools

How to build Make MCP Agent with another framework

Claude Code

Cursor

ChatGPT

Claude Cowork

Antigravity

OpenAI Agents SDK

Claude Agent SDK

Codex

Kimi Code

Grok Build

VS Code

OpenCode

OpenClaw

Hermes

Atomic Agent

CLI

Google ADK

LangChain

Vercel AI SDK

Mastra AI

LlamaIndex

CrewAI

Pydantic AI

Explore Other Toolkits

0CodeKit

Airtop

Apify MCP

Apilio

Frequently asked questions

What are the differences in Tool Router MCP and Make MCP?+

Can I use Tool Router MCP with Autogen?+

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

How safe is my data with Composio Tool Router?+

Start with Make.It takes 30 seconds.