How to Use the Docker Hub MCP in OpenAI Agents SDK

Q: How do I handle Docker Hub rate limits inside OpenAI Agents SDK?

Use the cacheToolsList=True parameter when defining your streamable HTTP server. This prevents the SDK from requesting the tool schema on every run, saving your API quota for actual calls like listtags and gettag.

Control your registry directly inside OpenAI Agents SDK pipelines with zero-config tool discovery and real-time safety guardrails.

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 OpenAI Agents SDK

Create your Vinkius account to connect Docker Hub to OpenAI Agents SDK 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 OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Inspect image tags directly from OpenAI Agents SDK

`list_tags` lets your OpenAI Agents SDK agent pull live version lists directly from your registry during execution. The tool returns the exact digest and size of each image tag. This means your agent reads real data from Docker Hub instead of guessing what's in your registry. Once initialized, the agent uses `get_repository` to verify image details before triggering deployments, eliminating mismatched image tags in your release pipelines.

Safe image repository creation with built-in guardrails

`create_repository` executes through your OpenAI Agents SDK agent only after passing your custom validation checks. The tool creates new repositories in your specified namespace or organization, setting visibility to public or private dynamically. Because the SDK tracks every tool call in the OpenAI developer dashboard, you inspect exactly when and why the agent spun up a new registry. If the agent tries to run `delete_repository`, your SDK guardrails intercept the call to prevent accidental data loss.

Audit team access using this Docker Hub MCP Server

`list_organizations` pulls the list of Docker Hub organizations associated with your active credentials. The tool returns names, creation dates, and account types to verify permissions. Your agent queries this metadata to ensure it operates within correct organization boundaries before performing write actions. This MCP Server integration allows your agent to self-correct when access tokens expire, logging clear connection errors directly to your OpenAI tracing dashboard.

Setup guide

Set up Docker Hub MCP in OpenAI Agents SDK

Prerequisites

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

1

Install the SDK

Run pip install openai-agents to install the OpenAI Agents SDK. The MCP integration is built-in — no extra dependencies needed.
2

Connect via SSE transport

Use MCPServerSse with your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. The SDK auto-discovers all Docker Hub tools at runtime.
3

Create your Agent

Pass the MCP to Agent(mcp_servers=[server]). The agent receives Docker Hub tools as native definitions — JSON schemas resolve automatically.
4

Run the agent

Call Runner.run(agent, prompt) to execute. The agent invokes the appropriate Docker Hub tools and returns structured results. Copy the full example on the right to get started.

agent.py

import asyncio
from agents import Agent, Runner
from agents.mcp import MCPServerSse

async def main():
    async with MCPServerSse(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ) as server:
        agent = Agent(
            name="Docker Hub Agent",
            instructions="You have access to Docker Hub tools.",
            mcp_servers=[server],
        )
        result = await Runner.run(agent, "List recent transactions")
        print(result.final_output)

asyncio.run(main())

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 OpenAI Agents SDK

Use the `cacheToolsList=True` parameter when defining your streamable HTTP server. This prevents the SDK from requesting the tool schema on every run, saving your API quota for actual calls like `list_tags` and `get_tag`.

Yes. You write a custom validation guardrail in Python that blocks destructive tools like `delete_repository` or `update_repository` before they execute, while leaving read-only tools like `list_repositories` open.

No. The SDK automatically discovers the schema for tools like `search_repositories` and maps them to Python structures. You just pass the server to your agent constructor and let auto-discovery handle the rest.

Define your MCP server once, then pass it to the specific agent that handles registry tasks. This allows a deployment agent to call `get_tag` while keeping your code-generation agents isolated from your production registry.

Vinkius hosts the server in a zero-trust, ephemeral sandbox where your personal access tokens never touch the LLM. The agent only receives the structured output of tools like `get_user` and `list_repositories`, keeping your raw authentication headers isolated from the model context.

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