AI agents use pve_resize_disk to create or update resources in Proxmox — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Proxmox environment.
Resizing a disk modifies VM storage configuration. While not outright destructive (data is not deleted when enlarging), disk resize operations can be irreversible in practice (shrinking is typically unsupported and can corrupt data; enlarging cannot be undone without snapshots). The operation modifies infrastructure state with a potentially large blast radius — misuse could render a VM's disk unusable.
From the tool's definition Resize a QEMU VM disk. Requires confirm=true.
Attacks that exploit this kind of access
Resize a QEMU VM disk. Requires confirm=true. It is categorised as a Write tool in the Proxmox MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Proxmox MCP server in PolicyLayer and add a rule for pve_resize_disk: 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_resize_disk is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the pve_resize_disk 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_resize_disk. 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_resize_disk 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 →