How to Use the Hetzner MCP in LangChain

Q: How do I connect the Hetzner MCP Server to LangChain?

Install langchain-mcp-adapters and langgraph. Initialize a MultiServerMCPClient pointing to your Vinkius endpoint URL. Then call client.gettools() to bind the Hetzner commands to your ReAct agent.

Q: Can LangChain agents modify my Hetzner firewalls?

Yes. Your agent can execute createfirewall and listfirewalls to audit or apply new rules. You control exactly which tools the agent has access to during the setup phase.

Connect your Hetzner infrastructure to LangChain agents to build automated, multi-step provisioning pipelines.

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 LangChain

Create your Vinkius account to connect Hetzner to LangChain 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 LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Automate Hetzner Deployments in LangChain

The Hetzner MCP server exposes 38 distinct infrastructure primitives to your LangChain agents. You build multi-step pipelines where an agent decides to check availability with `list_locations`, provisions compute using `create_server`, and then immediately secures it via `create_firewall`. Every action chains together naturally without manual intervention. Because LangChain excels at sequential logic, your agent uses the output of one tool as the input for the next. It grabs the new server's IP address and automatically configures a DNS record using `create_zone`. You track the entire provisioning execution, including token usage and exact API latency, straight through LangSmith.

Scripted Storage Box Management

Storage management requires careful sequencing, which fits perfectly into LangGraph workflows. Your agent monitors capacity and triggers `update_storage_box` to toggle protocols like WebDAV or SMB when specific conditions hit. It handles the mundane maintenance tasks so your team avoids manual dashboard clicks. You can also chain snapshot routines. A scheduled LangChain script calls `create_storage_box_snapshot` before executing risky server updates via `rebuild_server`. If a deployment fails, the agent has the context to rollback or alert a human, keeping your disaster recovery process strictly codified.

Dynamic Load Balancer Scaling

Traffic spikes demand immediate infrastructure adjustments. Your ReAct agent polls current instances with `list_servers` and spins up additional capacity if thresholds exceed your limits. Once the new nodes boot, the agent executes `create_load_balancer` to distribute the incoming requests across the expanded pool. Scaling down works exactly the same way. When traffic drops, the agent safely drains connections and calls `delete_load_balancer` followed by `delete_server`. You stop paying for idle compute resources, and the LangChain integration ensures the tear-down happens without orphan records left behind.

Setup guide

Set up Hetzner MCP in LangChain

Prerequisites

Python 3.10+ installed
langchain-mcp-adapters + langgraph packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install langchain-mcp-adapters langgraph langchain-openai. The MCP adapters package converts MCP tools into native LangChain BaseTool objects.
2

Connect via HTTP transport
Use MultiServerMCPClient with "transport": "http" pointing to your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Create a ReAct agent
Pass the discovered tools to create_react_agent() from LangGraph. The agent automatically routes Hetzner tool calls through the MCP protocol.
4

Run with any LLM
Swap ChatOpenAI for ChatAnthropic, ChatGoogleGenerativeAI, or any LangChain-compatible model. The MCP tools work identically across all providers.

agent.py

from langchain_mcp_adapters.client import MultiServerMCPClient
from langgraph.prebuilt import create_react_agent
from langchain_openai import ChatOpenAI

async with MultiServerMCPClient({
    "hetzner-mcp": {
        "transport": "http",
        "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp",
    }
}) as client:
    tools = client.get_tools()

    agent = create_react_agent(
        ChatOpenAI(model="gpt-4o"),
        tools,
    )
    result = await agent.ainvoke({
        "messages": "List recent Hetzner transactions"
    })
    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 LangChain

Install `langchain-mcp-adapters` and `langgraph`. Initialize a `MultiServerMCPClient` pointing to your Vinkius endpoint URL. Then call `client.get_tools()` to bind the Hetzner commands to your ReAct agent.

Yes. Your agent can execute `create_firewall` and `list_firewalls` to audit or apply new rules. You control exactly which tools the agent has access to during the setup phase.

Every tool invocation logs directly to LangSmith. You see the exact payload sent to `create_server` and the raw JSON response returned by the Hetzner API. This makes debugging failed infrastructure builds straightforward.

You handle project isolation by passing different Vinkius endpoint tokens to separate `MultiServerMCPClient` configurations. The agent routes requests to the correct environment based on your chain's logic.

The integration accesses server IPs, SSH keys, firewall rules, and storage box configurations. Vinkius executes these requests inside an ephemeral V8 Isolate sandbox, meaning your raw credentials never touch the LangChain runtime directly.

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