AI agents use pve_set_vm_config 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.
This tool modifies VM/container configuration properties, which is a Write operation—creating or updating data reversibly. While it affects system state, the changes are not destructive (can be reverted), not financial, and do not execute arbitrary code. The 'confirm=true' gate provides some safety. Severity is high because misconfiguration of VMs could impact availability or security, affecting multiple systems.
From the tool's definition 'Update VM/container config' with 'confirm=true' requirement indicates reversible modification of virtual machine configuration settings without data destruction.
Attacks that exploit this kind of access
Update VM/container config. 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_set_vm_config: 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_set_vm_config 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_set_vm_config 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_set_vm_config. 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_set_vm_config 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 →