How to Use the Hetzner MCP in AutoGen

Q: How do I configure the Hetzner MCP Server in AutoGen?

Install autogen-extmcp. Use mcpservertools with a StreamableHttpServerParams pointing to Vinkius. Pass the resulting tool list directly into your AssistantAgent constructor.

Deploy multi-agent AutoGen teams to debate, plan, and execute Hetzner infrastructure changes.

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 AutoGen

Create your Vinkius account to connect Hetzner to AutoGen 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 AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Multi-Agent Hetzner Provisioning

The Hetzner MCP server gives your AutoGen swarms the ability to manipulate real cloud infrastructure. You assign `create_server` and `create_network` to an execution agent, while a separate security agent reviews the proposed architecture. They debate the deployment plan before writing a single line of state. This conversational approach prevents stupid mistakes. If the execution agent tries to spin up a node without proper SSH keys, the security agent flags the missing `create_ssh_key` step. They negotiate the fix, finalize the configuration, and then execute the API calls in the correct sequence.

Consensus-Driven Firewall Management

Network security requires strict oversight. Your AutoGen setup can feature a networking agent that pulls current rules via `list_firewalls` and proposes modifications. A compliance agent then checks those changes against your internal policies before allowing `create_firewall` to run. The agents handle the back-and-forth automatically. If a developer requests port 80 to be opened, the swarm discusses whether a load balancer is a better approach. They might decide to use `create_load_balancer` instead, routing traffic securely without exposing the raw compute nodes.

Automated Disaster Recovery Drills

Testing backups usually falls to the bottom of the priority list. You can build an AutoGen routine where agents simulate a failure, use `list_storage_box_snapshots` to find a recovery point, and spin up a clone using `rebuild_server`. They verify the recovery without human intervention. One agent acts as the chaos monkey, shutting down instances with `poweron_server` toggles. The recovery agent detects the outage via `get_server` and executes the runbook. You get a complete transcript of their conversation, proving your disaster recovery plan actually works.

Setup guide

Set up Hetzner MCP in AutoGen

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] package
Active Vinkius subscription with a valid endpoint token

1

Install AutoGen with MCP
Run pip install "autogen-ext[mcp]" autogen-agentchat. The MCP extension includes mcp_server_tools for stateless tool access.
2

Fetch tools from the MCP
Call mcp_server_tools(SseServerParams(url=...)) with your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Run your agent
Pass the tools to AssistantAgent and call agent.run(). The agent invokes Hetzner tools and returns structured results.

agent.py

from autogen_ext.tools.mcp import SseServerParams, mcp_server_tools
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

server_params = SseServerParams(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

tools = await mcp_server_tools(server_params)

agent = AssistantAgent(
    name="Hetzner_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

result = await agent.run("List recent Hetzner data")
print(result.messages[-1].content)

Get your connection token →

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] + autogen-agentchat
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Same packages as above. McpWorkbench is ideal when your agent needs stateful sessions across multiple tool calls.
2

Use McpWorkbench as context manager
Wrap your agent in async with McpWorkbench(...) to maintain shared state and resources. The workbench manages the full MCP session lifecycle.
3

Run with workbench
Pass workbench=workbench to your agent. State is preserved across multiple tool calls within the same session.

agent.py

from autogen_ext.tools.mcp import McpWorkbench, SseServerParams
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

server_params = SseServerParams(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

async with McpWorkbench(server_params) as workbench:
    agent = AssistantAgent(
        name="Hetzner_assistant",
        model_client=OpenAIChatCompletionClient(model="gpt-4o"),
        workbench=workbench,
    )

    result = await agent.run("List recent Hetzner data")
    print(result.messages[-1].content)

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 AutoGen

Install `autogen-ext[mcp]`. Use `mcp_server_tools` with a `StreamableHttpServerParams` pointing to Vinkius. Pass the resulting tool list directly into your `AssistantAgent` constructor.

You assign the tools to specific agents based on their roles. The `McpToolAdapter` handles the schema conversion, letting your infrastructure agent call `create_volume` while your auditor agent only gets access to `list_volumes`.

The agents read the error responses returned by the MCP server. If a request to `list_servers` hits a limit, the agents discuss the failure, apply a backoff strategy, and retry the operation automatically.

Yes. Your swarm can manage persistent storage completely. Agents can call `create_storage_box_subaccount` for new employees or use `update_storage_box` to toggle specific file sharing protocols as needed.

The agents never see your actual API tokens. They interact with infrastructure data like primary IPs, load balancer states, and volume attachments through Vinkius. The platform handles authentication externally via a secure, stateless proxy layer.

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