SIGN UPLOG IN
X (Twitter)LinkedInGitHubDiscordYouTube

How to integrate Docker hub MCP with Autogen

Connect Autogen to Docker hub MCP. Create a new docker hub repository, add a member to your docker organization, and more using natural language, with authentication handled for you.

Get started for freeGet a demo
Docker hub logoDocker hub
Api Key

Docker Hub is a cloud-based registry for finding and sharing container images. It simplifies container collaboration and deployment for individuals and teams.

24 Tools

Introduction

This guide walks you through connecting Docker hub to AutoGen using the Composio tool router. By the end, you'll have a working Docker hub agent that can create and delete repositories, inspect images and tags, manage organizations and teams, and set up webhooks through natural language commands.

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

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

For exact tool slugs and parameter tables, see the tool catalog in the Composio docs.

Also integrate Docker hub with

Claude CodeClaude CoworkOpenAI Agents SDKClaude Agent SDKGrok BotCodexOpenClawHermesAtomic AgentGoogle ADKLangChainVercel AI SDKMastra AILlamaIndexCrewAIPydantic AI

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

The Docker hub MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Docker Hub account. It provides structured and secure access to your container repositories and organizations, so your agent can perform actions like creating repositories, managing organization members, deleting images, setting up webhooks, and cleaning up tags on your behalf.

  • Repository and image management: Let your agent create new Docker Hub repositories, delete existing ones, and remove specific images or tags as needed.
  • Organization and team automation: Easily add members to organizations, create new Docker Hub organizations, or delete organizations and teams directly from your workflows.
  • Webhook configuration: Set up or remove repository webhooks to automate external integrations and keep your CI/CD pipelines in sync.
  • Tag and resource cleanup: Direct your agent to delete outdated tags or unused resources, helping you maintain a tidy container registry.
  • Secure role management: Invite users with specific roles to your organizations, ensuring the right access for collaborators and teams.

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

Supported Tools

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

Add Organization Member

Invite a user to join a Docker Hub organization.

Create Docker Hub Organization

Create a new Docker Hub organization.

Create Docker Hub Repository

Creates a new Docker Hub repository under the specified namespace.

Create Docker Hub Webhook

Create a webhook on a Docker Hub repository for image push notifications, then add its hook URL; repository admin permissions are required.

Delete Repository Images

Delete up to 100 image manifests from a Docker Hub namespace by repository and SHA256 digest, or use a dry run to validate the request without deleting.

Delete Docker Hub Organization

Permanently deletes a Docker Hub organization.

Delete Docker Hub Repository

Permanently delete a Docker Hub repository and its images, tags, and metadata.

Delete Repository Tag

Permanently delete a specific tag from a Docker Hub repository.

Delete Docker Hub Team

Permanently deletes a team from a Docker Hub organization.

Delete Docker Hub repository webhook

Deletes a specific webhook from a Docker Hub repository.

Get Docker Hub Image

Retrieve a platform-specific image variant by digest by searching repository tags.

Get Docker Hub Repository

Retrieve detailed metadata for a Docker Hub repository, including available description, counts, permissions, and configuration.

Get Docker Hub Tag

Retrieve details of a specific Docker Hub repository tag by namespace, repository, and tag name.

Get Docker Hub Team

Retrieve details of a specific team (group) within a Docker Hub organization.

Get Docker Hub Webhook

Retrieves details of a specific Docker Hub webhook by its ID.

List Organization Access Tokens

List a page of organization access tokens for a Docker Hub organization, with pagination.

List Docker Hub Organizations

List Docker Hub organizations associated with the authenticated user, with available organization details in paginated results.

List Docker Hub Organization Members

List members of a Docker Hub organization with available roles and details, using paginated results.

List Docker Hub Repositories

List repositories under a Docker Hub namespace with optional filtering and pagination.

List Team Members

List members of a Docker Hub team (group) within an organization, returning paginated user details.

List Organization Teams

List all teams (groups) within a Docker Hub organization.

List Docker Hub repository webhooks

List webhooks configured for a Docker Hub repository, returning paginated configuration details.

Remove Organization Member

Remove a member from a Docker Hub organization.

Remove Team Member

Remove a user from a Docker Hub organization team (group), revoking that team membership.

FRAMEWORKS

How to build Docker hub MCP Agent with another framework

Claude Code logo

Claude Code

Use Docker hub MCP with Claude Code

Claude Cowork logo

Claude Cowork

Use Docker hub MCP with Claude Cowork

OpenAI Agents SDK logo

OpenAI Agents SDK

Use Docker hub MCP with OpenAI Agents SDK

Claude Agent SDK logo

Claude Agent SDK

Use Docker hub MCP with Claude Agent SDK

Grok Bot logo

Grok Bot

Use Docker hub MCP with Grok Bot

Codex logo

Codex

Use Docker hub MCP with Codex

OpenClaw logo

OpenClaw

Use Docker hub MCP with OpenClaw

Hermes logo

Hermes

Use Docker hub MCP with Hermes

Atomic Agent logo

Atomic Agent

Use Docker hub MCP with Atomic Agent

Google ADK logo

Google ADK

Use Docker hub MCP with Google ADK

LangChain logo

LangChain

Use Docker hub MCP with LangChain

Vercel AI SDK logo

Vercel AI SDK

Use Docker hub MCP with Vercel AI SDK

Mastra AI logo

Mastra AI

Use Docker hub MCP with Mastra AI

LlamaIndex logo

LlamaIndex

Use Docker hub MCP with LlamaIndex

CrewAI logo

CrewAI

Use Docker hub MCP with CrewAI

Pydantic AI logo

Pydantic AI

Use Docker hub MCP with Pydantic AI

FAQ

Frequently asked questions

Start with Docker hub.It takes 30 seconds.

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

Start building