The full upstream README, mirrored here for reference. Install config, tool schemas, adoption signals, and an original overview live on the Proxmox AIops listing page.
Disclaimer: Community-maintained open-source project. Not affiliated with, endorsed by, or sponsored by Proxmox Server Solutions GmbH. "Proxmox" is a trademark of its owner. MIT licensed.
AI-powered Proxmox VE VM and container lifecycle operations with a built-in
governance harness — unified audit log, token/runaway budget
guard, undo-token recording, and descriptive risk-tier labels. Self-contained:
no external dependencies beyond proxmoxer and the MCP SDK. Coverage is not
yet exhaustive across every Proxmox operation.
Verification status: live-verified against real Proxmox VE 8.4.19 across three rounds — read-only surfaces, the QEMU write surface, and a two-node cluster (quorum, live migration,
move-disk, a backup that actually succeeded). Rounds 2 and 3 each found a real bug the mocks could not see. See docs/VERIFICATION.md for exactly what was proven and what is still uncovered.
proxmox-aiops ...): vm list/get/config/start/stop/shutdown/reboot/reconfigure/clone/delete/migrate, vm resize-disk/move-disk/agent-ping, vm snapshot-create/snapshot-delete/snapshot-list/snapshot-rollback, backup create/list/restore, ct list/start/stop, cluster nodes/status/task-status/resources/node-status/task-log/next-vmid, ha status/resources, pool list/members, firewall vm-rules/cluster-status, storage list/content, diagnose node-pressure/guest-health, undo list/apply, init, secret set/list/rm/migrate/rotate-password, doctor, mcp.proxmox-aiops mcp or proxmox-aiops-mcp): 43 tools, every one wrapped with the bundled @governed_tool harness.diagnose node-pressure ranks cluster nodes by CPU/memory/root-fs pressure; diagnose guest-health scans VMs/containers for stopped guests, memory saturation, and disks near full. Every finding cites the measured number that tripped it and a concrete action — transparent heuristics, not a black-box verdict.proxmox-aiops init (onboarding wizard) and proxmox-aiops secret ... manage an encrypted secret store — no plaintext passwords in config.yaml.high risk. Disk resize is grow-only (shrink refused).cluster task-status / read lines with cluster task-log (the runaway budget guard prevents poll loops from running away).It delivers Proxmox VE operations — reads and writes — accurately and efficiently, and records every one of them. It does not decide whether a write is allowed to happen. That is the agent's judgement, or the permission of the account you connect it with: use a Proxmox VE user or API token granted only read privileges (no VM./Datastore. write roles), and the writes fail at the server — the place that actually owns the permission.
So there is no read-only switch, no policy file, no approval gate to configure. The one thing the
tool guarantees is that nothing is silent: every call, over MCP and over the CLI alike, lands an
audit row in ~/.proxmox-aiops/audit.db, and destructive writes still capture their before-state
and record an inverse where one exists.
Each tool declares a
risk_level, carried into the audit row as a descriptive tier (none/confirm/review) — so a reviewer can see at a glance that a row was a high-risk delete. It is a label, not a gate.
Running a smaller / local model? See agent-guardrails.md — it lists the guardrails this tool now enforces for you (so you don't spend prompt budget restating them) and gives a ready-made system prompt for what's left.
One install gives an agent both the skill and the MCP server:
The MCP server is fetched with uv and pinned to the
package version this plugin declares, so an audit row can be traced back to the
code that wrote it. Credentials are still configured with proxmox-aiops init — see below.
The same bundle is published on ClawHub, where one install delivers the skill and its MCP server together:
Restart the OpenClaw gateway afterwards so it loads the plugin. The MCP server is
fetched with uv, pinned to this exact release, so
uvx has to be on PATH — without it the skill still installs but reports
Visible to model: no. Credentials are configured exactly as below.
Example ~/.proxmox-aiops/config.yaml:
~/.proxmox-aiops/.env (chmod 600): PROXMOX_PVE_LAB_SECRET=<token-uuid>
All operations are logged to a local SQLite audit DB under ~/.proxmox-aiops/
(relocatable via PROXMOX_AIOPS_HOME). Every write tool passes through the
governance harness: token/runaway budget guard, risk-tier tagging, and audit
logging. Destructive CLI commands (vm stop,
vm delete, vm snapshot-delete, vm snapshot-rollback, ct stop) require
double confirmation and support --dry-run (notably backup restore, which is
high risk). API-returned text is run through a prompt-injection sanitizer.
Coverage is intentionally focused. Missing a device, action, or feature you need? Open an issue or pull request at github.com/AIops-tools/Proxmox-AIops — feature requests, contributions, and comments are all welcome.
License: MIT.