Rollback to a snapshot. Requires confirm=true.
AI agents call pve_rollback_snapshot to permanently remove resources in Proxmox — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
Rolling back to a snapshot irreversibly overwrites the current VM/container state (disk, memory, configuration) with the snapshot's state. Any changes made after the snapshot was taken are permanently lost and cannot be recovered. This is an irreversible destructive operation with a critical blast radius since it affects entire VM/container states in a production virtualization environment.
From the tool's definition Rollback to a snapshot. Requires confirm=true.
Attacks that exploit this kind of access
Rollback to a snapshot. Requires confirm=true. It is categorised as a Destructive tool in the Proxmox MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Proxmox MCP server in PolicyLayer and add a rule for pve_rollback_snapshot: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Proxmox. Nothing to install.
pve_rollback_snapshot is a Destructive tool with critical risk. Critical-risk tools should be blocked by default and only enabled with explicit human approval.
Yes. Add a rate_limit block to the pve_rollback_snapshot rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for pve_rollback_snapshot. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
pve_rollback_snapshot is provided by the Proxmox MCP server (plgonzalezrx8/proxmox-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →