A Python-based Model Context Protocol (MCP) server for interacting with Proxmox hypervisors, providing a clean interface for managing nodes, VMs, and containers.
- Cline - Autonomous coding agent - Go faster with Cline.
- Proxmoxer - Python wrapper for Proxmox API
- MCP SDK - Model Context Protocol SDK
- Pydantic - Data validation using Python type annotations
- π€ Full integration with Cline
- π οΈ Built with the official MCP SDK
- π Secure token-based authentication with Proxmox
- π₯οΈ Tools for managing nodes and VMs
- π» VM console command execution
- π Configurable logging system
- β Type-safe implementation with Pydantic
- π¨ Rich output formatting with customizable themes
Proxmox.Manager.Demo.mp4
- UV package manager (recommended)
- Python 3.10 or higher
- Git
- Access to a Proxmox server with API token credentials
Before starting, ensure you have:
- Proxmox server hostname or IP
- Proxmox API token (see API Token Setup)
- UV installed (
pip install uv
)
-
Clone and set up environment:
# Clone repository cd ~/Documents/Cline/MCP # For Cline users # OR cd your/preferred/directory # For manual installation git clone https://github.com/canvrno/ProxmoxMCP.git cd ProxmoxMCP # Create and activate virtual environment uv venv source .venv/bin/activate # Linux/macOS # OR .\.venv\Scripts\Activate.ps1 # Windows
-
Install dependencies:
# Install with development dependencies uv pip install -e ".[dev]"
-
Create configuration:
# Create config directory and copy template mkdir -p proxmox-config cp config/config.example.json proxmox-config/config.json
-
Edit
proxmox-config/config.json
:{ "proxmox": { "host": "PROXMOX_HOST", # Required: Your Proxmox server address "port": 8006, # Optional: Default is 8006 "verify_ssl": false, # Optional: Set false for self-signed certs "service": "PVE" # Optional: Default is PVE }, "auth": { "user": "USER@pve", # Required: Your Proxmox username "token_name": "TOKEN_NAME", # Required: API token ID "token_value": "TOKEN_VALUE" # Required: API token value }, "logging": { "level": "INFO", # Optional: DEBUG for more detail "format": "%(asctime)s - %(name)s - %(levelname)s - %(message)s", "file": "proxmox_mcp.log" # Optional: Log to file } }
-
Check Python environment:
python -c "import proxmox_mcp; print('Installation OK')"
-
Run the tests:
pytest
-
Verify configuration:
# Linux/macOS PROXMOX_MCP_CONFIG="proxmox-config/config.json" python -m proxmox_mcp.server # Windows (PowerShell) $env:PROXMOX_MCP_CONFIG="proxmox-config\config.json"; python -m proxmox_mcp.server
You should see either:
- A successful connection to your Proxmox server
- Or a connection error (if Proxmox details are incorrect)
- Log into your Proxmox web interface
- Navigate to Datacenter -> Permissions -> API Tokens
- Create a new API token:
- Select a user (e.g., root@pam)
- Enter a token ID (e.g., "mcp-token")
- Uncheck "Privilege Separation" if you want full access
- Save and copy both the token ID and secret
For testing and development:
# Activate virtual environment first
source .venv/bin/activate # Linux/macOS
# OR
.\.venv\Scripts\Activate.ps1 # Windows
# Run the server
python -m proxmox_mcp.server
For Cline users, add this configuration to your MCP settings file (typically at ~/.config/Code/User/globalStorage/saoudrizwan.claude-dev/settings/cline_mcp_settings.json
):
{
"mcpServers": {
"github.com/canvrno/ProxmoxMCP": {
"command": "/absolute/path/to/ProxmoxMCP/.venv/bin/python",
"args": ["-m", "proxmox_mcp.server"],
"cwd": "/absolute/path/to/ProxmoxMCP",
"env": {
"PYTHONPATH": "/absolute/path/to/ProxmoxMCP/src",
"PROXMOX_MCP_CONFIG": "/absolute/path/to/ProxmoxMCP/proxmox-config/config.json",
"PROXMOX_HOST": "your-proxmox-host",
"PROXMOX_USER": "username@pve",
"PROXMOX_TOKEN_NAME": "token-name",
"PROXMOX_TOKEN_VALUE": "token-value",
"PROXMOX_PORT": "8006",
"PROXMOX_VERIFY_SSL": "false",
"PROXMOX_SERVICE": "PVE",
"LOG_LEVEL": "DEBUG"
},
"disabled": false,
"autoApprove": []
}
}
}
To help generate the correct paths, you can use this command:
# This will print the MCP settings with your absolute paths filled in
python -c "import os; print(f'''{{
\"mcpServers\": {{
\"github.com/canvrno/ProxmoxMCP\": {{
\"command\": \"{os.path.abspath('.venv/bin/python')}\",
\"args\": [\"-m\", \"proxmox_mcp.server\"],
\"cwd\": \"{os.getcwd()}\",
\"env\": {{
\"PYTHONPATH\": \"{os.path.abspath('src')}\",
\"PROXMOX_MCP_CONFIG\": \"{os.path.abspath('proxmox-config/config.json')}\",
...
}}
}}
}}
}}''')"
Important:
- All paths must be absolute
- The Python interpreter must be from your virtual environment
- The PYTHONPATH must point to the src directory
- Restart VSCode after updating MCP settings
The server provides the following MCP tools for interacting with Proxmox:
Lists all nodes in the Proxmox cluster.
- Parameters: None
- Example Response:
π₯οΈ Proxmox Nodes π₯οΈ pve-compute-01 β’ Status: ONLINE β’ Uptime: β³ 156d 12h β’ CPU Cores: 64 β’ Memory: 186.5 GB / 512.0 GB (36.4%) π₯οΈ pve-compute-02 β’ Status: ONLINE β’ Uptime: β³ 156d 11h β’ CPU Cores: 64 β’ Memory: 201.3 GB / 512.0 GB (39.3%)
Get detailed status of a specific node.
- Parameters:
node
(string, required): Name of the node
- Example Response:
π₯οΈ Node: pve-compute-01 β’ Status: ONLINE β’ Uptime: β³ 156d 12h β’ CPU Usage: 42.3% β’ CPU Cores: 64 (AMD EPYC 7763) β’ Memory: 186.5 GB / 512.0 GB (36.4%) β’ Network: β¬οΈ 12.8 GB/s β¬οΈ 9.2 GB/s β’ Temperature: 38Β°C
List all VMs across the cluster.
- Parameters: None
- Example Response:
ποΈ Virtual Machines ποΈ prod-db-master (ID: 100) β’ Status: RUNNING β’ Node: pve-compute-01 β’ CPU Cores: 16 β’ Memory: 92.3 GB / 128.0 GB (72.1%) ποΈ prod-web-01 (ID: 102) β’ Status: RUNNING β’ Node: pve-compute-01 β’ CPU Cores: 8 β’ Memory: 12.8 GB / 32.0 GB (40.0%)
List available storage.
- Parameters: None
- Example Response:
πΎ Storage Pools πΎ ceph-prod β’ Status: ONLINE β’ Type: rbd β’ Usage: 12.8 TB / 20.0 TB (64.0%) β’ IOPS: β¬οΈ 15.2k β¬οΈ 12.8k πΎ local-zfs β’ Status: ONLINE β’ Type: zfspool β’ Usage: 3.2 TB / 8.0 TB (40.0%) β’ IOPS: β¬οΈ 42.8k β¬οΈ 35.6k
Get overall cluster status.
- Parameters: None
- Example Response:
βοΈ Proxmox Cluster β’ Name: enterprise-cloud β’ Status: HEALTHY β’ Quorum: OK β’ Nodes: 4 ONLINE β’ Version: 8.1.3 β’ HA Status: ACTIVE β’ Resources: - Total CPU Cores: 192 - Total Memory: 1536 GB - Total Storage: 70 TB β’ Workload: - Running VMs: 7 - Total VMs: 8 - Average CPU Usage: 38.6% - Average Memory Usage: 42.8%
Execute a command in a VM's console using QEMU Guest Agent.
- Parameters:
node
(string, required): Name of the node where VM is runningvmid
(string, required): ID of the VMcommand
(string, required): Command to execute
- Example Response:
π§ Console Command Result β’ Status: SUCCESS β’ Command: systemctl status nginx β’ Node: pve-compute-01 β’ VM: prod-web-01 (ID: 102) Output: β nginx.service - A high performance web server and a reverse proxy server Loaded: loaded (/lib/systemd/system/nginx.service; enabled; vendor preset: enabled) Active: active (running) since Tue 2025-02-18 15:23:45 UTC; 2 months 3 days ago
- Requirements:
- VM must be running
- QEMU Guest Agent must be installed and running in the VM
- Command execution permissions must be enabled in the Guest Agent
- Error Handling:
- Returns error if VM is not running
- Returns error if VM is not found
- Returns error if command execution fails
- Includes command output even if command returns non-zero exit code
After activating your virtual environment:
- Run tests:
pytest
- Format code:
black .
- Type checking:
mypy .
- Lint:
ruff .
proxmox-mcp/
βββ src/
β βββ proxmox_mcp/
β βββ server.py # Main MCP server implementation
β βββ config/ # Configuration handling
β βββ core/ # Core functionality
β βββ formatting/ # Output formatting and themes
β βββ tools/ # Tool implementations
β β βββ console/ # VM console operations
β βββ utils/ # Utilities (auth, logging)
βββ tests/ # Test suite
βββ proxmox-config/
β βββ config.example.json # Configuration template
βββ pyproject.toml # Project metadata and dependencies
βββ LICENSE # MIT License
MIT License