How to Use the Hetzner MCP in Google ADK

Q: How do I configure Google ADK to connect to the Hetzner MCP Server?

Install the package via pip install google-adk and set up an McpToolset pointing to your Vinkius HTTP endpoint. Pass this toolset to your LlmAgent instance to give Gemini direct access to the Hetzner infrastructure tools.

Q: Can I restrict which Hetzner tools are exposed to Google ADK?

Yes, you can use the optional toolnames filter when initializing your McpToolset in Google ADK. This lets you restrict the Gemini agent to harmless read-only tools like listlocations while blocking destructive actions.

Deploy and scale Hetzner infrastructure using Google ADK to drive Gemini models with massive context windows.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Hetzner MCP to Google ADK

Create your Vinkius account to connect Hetzner 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 Hetzner with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Drive Hetzner deployments using Google ADK and Gemini

Using `list_servers`, your Google ADK agent parses your Hetzner setup to retrieve active footprint metrics and feed them into Gemini. The Gemini model uses this MCP Server to hold your entire Hetzner infrastructure history in its million-token context window. Once the Google ADK plan is ready, the Gemini model directly executes `create_server` to spin up matching Hetzner nodes. It does this without losing track of your historical Hetzner deployment patterns or Vertex AI system architecture constraints.

Enterprise load balancing and network isolation

By invoking `create_load_balancer`, your Google ADK agent monitors traffic trends to scale your Hetzner hosting footprint. This allows Gemini to analyze real-time BigQuery data pipelines and trigger infrastructure adjustments on Hetzner instantly. To keep backend systems secure, the Google ADK agent isolates Hetzner database nodes by calling `create_network`. This keeps your enterprise data flow clean and compliant with both Google Cloud and Hetzner security policies.

Automated DNS and domain routing via MCP Server

With `create_zone`, your Google ADK agent manages your public routing table based on real-time Hetzner service health checks. The Gemini model updates your Hetzner DNS records in seconds, ensuring your users never hit a dead endpoint. This integration allows you to build completely self-healing Hetzner deployments using Google ADK without writing custom DNS update scripts. You can restrict these automated routing actions by applying a `tool_names` filter to your Google ADK setup.

Setup guide

Set up Hetzner 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 Hetzner 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="Hetzner_agent",
    model="gemini-2.0-flash",
    instruction="You have access to Hetzner 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 Hetzner Cloud. 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 Hetzner 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 Hetzner MCP in Google ADK

Install the package via `pip install google-adk` and set up an `McpToolset` pointing to your Vinkius HTTP endpoint. Pass this toolset to your `LlmAgent` instance to give Gemini direct access to the Hetzner infrastructure tools.

Yes, you can use the optional `tool_names` filter when initializing your `McpToolset` in Google ADK. This lets you restrict the Gemini agent to harmless read-only tools like `list_locations` while blocking destructive actions.

Yes, the Google ADK framework supports both transport methods. For cloud-hosted environments, the HTTP transport is recommended as it connects directly to your managed MCP endpoint without local process overhead.

Gemini can ingest massive logs, system architectures, and current resource lists returned by `list_servers`. It holds this context to make highly informed decisions when executing configuration changes on Hetzner.

Vinkius processes all requests in an ephemeral V8 Isolate Sandbox. Your DNS zones and storage box credentials are never stored on disk, and the zero-trust architecture ensures that only authorized Gemini calls reach the API.

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