AI agents use pve_create_snapshot 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.
Snapshots are a reversible write operation that modifies cluster state by creating a new backup point. While snapshots can be deleted, their creation is a persistent write action that increases storage usage and cluster complexity. This is less severe than deletion (Destructive) but more impactful than simple metadata reads.
From the tool's definition 'Create a VM/container snapshot' — creates a new snapshot resource that persists in the system state. The confirmation gate (requires confirm=true) indicates operational sensitivity.
Attacks that exploit this kind of access
Create a VM/container snapshot. 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_create_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_create_snapshot 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_create_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_create_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_create_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 →