proxmox-ops-mcp
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| PROXMOX_HOST | Yes | Proxmox VE host to connect to. | |
| PROXMOX_TOKEN_ID | Yes | Proxmox API token ID, for example 'mcp@pve!ops'. | |
| PROXMOX_AUDIT_LOG | No | Path to the audit log for write operations. | |
| PROXMOX_CA_BUNDLE | No | Path to a CA bundle for TLS verification. | |
| PROXMOX_ACCESS_TIER | No | Access tier controlling which tools are registered. Defaults to read_only. | read_only |
| PROXMOX_TOKEN_SECRET | Yes | Secret for the Proxmox API token. | |
| PROXMOX_TLS_FINGERPRINT | No | Pinned TLS certificate fingerprint, as an alternative to a CA bundle. |
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
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| list_nodesA | List all cluster nodes with status, CPU and memory utilisation. |
| list_guestsB | List VMs and containers across the cluster with resource usage, tags and HA state. |
| get_guestA | Show one guest's live status and full configuration (secrets redacted). |
| get_task_statusB | Return the state of a Proxmox task and the tail of its log. |
| cluster_healthA | Check quorum, node availability, CPU/memory pressure, storage fill levels and HA. Start here for any "is something wrong with the cluster?" question. Findings are sorted worst-first and each carries a concrete recommendation. |
| ceph_healthA | Analyse Ceph: health checks, OSD up/in counts, PG states, monitor quorum, capacity. Use for "why is Ceph degraded/warning?". Each Ceph health check becomes a finding with operator guidance. |
| compare_nodesA | Compare live CPU, I/O wait, load, memory, swap and versions across nodes. Use for "why is node X slower than node Y?". Flags I/O-bound nodes, swapping, overload, version drift and memory imbalance. |
| recent_task_failuresA | List tasks that failed recently, grouped by type. Good first stop after an incident. Based on the cluster-wide recent task list, which Proxmox keeps short; very old failures may no longer be included regardless of the window. |
| storage_healthA | Check ZFS pools and physical disks for anything that threatens data. Covers pool state, device errors, data errors, fill level, scrub age, SMART health, SSD wear and bad sectors. Use when asking whether the storage underneath the guests is healthy, or before maintenance on a node. |
| node_maintenance_statusA | Show pending Proxmox updates, needed reboots and expiring node certificates. A reboot is needed when a newer kernel is installed than the one running. Covers the Proxmox package set (kernel, QEMU, ZFS, pve-*). Reflects apt's last package list refresh, which Proxmox runs daily. |
| backup_auditA | Find guests with missing or stale backups, unscheduled guests and failed jobs. Reads backup volumes directly from every backup storage (including Proxmox Backup Server), so it reports what actually exists - not what the schedule promises. Set max_age_hours to match your schedule (e.g. ~170 for weekly backups). Failed tasks come from the cluster's recent task list, which only covers recent history. |
| recommend_placementA | Rank nodes for a new VM/container by memory headroom, CPU load and vCPU over-commit. Every node gets a score and the reasons it was accepted or rejected. |
| plan_node_evacuationA | Plan how to empty a node for maintenance without breaking HA or overloading others. Detects passthrough devices, bind mounts, local disks, locks and HA-managed guests, assigns every guest a target and migration mode, and returns the exact command sequence (including Ceph 'noout' and HA maintenance mode). Executes nothing. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
| triage_cluster | Full health triage across cluster, Ceph, backups and recent failures. |
| prepare_maintenance | Check whether a node can be drained and produce a step-by-step runbook. |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 13 tools
Most tools target clearly distinct resources or diagnostic concerns: cluster, Ceph, storage, node comparison, guests, tasks, backups, placement, and evacuation. There is some overlap between cluster_health, ceph_health, and storage_health around storage fill and health checks, but descriptions mostly clarify that cluster_health is a broad first-stop while the others are focused deep dives.
All names use snake_case and are readable, but the naming convention is mixed: action-oriented names like list_nodes, compare_nodes, get_guest, recommend_placement, and plan_node_evacuation coexist with noun-based names like ceph_health, storage_health, cluster_health, backup_audit, and recent_task_failures. The inconsistency is understandable but prevents a fully predictable pattern.
Thirteen tools is well within a reasonable range for a broad Proxmox operations/diagnostics server. Each tool covers a distinct operational concern such as cluster health, storage health, backup auditing, placement, or evacuation planning, and none appears redundant.
The surface covers the main diagnostic and planning areas for Proxmox operations: cluster/node/Ceph/storage health, guest listing and inspection, task status and failures, backup auditing, maintenance status, placement recommendation, and evacuation planning. Minor gaps include network health, deeper HA state inspection, and any execution-oriented guest lifecycle operations, though the latter may be intentionally out of scope for this diagnostic/planning server.