How to Use the Hetzner MCP in Pydantic AI

Q: How do I initialize the Hetzner MCP Server using Pydantic AI?

Install the slim package with pip install "pydantic-ai-slimmcp" and use the unified MCPToolset pointing to your Vinkius HTTP endpoint. Pass this toolset directly to your Pydantic AI Agent to expose all 38 infrastructure tools.

Q: Is the MCPServerHTTP connection method deprecated in this setup?

Yes, the old MCPServerHTTP class is deprecated in Pydantic AI. You should use the unified MCPToolset class to connect to your externally running MCP endpoint for a cleaner and more stable integration.

Build type-safe Hetzner infrastructure agents with Pydantic AI to guarantee runtime validation on every server change.

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 Pydantic AI

Create your Vinkius account to connect Hetzner 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 Hetzner with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Type-safe Hetzner resource creation with Pydantic AI

Using `create_server`, Pydantic AI validates every single response from the Hetzner API against strict Python schemas before your agent even processes it. The Pydantic AI agent guarantees that no malformed data or unexpected API payloads can corrupt your Hetzner configuration. If the model attempts to call `create_server` with an invalid Hetzner server type, Pydantic AI raises a validation error immediately. This prevents your script from executing half-baked Hetzner deployments that waste your Hetzner cloud budget.

Validated firewall rules and security groups

By executing `create_firewall`, your Pydantic AI agent enforces strict security compliance across your entire Hetzner hosting environment. The framework validates your firewall rules at runtime to ensure your Hetzner ports match predefined security schemas. This means you can block your Pydantic AI agent from accidentally opening up Hetzner SSH ports to the entire internet. The Pydantic validation ensures that every Hetzner rule matches your exact Python type declarations before hitting the live API.

Reliable storage box subaccount provisioning via MCP Server

Through `create_storage_box_subaccount`, this MCP Server allows you to manage Hetzner backup storage with absolute structural confidence. The Pydantic AI framework ensures that the returned Hetzner credentials and subaccount details match your expected Python models. This eliminates the risk of unhandled null values or corrupted strings in your Pydantic AI backup pipelines. You get a bulletproof integration that fails loudly if Hetzner returns any unexpected API response.

Setup guide

Set up Hetzner 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": {
        "hetzner-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

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

result = await agent.run("List recent Hetzner 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 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 Pydantic AI

Install the slim package with `pip install "pydantic-ai-slim[mcp]"` and use the unified `MCPToolset` pointing to your Vinkius HTTP endpoint. Pass this toolset directly to your Pydantic AI `Agent` to expose all 38 infrastructure tools.

Yes, the framework validates all tool outputs at runtime. If the API returns unexpected Hetzner server states or fields, Pydantic AI raises a validation error, preventing silent data corruption.

Yes, this framework is model-agnostic. You can run your Pydantic AI agent using OpenAI, Anthropic, Gemini, or a local model while relying on the same type-safe tools to manage your Hetzner infrastructure.

Yes, the old `MCPServerHTTP` class is deprecated in Pydantic AI. You should use the unified `MCPToolset` class to connect to your externally running MCP endpoint for a cleaner and more stable integration.

All traffic goes through our V8 Isolate Sandbox, which enforces zero-trust access. Your firewall rules and server states are processed ephemerally, ensuring that sensitive configuration details are never cached or exposed to external threats.

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