What are the requirements?
Python 3.11+ and a Hetzner Cloud API token are required.
@dkruyt
Basic information
A Model Context Protocol (MCP) server for interacting with the Hetzner Cloud API. This server allows language models to manage Hetzner Cloud resources through structured functions.
Add this server to your MCP-compatible client using the configuration below.
{
"mcpServers": {
"mcp-hetzner": {
"command": "python",
"args": [
"-m",
"mcp_hetzner"
]
}
}
}Tool list not available yet
This listing does not currently have a tool list to display. This does not mean the server has no tools; check its documentation for supported capabilities.
We auto-extract tools from the README. The maintainer can list them under a ## Tools heading to populate this section.
A Model Context Protocol (MCP) server that allows language models to manage Hetzner Cloud resources through structured functions. It integrates with the Hetzner Cloud API to manage servers, volumes, firewalls, SSH keys, and available infrastructure options.
Install via pip or clone the repository, then create a .env file with your HCLOUD_TOKEN. Run the server with mcp-hetzner (or python -m mcp_hetzner). It supports both stdio (default) and SSE transports, and can be connected to Claude Code for interactive management.
Python 3.11+ and a Hetzner Cloud API token are required.
Two modes: stdio (default, used with Claude Code) and SSE (Server-Sent Events, suitable for HTTP clients).
Yes, by setting the `MCP_HOST` and `MCP_PORT` environment variables or using the `--port` command line argument.
Start the server with SSE transport (`mcp-hetzner --transport sse --port 8080`) and then connect Claude Code using `claude-code --mcp-server localhost:8080`.

A good sequence diagram can solve almost any communication problem in engineering. Volley lets your agent write them as plain text, with the real request and response payloads on every arrow. It checks its own syntax wi

Run advanced phishing, voice phishing, deepfake fraud simulations, and cybersecurity awareness training from your AI assistant.

Handl speaks the Model Context Protocol. Your whole billing operation — projects, invoices, clients, reports, approvals — as tools any AI assistant can call, inside your autonomy rules.

See and control a real Windows PC you own — from any MCP client, locally or remotely. Observe (UIA + screenshots), click/type/drag/scroll, launch apps, owner Live View. BYOH: your machine, your key.
YC (S26) | Open Computer History | Continuously record your company computer work, map your workflows, help you find work worth automating, and power your agents' context
Comments