How to integrate Ai ml api MCP with Autogen

This guide walks you through connecting Ai ml api to AutoGen using the Composio tool router. By the end, you'll have a working Ai ml api agent that can check if this image contains unsafe content, summarize this customer chat conversation, generate a polite reply to this message through natural language commands. This guide will help you understand how to give your AutoGen agent real control over a Ai ml api account through Composio's Ai ml api MCP server. Before we dive in, let's take a quick look at the key ideas and tools involved.

Get started for freeGet a demo
Ai ml api logoAi ml api
Api Key

Ai ml api is a suite of AI/ML models for natural language and image tasks. It provides fast, scalable access to advanced AI capabilities for your apps and workflows.

30 Tools

Introduction

This guide walks you through connecting Ai ml api to AutoGen using the Composio tool router. By the end, you'll have a working Ai ml api agent that can check if this image contains unsafe content, summarize this customer chat conversation, generate a polite reply to this message through natural language commands.

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

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

Also integrate Ai ml api with

OpenAI Agents SDKClaude Agent SDKClaude CodeClaude CoworkCodexOpenClawHermesCLIGoogle ADKLangChainVercel AI SDKMastra AILlamaIndexCrewAI

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

The Ai ml api MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Ai ml api account. It provides structured and secure access to powerful AI/ML models, so your agent can generate text, moderate user content, and automate intelligent workflows on your behalf.

  • Automated content moderation: Instantly classify and filter user-generated text or images using advanced moderation models to keep your platform safe and compliant.
  • Dynamic text generation: Have your agent generate chat responses, write creative copy, or complete conversations using state-of-the-art language models.
  • Context-aware conversation handling: Let your agent analyze conversation history and produce coherent, relevant replies for chatbots or digital assistants.
  • Seamless integration of AI workflows: Combine moderation and text generation tools to build smart, automated pipelines tailored to your product’s needs.

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

Supported Tools

Every Ai ml api action and event your agent gets out of the box.

Cancel Run

Tool to cancel a run that is currently in progress.

Create Assistant

Tool to create an AI assistant with configurable model, instructions, and tools.

Create Message

Tool to create a new message in a thread.

Create Run

Tool to create a run that executes an assistant on a thread.

Create Thread

Tool to create a new thread for conversation with an assistant.

Delete Assistant

Tool to delete an assistant by ID.

Delete Message

Tool to delete a specific message from a thread.

Delete Thread

Tool to delete a thread by its ID.

Get Assistant

Tool to retrieve details of a specific assistant by ID.

Get Billing Balance

Tool to retrieve the current billing balance for the account.

Get Luma Generation

Tool to fetch Luma AI video generation results by generation IDs.

Get Message

Tool to retrieve information about a specific message by its ID.

Get Response by ID

Tool to retrieve a previously generated model response by its unique ID.

Get Run

Tool to retrieve a specific run by ID from a thread.

Get Run Step

Tool to retrieve a specific run step by its ID within a thread and run.

Get Thread

Tool to retrieve information about a specific thread by ID.

List Assistants

Tool to list all assistants associated with the account.

List Batches

Tool to get the status or results of a batch processing job.

List Luma AI Generations

Tool to fetch user's Luma AI video generations.

List Thread Messages

Tool to retrieve a list of messages from a specific thread.

List Models

Tool to list all available AI models from the AI/ML API.

List Models With Details

Tool to list all available AI/ML models with detailed information including pricing, features, and capabilities.

List Runs

Tool to list all runs for a specific thread.

List Run Steps

Tool to list the steps in a run.

Submit Tool Outputs

Tool to submit tool outputs for a run that requires action.

Text Chat Completion

Tool to generate text completions or chat responses using a specified LLM model.

Update Assistant

Tool to modify an existing assistant's properties including name, instructions, model, and tools.

Update Message

Tool to modify metadata for a specific message in a thread.

Update Run

Tool to update a run's metadata with key-value pairs.

Update Thread

Tool to update thread metadata and tool resources in the AI/ML API.

FRAMEWORKS

How to build Ai ml api MCP Agent with another framework

OpenAI Agents SDK logo

OpenAI Agents SDK

Use Ai ml api MCP with OpenAI Agents SDK

Claude Agent SDK logo

Claude Agent SDK

Use Ai ml api MCP with Claude Agent SDK

Claude Code logo

Claude Code

Use Ai ml api MCP with Claude Code

Claude Cowork logo

Claude Cowork

Use Ai ml api MCP with Claude Cowork

Codex logo

Codex

Use Ai ml api MCP with Codex

OpenClaw logo

OpenClaw

Use Ai ml api MCP with OpenClaw

Hermes logo

Hermes

Use Ai ml api MCP with Hermes

CLI logo

CLI

Use Ai ml api MCP with CLI

Google ADK logo

Google ADK

Use Ai ml api MCP with Google ADK

LangChain logo

LangChain

Use Ai ml api MCP with LangChain

Vercel AI SDK logo

Vercel AI SDK

Use Ai ml api MCP with Vercel AI SDK

Mastra AI logo

Mastra AI

Use Ai ml api MCP with Mastra AI

LlamaIndex logo

LlamaIndex

Use Ai ml api MCP with LlamaIndex

CrewAI logo

CrewAI

Use Ai ml api MCP with CrewAI

FAQ

Frequently asked questions

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

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

Start with Ai ml api.It takes 30 seconds.

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

Start building
Customer stories

Teams ship real agents on Composio

GET STARTED FOR FREEBOOK A DEMO
agent.aiZoomLettaGleanHubSpotAWSWabi

Karan skipped his own birthday party to fix our critical issue. It was 10pm and he diverted his Waymo to help us instead. This really sets the bar — it shows the commitment you need when users rely on your software.

Harsha Gaddipati
Harsha Gaddipati
Co-founder, Slashy

A lot of students tell us that the moment their connected tools start talking to each other inside Opennote feels almost magical. The agent just knows them, and it's immensely helped keep new users on the platform.

Abhi Arya
Abhi Arya
Co-founder, Opennote

We chose Composio over Pipedream because it delivered depth where it mattered — niche tools and tricky edge cases other platforms simply ignored. That gave us confidence to scale without compromising.

Nirman Dave
Nirman Dave
CEO, Zams

As a solo builder, shipping fast is life or death. The only way I can outcompete incumbents is by outmanoeuvring them. Getting bogged down managing agent auth would have been a death sentence.

Ryan Yu
Ryan Yu
Founder, Extra Thursday

Before Composio, adding tool integrations was slow and resource-intensive. Each one could take weeks of engineering time, and maintaining them meant constantly keeping up with API changes.

Tomisin Jenrola
Tomisin Jenrola
Founder & CEO, SwarmZero

With hands-on help from their founder, we integrated Gmail and Google Drive in just 30 minutes. This level of personal support and commitment is exactly what startups should strive for.

Jerome Leclanche
Jerome Leclanche
Co-Founder, Ingram Technologies