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.
What is dkruyt mcp hetzner
Hetzner Cloud MCP Server
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.
!MCP Hetzner Demo
Features
- List, create, and manage Hetzner Cloud servers
- Create, attach, detach, and resize volumes
- Manage firewall rules and apply them to servers
- Create and manage SSH keys for secure server access
- View available images, server types, and locations
- Power on/off and reboot servers
- Simple, structured API for language model interaction
- Claude Code integration for managing Hetzner resources directly from Claude
Requirements
- Python 3.11+
- Hetzner Cloud API token
Installation
Method 1: Direct Installation
- Clone this repository:
git clone https://github.com/dkruyt/mcp-hetzner.git
cd mcp-hetzner
- Install dependencies:
pip install -e .
- Create a
.env
file and add your Hetzner Cloud API token:
HCLOUD_TOKEN=your_hetzner_cloud_api_token_here
Method 2: Install as a Package
# Install directly from the repository
pip install git+https://github.com/dkruyt/mcp-hetzner.git
After installing as a package, create a .env
file in your working directory with your Hetzner Cloud API token.
Usage
Starting the Server
Option 1: Run the installed package:
# Using default stdio transport
mcp-hetzner
# Using SSE transport
mcp-hetzner --transport sse
# Setting a custom port
mcp-hetzner --transport sse --port 8000
Option 2: Run as a module:
python -m mcp_hetzner
# or
python -m mcp_hetzner.server
The server supports two transport modes:
stdio
(default): Standard I/O transport, typically used with Claude Codesse
: Server-Sent Events transport, suitable for HTTP clients
By default, the server runs on localhost:8080
. You can customize the host and port by:
- Setting the
MCP_HOST
andMCP_PORT
environment variables in your.env
file - Using the
--port
command line argument (overrides the environment variable)
Using with Claude Code
To use with Claude Code, run the server with SSE transport:
# Start the server with SSE transport
mcp-hetzner --transport sse --port 8080
# In another terminal, connect Claude Code to the server
claude-code --mcp-server localhost:8080
Testing the API
A test client is included to verify the server functionality:
python -m mcp_hetzner.client
Example Workflows
Basic Server Management
# List all your servers
list_servers
# Create a new server
create_server {
"name": "web-server",
"server_type": "cx11",
"image": "ubuntu-22.04"
}
# Power operations
power_off {"server_id": 12345}
power_on {"server_id": 12345}
reboot {"server_id": 12345}
# Delete a server when no longer needed
delete_server {"server_id": 12345}
Volume Management
# List all volumes
list_volumes
# Create a new volume
create_volume {
"name": "data-volume",
"size": 10,
"location": "nbg1",
"format": "ext4"
}
# Attach volume to a server
attach_volume {
"volume_id": 12345,
"server_id": 67890,
"automount": true
}
# Detach volume from server
detach_volume {
"volume_id": 12345
}
# Resize a volume (can only increase size)
resize_volume {
"volume_id": 12345,
"size": 50
}
# Delete a volume when no longer needed
delete_volume {
"volume_id": 12345
}
Firewall Management
# List all firewalls
list_firewalls
# Create a firewall for web servers
create_firewall {
"name": "web-firewall",
"rules": [
{
"direction": "in",
"protocol": "tcp",
"port": "80",
"source_ips": ["0.0.0.0/0", "::/0"]
},
{
"direction": "in",
"protocol": "tcp",
"port": "443",
"source_ips": ["0.0.0.0/0", "::/0"]
}
]
}
# Apply firewall to a server
apply_firewall_to_resources {
"firewall_id": 12345,
"resources": [
{
"type": "server",
"server_id": 67890
}
]
}
SSH Key Management
# List all SSH keys
list_ssh_keys
# Create a new SSH key
create_ssh_key {
"name": "my-laptop",
"public_key": "ssh-rsa AAAAB3NzaC1yc2EAAA... user@laptop"
}
# Use the SSH key when creating a server
create_server {
"name": "secure-server",
"server_type": "cx11",
"image": "ubuntu-22.04",
"ssh_keys": [12345]
}
# Update an SSH key's name
update_ssh_key {
"ssh_key_id": 12345,
"name": "work-laptop"
}
# Delete an SSH key
delete_ssh_key {
"ssh_key_id": 12345
}
Infrastructure Planning
# Explore available resources
list_server_types
list_images
list_locations
# Get specific server information
get_server {"server_id": 12345}
Available Functions
The MCP server provides the following functions:
Server Management
list_servers
: List all servers in your Hetzner Cloud accountget_server
: Get details about a specific servercreate_server
: Create a new serverdelete_server
: Delete a serverpower_on
: Power on a serverpower_off
: Power off a serverreboot
: Reboot a server
Volume Management
list_volumes
: List all volumes in your Hetzner Cloud accountget_volume
: Get details about a specific volumecreate_volume
: Create a new volumedelete_volume
: Delete a volumeattach_volume
: Attach a volume to a serverdetach_volume
: Detach a volume from a serverresize_volume
: Increase the size of a volume
Firewall Management
list_firewalls
: List all firewalls in your Hetzner Cloud accountget_firewall
: Get details about a specific firewallcreate_firewall
: Create a new firewallupdate_firewall
: Update firewall name or labelsdelete_firewall
: Delete a firewallset_firewall_rules
: Set or update firewall rulesapply_firewall_to_resources
: Apply a firewall to servers or server groupsremove_firewall_from_resources
: Remove a firewall from servers or server groups
SSH Key Management
list_ssh_keys
: List all SSH keys in your Hetzner Cloud accountget_ssh_key
: Get details about a specific SSH keycreate_ssh_key
: Create a new SSH keyupdate_ssh_key
: Update SSH key name or labelsdelete_ssh_key
: Delete an SSH key
Information
list_images
: List available OS imageslist_server_types
: List available server typeslist_locations
: List available datacenter locations
License
MIT
Leave a Comment
Frequently Asked Questions
What is MCP?
MCP (Model Context Protocol) is an open protocol that standardizes how applications provide context to LLMs. Think of MCP like a USB-C port for AI applications, providing a standardized way to connect AI models to different data sources and tools.
What are MCP Servers?
MCP Servers are lightweight programs that expose specific capabilities through the standardized Model Context Protocol. They act as bridges between LLMs like Claude and various data sources or services, allowing secure access to files, databases, APIs, and other resources.
How do MCP Servers work?
MCP Servers follow a client-server architecture where a host application (like Claude Desktop) connects to multiple servers. Each server provides specific functionality through standardized endpoints and protocols, enabling Claude to access data and perform actions through the standardized protocol.
Are MCP Servers secure?
Yes, MCP Servers are designed with security in mind. They run locally with explicit configuration and permissions, require user approval for actions, and include built-in security features to prevent unauthorized access and ensure data privacy.
Related MCP Servers
Brave Search MCP
Integrate Brave Search capabilities into Claude through MCP. Enables real-time web searches with privacy-focused results and comprehensive web coverage.
AWS Knowledge Base Retrieval
An MCP server implementation for retrieving information from the AWS Knowledge Base using the Bedrock Agent Runtime.
chrisdoc hevy mcp
sylphlab pdf reader mcp
An MCP server built with Node.js/TypeScript that allows AI agents to securely read PDF files (local or URL) and extract text, metadata, or page counts. Uses pdf-parse.
aashari mcp server atlassian bitbucket
Node.js/TypeScript MCP server for Atlassian Bitbucket. Enables AI systems (LLMs) to interact with workspaces, repositories, and pull requests via tools (list, get, comment, search). Connects AI directly to version control workflows through the standard MCP interface.
aashari mcp server atlassian confluence
Node.js/TypeScript MCP server for Atlassian Confluence. Provides tools enabling AI systems (LLMs) to list/get spaces & pages (content formatted as Markdown) and search via CQL. Connects AI seamlessly to Confluence knowledge bases using the standard MCP interface.
prisma prisma
Next-generation ORM for Node.js & TypeScript | PostgreSQL, MySQL, MariaDB, SQL Server, SQLite, MongoDB and CockroachDB
Zzzccs123 mcp sentry
mcp sentry for typescript sdk
zhuzhoulin dify mcp server
zhongmingyuan mcp my mac
Submit Your MCP Server
Share your MCP server with the community
Submit Now