AI agents call pve_get_vm_config to retrieve information from Proxmox without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves configuration data about virtual machines or containers without performing any side effects, modifications, deletions, or external operations. It is a pure read operation and poses minimal risk if invoked by an AI agent, as it only returns existing configuration information.
From the tool's definition Tool name 'pve_get_vm_config' and description 'Get config for a QEMU VM or LXC container' indicate data retrieval with no modification. The verb 'Get' and server description's emphasis on 'read-only cluster inspection' confirm this is a query operation.
Attacks that exploit this kind of access
Get config for a QEMU VM or LXC container. It is categorised as a Read tool in the Proxmox MCP Server, which means it retrieves data without modifying state.
Register the Proxmox MCP server in PolicyLayer and add a rule for pve_get_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_get_vm_config is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the pve_get_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_get_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_get_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 →