How to Use the Docker Hub MCP in CrewAI

Q: Can a CrewAI agent create private repositories on Docker Hub?

Yes, the createrepository tool accepts a private visibility flag. Your agent simply sets the visibility argument to private when executing the tool. This prevents accidental public exposure of internal proprietary images.

Q: Can I restrict a specific agent to read-only tools?

You restrict access by using the toolfilter option in CrewAI's HTTP client setup. This lets you expose safe tools like listtags to your research agents while blocking destructive tools. Your deployment pipeline stays safe from accidental deletions.

Give your CrewAI agent teams direct control to search, inspect, and manage Docker Hub repositories without manual intervention.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Docker Hub MCP to CrewAI

Create your Vinkius account to connect Docker Hub to CrewAI and route execution through our secure gateway. The platform manages server hosting, runtime updates, and security layers. Configuration requires no manual server provisioning.

GDPR Free for Subscribers

Setup Docker Hub with CrewAI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Let CrewAI agents clean up old tags

`list_tags` gives your release agent the exact list of image digests and creation dates directly from your registry. The agent checks this data against your retention policy to find stale builds. Once identified, the agent passes the targets to a cleanup agent. That agent uses `delete_repository` or updates metadata to keep your storage footprint lean.

Automate repository creation in CrewAI pipelines

`create_repository` lets a provisioning agent set up a new public or private namespace the second a new microservice gets approved. You don't have to click through the web UI or write custom bash scripts anymore. A separate QA agent then uses `get_repository` to verify the settings before the build pipeline kicks off. This team coordination keeps your registry structured without human gatekeepers.

Build autonomous registry monitor MCP Server squads

`list_repositories` allows a monitor agent to pull all active images under your namespace on a set schedule. The agent counts stars and pulls to track usage trends. If a repository shows zero activity, a moderator agent uses `update_repository` to toggle its visibility or archive it. This workflow runs entirely in the background while your team focuses on writing code.

Setup guide

Set up Docker Hub MCP in CrewAI

Prerequisites

Python 3.10+ installed
crewai package (pip install crewai)
Active Vinkius subscription with a valid endpoint token

1

Install CrewAI
Run pip install crewai to install the framework. MCP support is built-in via the mcps parameter.
2

Add the MCP URL to your agent
Pass your Vinkius endpoint directly to the mcps list. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. CrewAI handles tool discovery and caching automatically.
3

Kick off your crew
Create a Crew with your agent and tasks. Call crew.kickoff() — the agent will automatically invoke Docker Hub tools as needed.

crew.py

from crewai import Agent, Task, Crew

agent = Agent(
    role="Docker Hub Analyst",
    goal="Access and analyze Docker Hub data via MCP.",
    backstory="Expert analyst with direct Docker Hub access.",
    mcps=[
        "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ],
)

task = Task(
    description="List recent Docker Hub transactions",
    agent=agent,
    expected_output="A summary of recent activity",
)

crew = Crew(agents=[agent], tasks=[task])
result = crew.kickoff()
print(result)

Get your connection token →

Prerequisites

Python 3.10+ installed
crewai + crewai-tools packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install crewai crewai-tools. The MCPServerAdapter handles lifecycle management and tool conversion.
2

Connect with MCPServerAdapter
Use MCPServerAdapter as a context manager with SseServerParameters pointing to your Vinkius endpoint. The adapter automatically manages connection lifecycle.
3

Assign tools and run
Pass the returned mcp_tools to your agent's tools parameter. The adapter converts MCP tools to native BaseTool objects compatible with all CrewAI agents.

crew.py

from crewai import Agent, Task, Crew
from crewai_tools import MCPServerAdapter
from mcp import SseServerParameters

server_params = SseServerParameters(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

with MCPServerAdapter(server_params) as mcp_tools:
    agent = Agent(
        role="Docker Hub Analyst",
        goal="Access and analyze Docker Hub data via MCP.",
        backstory="Expert analyst with direct Docker Hub access.",
        tools=mcp_tools,
    )

    task = Task(
        description="List recent Docker Hub transactions",
        agent=agent,
        expected_output="A summary of recent activity",
    )

    crew = Crew(agents=[agent], tasks=[task])
    result = crew.kickoff()
    print(result)

Get your connection token →

Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by Docker Hub. All third-party trademarks, logos, and brand names are the property of their respective owners. Their use on this website is strictly for informational purposes to identify service compatibility and interoperability.

Why Choose Vinkius

Vinkius connects your tools to AI with real-time monitoring and automatic cost savings — all from one dashboard.

Connect Docker Hub now

Real-time monitoring

Live

visibility into every interaction

Connect your favorite tools to your AI and see exactly what's happening — every request, every response, in real time.

Built-in savings

60%

lower AI costs

Vinkius compresses data between your apps and your AI automatically. Lower bills every month — no configuration required.

Single dashboard

One

place for every integration

Every tool your AI connects to, managed from a single screen. One account, complete control.

Common questions about Docker Hub MCP in CrewAI

Pass the Vinkius SSE URL directly into your CrewAI agent configuration using the MCP server list. If you need fine-grained control, import `MCPServerHTTP` from the CrewAI MCP module in your Python script. This lets you filter which tools your specific agents can access.

Yes, the `create_repository` tool accepts a private visibility flag. Your agent simply sets the visibility argument to private when executing the tool. This prevents accidental public exposure of internal proprietary images.

Your agents will receive standard HTTP 429 status codes if they hit rate limits during operations like `search_repositories`. You must configure your CrewAI tasks with backoff retry logic to handle these API limits. The MCP server passes the raw API errors straight back to your executing agent.

You restrict access by using the `tool_filter` option in CrewAI's HTTP client setup. This lets you expose safe tools like `list_tags` to your research agents while blocking destructive tools. Your deployment pipeline stays safe from accidental deletions.

Vinkius runs this server inside an isolated, zero-trust V8 sandbox where your API credentials never touch disk. Only metadata like repository names and image tags pass through to your agent during execution. Your main account password is never stored or exposed to the LLM.

Use it with your favorite AI tools

Connect this server to Cursor, Claude, VS Code, and more.

OpenAI Agents SDK sdk-python

Google ADK sdk-python

Pydantic AI sdk-python

Vercel AI SDK sdk-typescript