How to Use the Hetzner MCP in OpenAI Agents SDK

Q: How do I add the Hetzner MCP Server to my OpenAI Agents SDK pipeline?

Install the package using pip install openai-agents and instantiate MCPServerStreamableHttp with your Vinkius endpoint URL. Pass this server instance in the mcpservers list to your OpenAI Agent constructor to let the model auto-discover all 38 Hetzner tools.

Q: How do I optimize tool discovery latency for Hetzner on OpenAI Agents SDK?

Set cacheToolsList=True in your connection parameters. This prevents the OpenAI agent from fetching the list of 38 Hetzner tools on every single request, which speeds up response times significantly.

Q: Can the OpenAI agent reboot or power cycle Hetzner instances?

Yes, the OpenAI agent can check the server state and call poweronserver to bring a machine back online. You just need to ensure your agent's system prompt allows it to execute Hetzner power state operations.

Spin up Hetzner Cloud infrastructure safely using OpenAI Agents SDK to manage servers and firewalls with production guardrails.

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 OpenAI Agents SDK

Create your Vinkius account to connect Hetzner 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 Hetzner with OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Secure Hetzner provisioning with OpenAI Agents SDK

Using the `create_network` tool, your OpenAI Agents SDK pipeline structures your Hetzner Cloud network without risking rogue API calls. By passing the Hetzner MCP Server to your OpenAI Agent constructor, the model automatically maps out how to bind virtual subnets. The OpenAI Agents SDK uses built-in safety guardrails to validate parameters before executing `create_firewall` on your Hetzner console. This ensures that your Hetzner environment isn't accidentally exposed to the public internet during automated OpenAI provisioning.

Automated server rebuilding and lifecycle management

With the `get_server` tool, your OpenAI Agents SDK agent can instantly initiate a recovery workflow when a Hetzner deployment fails. It queries the virtual machine's status directly from Hetzner to diagnose why the instance went offline before triggering the OpenAI recovery loop. Instead of manual intervention, the OpenAI agent handles the teardown and calls `rebuild_server` on the failing Hetzner node. This keeps your Hetzner application online while maintaining a clean, traceable log in your OpenAI dashboard.

Dynamic storage allocation via MCP Server

By calling `create_volume`, specialized OpenAI Agents SDK instances coordinate block storage needs during heavy Hetzner database runs. One OpenAI agent can monitor disk usage, while another attaches the extra volume directly to your Hetzner cloud instance. The OpenAI agent handles the handoff to a backup specialist that triggers `create_storage_box_snapshot` on your Hetzner storage box. This MCP integration lets you design hands-free, automated Hetzner storage operations with zero manual OpenAI configuration overhead.

Setup guide

Set up Hetzner 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 Hetzner tools at runtime.
3

Create your Agent

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

Run the agent

Call Runner.run(agent, prompt) to execute. The agent invokes the appropriate Hetzner 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="Hetzner Agent",
            instructions="You have access to Hetzner 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 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 OpenAI Agents SDK

Install the package using `pip install openai-agents` and instantiate `MCPServerStreamableHttp` with your Vinkius endpoint URL. Pass this server instance in the `mcp_servers` list to your OpenAI Agent constructor to let the model auto-discover all 38 Hetzner tools.

Yes, you can design specialized OpenAI agents that hand off tasks to each other. For instance, a networking agent can configure the IP space using `create_floating_ip`, then pass the context to a compute agent to spin up the actual Hetzner instance.

Set `cacheToolsList=True` in your connection parameters. This prevents the OpenAI agent from fetching the list of 38 Hetzner tools on every single request, which speeds up response times significantly.

Yes, the OpenAI agent can check the server state and call `poweron_server` to bring a machine back online. You just need to ensure your agent's system prompt allows it to execute Hetzner power state operations.

Vinkius runs the integration inside an isolated V8 sandbox, meaning your Hetzner API keys and server configurations are never exposed to the LLM or stored on persistent disks. All operations run in an ephemeral, zero-trust environment that only executes authorized API calls.

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