How to Use the Hetzner MCP in Vercel AI SDK

Q: How does Vercel AI SDK handle Hetzner SSH keys?

You call listsshkeys to grab the IDs. The agent passes those IDs into the deployment payload when spinning up new hardware.

Build React dashboards that deploy Hetzner infrastructure live using the Vercel AI SDK.

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 Vercel AI SDK

Create your Vinkius account to connect Hetzner to Vercel AI 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 Vercel AI SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Stream raw provisioning data

The `create_server` tool connects your React frontend directly to Hetzner's provisioning API. Your users type a prompt, and the Vercel AI SDK streams the tool execution back to the browser. You don't build loading spinners. You show the raw JSON response as the server boots. Combine this with `list_server_types` and `list_locations` to build dynamic dropdowns. The agent fetches available hardware in Nuremberg or Ashburn, renders the options, and executes the build command the moment the user clicks submit.

Wire up networks via Hetzner MCP Server

The `create_firewall` tool lets your users define security rules through a natural language chat interface. They ask to open port 443, and the agent translates that into the exact API payload required. You can chain `list_networks` and `create_floating_ip` to build complex routing setups from a simple text prompt. The Vercel AI SDK handles the asynchronous tool calls, feeding the new IP addresses straight into your UI components without a page refresh.

Manage block storage from chat

The `create_volume` tool attaches block storage to running instances while the user watches the console output. You give your agent access to block devices, letting it format and mount drives based on plain English requests. When a user needs backups, the agent triggers `create_storage_box_snapshot`. It reads the current state using `get_storage_box` and confirms the snapshot ID back to the chat. Everything happens in one continuous stream.

Setup guide

Set up Hetzner MCP in Vercel AI SDK

Prerequisites

Node.js 18+ and a TypeScript project
ai + @modelcontextprotocol/sdk packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies

Run npm install ai @modelcontextprotocol/sdk plus your preferred model provider (e.g. @ai-sdk/openai).
2

Create the Streamable HTTP transport

Use StreamableHTTPClientTransport with your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Discover and use tools

Call mcpClient.tools() to auto-discover all Hetzner tools. Pass them directly to generateText() or streamText() — no manual schema definitions needed.
4

Works with any model provider

Swap openai("gpt-4o") for any AI SDK provider — Anthropic, Google, Mistral. The MCP tools work identically across all supported models.

index.ts

import { experimental_createMCPClient as createMCPClient } from "ai";
import { StreamableHTTPClientTransport } from "@modelcontextprotocol/sdk/client/streamableHttp";
import { generateText } from "ai";
import { openai } from "@ai-sdk/openai";

const transport = new StreamableHTTPClientTransport(
  new URL("https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp")
);

const mcpClient = await createMCPClient({ transport });
const tools = await mcpClient.tools();

const { text } = await generateText({
  model: openai("gpt-4o"),
  tools,
  prompt: "List recent Hetzner transactions",
});

console.log(text);
await mcpClient.close();

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 Vercel AI SDK

Run npm install ai @ai-sdk/mcp. Use createMCPClient with an HTTP transport pointing to your server URL. Pass the resulting tools into streamText to start building servers.

Yes. The agent calls the tool and Vercel AI SDK streams the progress chunks to your frontend. The user sees the deployment happen live.

You call list_ssh_keys to grab the IDs. The agent passes those IDs into the deployment payload when spinning up new hardware.

The MCP protocol catches the error from the API. Your Next.js error boundary intercepts the failed tool execution and renders a fallback UI.

No. The server only proxies requests for server IDs, firewall rules, and floating IPs. It runs in an ephemeral V8 sandbox that destroys memory after the request finishes.

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