How to Use the Docker Hub MCP in Google ADK

Q: How do I configure Docker Hub tool filtering in Google ADK?

Pass a list of allowed tool names to your McpToolset initialization. This lets you expose safe tools like listtags while hiding destructive actions like deleterepository from the Gemini agent.

Q: Can Gemini analyze Docker Hub image digests with Google ADK?

Yes. Gemini uses gettag to retrieve the exact image digest, which it can then compare against your Google Kubernetes Engine deployment manifests to check for drift.

Let Gemini query your Docker Hub registry directly alongside your BigQuery and Vertex AI workflows in Google ADK.

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 Google ADK

Create your Vinkius account to connect Docker Hub to Google ADK 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 Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Analyze Docker Hub image metrics in Google ADK

`list_repositories` retrieves your image metadata, including pull counts, star counts, and last updated dates, directly into your Gemini agent. The tool outputs clean registry data that your agent can feed into BigQuery for automated usage analytics. This allows your enterprise agent to track image popularity and build trends across your entire organization. By passing this toolset into your `LlmAgent`, Gemini uses its massive context window to correlate registry activity with your Google Cloud deployment logs.

Verify release tags using this Google ADK MCP Server

`get_tag` fetches the specific size, digest, and last pushed date for any image tag in your repository. The tool provides the exact cryptographic hash of your build, giving Gemini the precise data it needs to verify deployment integrity. This prevents your agent from deploying unverified or modified images to your GKE clusters. When combined with `search_repositories`, your agent can discover public base images, check their latest digests, and recommend updates for your internal Dockerfiles.

Controlled repository updates in enterprise pipelines

`update_repository` modifies your repository descriptions and privacy settings directly from your Python agent. The tool allows Gemini to automate registry housekeeping, such as marking legacy repositories as private. You keep control by passing a `tool_names` filter to your `McpToolset` to limit what the agent can modify. If you want to prevent Gemini from using `delete_repository`, simply omit it from the allowed tools list.

Setup guide

Set up Docker Hub MCP in Google ADK

Prerequisites

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

1

Install Google ADK

Run pip install google-adk to install the Agent Development Kit. MCP support is included via the McpToolset class.
2

Connect via SSE transport

Use McpToolset.from_server() with SseServerParams pointing to your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Create an LlmAgent

Pass the returned mcp_tools list directly to LlmAgent(tools=mcp_tools). The ADK maps each MCP tool to a native Gemini function call — no manual schema definitions required.
4

Run with any Gemini model

The agent works with any Gemini model (gemini-2.0-flash, gemini-2.5-pro, etc.). Copy the full example on the right to get started with Docker Hub tools in your ADK agent.

agent.py

from google.adk.agents import LlmAgent
from google.adk.tools.mcp_tool.mcp_toolset import McpToolset
from google.adk.tools.mcp_tool.mcp_session_manager import SseServerParams

# Connect to the MCP via SSE
mcp_tools, exit_stack = await McpToolset.from_server(
    connection_params=SseServerParams(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    )
)

# Create your agent with auto-discovered tools
agent = LlmAgent(
    name="Docker Hub_agent",
    model="gemini-2.0-flash",
    instruction="You have access to Docker Hub tools via MCP.",
    tools=mcp_tools,
)

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 Google ADK

Pass a list of allowed tool names to your `McpToolset` initialization. This lets you expose safe tools like `list_tags` while hiding destructive actions like `delete_repository` from the Gemini agent.

Yes. Gemini uses `get_tag` to retrieve the exact image digest, which it can then compare against your Google Kubernetes Engine deployment manifests to check for drift.

Yes. The MCP server supports both Stdio and Streamable HTTP transports, allowing you to run the server locally or connect to a managed Vinkius endpoint over secure HTTP.

Gemini's million-token context easily handles the raw JSON output from `list_tags`. It filters, sorts, and extracts the exact versions you need without running out of memory.

Your repository metadata and credentials are encrypted in transit and processed within a secure V8 isolate sandbox on Vinkius. The MCP server only returns the specific JSON payload required by tools like `get_repository`, ensuring no broad access to your registry is exposed.

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