AI agents invoke pve_reboot_vm to trigger actions in Proxmox. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.
Rebooting a VM/container is an external operational action that interrupts running workloads. It is not purely destructive (no data is permanently deleted), but it executes a lifecycle operation with significant blast radius — rebooting a production VM can cause downtime for dependent services. The confirmation gate signals awareness of risk but doesn't change the category.
From the tool's definition Reboot a VM/container. Requires confirm=true.
Attacks that exploit this kind of access
Reboot a VM/container. Requires confirm=true. It is categorised as a Execute tool in the Proxmox MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Proxmox MCP server in PolicyLayer and add a rule for pve_reboot_vm: 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_reboot_vm is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the pve_reboot_vm 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_reboot_vm. 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_reboot_vm 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 →