How to Use the Docker Hub MCP in Pydantic AI

Q: How does Pydantic AI handle invalid Docker Hub MCP Server responses?

The framework validates the output of tools like getrepository against expected Pydantic models. If the schema doesn't match, it raises a validation error immediately, stopping the agent before it can execute bad code.

Q: Can I use the deprecated MCPServerHTTP for Docker Hub in Pydantic AI?

No. You should use the unified MCPToolset("http://...") class instead, which supports both Streamable HTTP and SSE transports for your managed Vinkius server.

Q: How do I pass Docker Hub tools to a Pydantic AI agent?

Initialize your MCPToolset with your Vinkius server URL, then pass it to the agent constructor using the toolsets parameter. This registers the MCP server tools like listrepositories and gettag automatically.

Q: Does this server support destructive tools like deleterepository?

Yes, the server exposes deleterepository. However, because this is an irreversible action, you should wrap your agent logic in a confirmation step before letting it call this tool.

Build type-safe registry pipelines with Pydantic AI and runtime schema validation for every Docker Hub tool.

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 Pydantic AI

Create your Vinkius account to connect Docker Hub to Pydantic AI 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 Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Validate Docker Hub image tags with Pydantic AI

`list_tags` returns structured data about image versions, which this framework validates against strict Pydantic schemas at runtime. The tool provides the tag name, image size, and digest. If the registry API returns an unexpected data format, the agent fails immediately instead of processing corrupted strings. This type-safety ensures that when your agent passes a tag to a deployment script, the version string is guaranteed to be valid.

Type-safe repository creation using this MCP Server

`create_repository` builds new repositories with strict validation on input arguments like namespace and visibility. The tool enforces type constraints before the API request is ever sent. If your agent attempts to pass an invalid namespace, the framework catches the error locally, saving you unnecessary API roundtrips. You register this capability by passing the MCP server toolset directly into your agent constructor.

Search and inspect repositories without silent errors

`search_repositories` queries Docker Hub for public images, parsing the results into validated Python models. The tool extracts pull counts and star counts so your agent can rank images by popularity. Because every field is typed, your agent can reliably sort results without hitting runtime attribute errors. If you need to verify credentials, `get_user` returns the authenticated user profile.

Setup guide

Set up Docker Hub MCP in Pydantic AI

Prerequisites

Python 3.10+ installed
pydantic-ai-slim[fastmcp] package
Active Vinkius subscription with a valid endpoint token

1

Install Pydantic AI with FastMCP
Run pip install "pydantic-ai-slim[fastmcp]". The FastMCP toolset replaces the deprecated MCPServerHTTP class with full protocol support.
2

Configure the FastMCPToolset
Pass a JSON-style config dict to FastMCPToolset with your Vinkius URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. Supports Streamable HTTP, SSE, and Stdio transports.
3

Create and run your agent
Pass the toolset to Agent(toolsets=[toolset]) and call agent.run(). Swap openai:gpt-4o for any supported model — Anthropic, Google, Mistral, or Groq.

agent.py

from pydantic_ai import Agent
from pydantic_ai.toolsets.fastmcp import FastMCPToolset

toolset = FastMCPToolset({
    "mcpServers": {
        "docker-hub-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

agent = Agent(
    "openai:gpt-4o",
    toolsets=[toolset],
    system_prompt="You have access to Docker Hub tools.",
)

result = await agent.run("List recent Docker Hub transactions")
print(result.output)

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 Pydantic AI

The framework validates the output of tools like `get_repository` against expected Pydantic models. If the schema doesn't match, it raises a validation error immediately, stopping the agent before it can execute bad code.

No. You should use the unified `MCPToolset("http://...")` class instead, which supports both Streamable HTTP and SSE transports for your managed Vinkius server.

Initialize your `MCPToolset` with your Vinkius server URL, then pass it to the agent constructor using the `toolsets` parameter. This registers the MCP server tools like `list_repositories` and `get_tag` automatically.

Yes, the server exposes `delete_repository`. However, because this is an irreversible action, you should wrap your agent logic in a confirmation step before letting it call this tool.

Your personal access token is stored securely in Vinkius environment variables and never exposed to the LLM. The server uses it solely to authenticate requests for tools like `list_organizations`, returning only the validated JSON payload to your local Python process.

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