Proxmox MCP Server
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| PROXMOX_HOST | No | Proxmox server hostname/IP | localhost |
| PROXMOX_PORT | No | Proxmox API port | 8006 |
| MCP_SERVER_HOST | No | SSE server bind address | 0.0.0.0 |
| MCP_SERVER_PORT | No | SSE server port | 8080 |
| PROXMOX_VERIFY_SSL | No | Verify SSL certificates | false |
| PROXMOX_API_TOKEN_ID | Yes | API token ID (user@realm!tokenid) | |
| PROXMOX_API_TOKEN_SECRET | Yes | API token secret |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": false
} |
| prompts | {
"listChanged": false
} |
| resources | {
"subscribe": false,
"listChanged": false
} |
| experimental | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| list_vmsA | List all VMs and containers across all Proxmox nodes. Returns a list of all virtual machines and LXC containers with their basic information including:
|
| get_vm_infoA | Get detailed information about a specific VM or container. Args: vmid: The VM or container ID (e.g., 100, 101) node: The Proxmox node name. If not provided, will search all nodes. Returns detailed configuration including:
|
| get_vm_statusB | Get the current runtime status of a VM or container. Args: vmid: The VM or container ID node: The Proxmox node name (optional, will auto-detect) Returns:
|
| get_vm_metricsA | Get historical metrics/performance data for a VM. Args: vmid: The VM or container ID node: The Proxmox node name (optional) timeframe: Time range for metrics - one of: - 'hour': Last hour (default) - 'day': Last 24 hours - 'week': Last 7 days - 'month': Last 30 days - 'year': Last year Returns time-series data including:
|
| list_nodesA | List all Proxmox nodes in the cluster. Returns information about each node including:
|
| list_vm_snapshotsA | List all snapshots for a VM. Args: vmid: The VM ID node: The Proxmox node name (optional, will auto-detect) Returns list of snapshots with:
|
| get_cluster_statusA | Get overall Proxmox cluster status and health. Returns:
|
| get_vm_filesystem_infoA | Get filesystem/disk space information from inside a VM using the QEMU guest agent. This requires the qemu-guest-agent to be installed and running inside the VM. Install it with: apt install qemu-guest-agent (Debian/Ubuntu) or yum install qemu-guest-agent (RHEL/CentOS) Args: vmid: The VM ID node: The Proxmox node name (optional, will auto-detect) Returns filesystem information including:
|
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 8 tools
Most tools have distinct purposes, but there is notable overlap between get_vm_info and get_vm_status, which both provide VM status details, potentially causing confusion. The other tools are clearly differentiated, such as list_vms for listing all VMs and get_vm_metrics for historical performance data.
All tools follow a consistent verb_noun pattern with underscores, such as get_cluster_status, list_vms, and get_vm_info. This predictable naming scheme makes it easy for agents to understand and use the tools without confusion.
With 8 tools, the count is reasonable for a Proxmox server, covering core monitoring and listing functions. However, it lacks management tools like start/stop VMs or create snapshots, which slightly reduces appropriateness for a full-featured server.
The toolset covers read-only operations well, including status, info, metrics, and listings for clusters, nodes, VMs, and snapshots. However, there are significant gaps in management actions, such as creating, updating, or deleting VMs or snapshots, which limits agent workflows in this domain.