vm_agent_exec

Execute a command inside a VM via the QEMU Guest Agent.

SERVERProxmox MCP Server SOURCEgethosthewalrus/proxmox-mcp

High RISK CLASS

Category Execute

Parameters 00 required

Recommended Rate-limitedsee the rule below

Registry record Grade F, identity unverified Pull the record →

This record as markdown: /tools/gethosthewalrus-proxmox-mcp/vm-agent-exec.md

WHAT IT DOES

What vm_agent_exec does on Proxmox MCP Server

AI agents invoke vm_agent_exec to trigger actions in Proxmox MCP Server. 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.

RISK

Why vm_agent_exec is rated High

This tool enables running code/commands inside VMs, which is fundamentally an Execute action. The blast radius is high because arbitrary command execution can modify VM state, access sensitive data, install malware, or compromise the guest system and potentially the host infrastructure. However, it is not Destructive (reversible in most cases) or Financial, making Execute the most appropriate category.

From the tool's definition Tool description states 'Execute a command inside a VM via the QEMU Guest Agent', which explicitly indicates execution of arbitrary commands within a virtual machine environment.

Attacks that exploit this kind of access

RECOMMENDED RULE

The rule that runs vm_agent_exec safely

PolicyLayer is an MCP gateway: it sits between your AI agents and Proxmox MCP Server, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For vm_agent_exec, this is the rule to start with:

vm_agent_exec Rate-limited

vm_agent_exec stays usable, but rate-capped: a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "vm_agent_exec": {
      "limits": [
        {
          "counter": "vm_agent_exec_rate",
          "window": "minute",
          "max": 10,
          "scope": "grant"
        }
      ]
    }
  }
}

RATE-LIMIT THIS TOOL → Instant setup, no code required.

The button opens the PolicyLayer dashboard: create your workspace, connect Proxmox MCP Server, apply this rule, and every vm_agent_exec call is checked against it from then on.

FAQ

Questions about vm_agent_exec

What does the vm_agent_exec tool do? +

Execute a command inside a VM via the QEMU Guest Agent. It is categorised as a Execute tool in the Proxmox MCP Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on vm_agent_exec? +

Register the Proxmox MCP Server MCP server in PolicyLayer and add a rule for vm_agent_exec: 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 MCP Server. Nothing to install.

What risk level is vm_agent_exec? +

vm_agent_exec is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.

Can I rate-limit vm_agent_exec? +

Yes. Add a rate_limit block to the vm_agent_exec 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.

How do I block vm_agent_exec completely? +

Set action: deny in the PolicyLayer policy for vm_agent_exec. 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.

What MCP server provides vm_agent_exec? +

vm_agent_exec is provided by the Proxmox MCP Server MCP server (gethosthewalrus/proxmox-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

KEEP EXPLORING

More on Proxmox MCP Server, and thousands of servers like it.

This server

All 286 Proxmox MCP Server tools → High-risk tools on this server →

Across the catalogue

All high-risk MCP tools → The MCP Attack Database →

Guides

Govern code and CI agents →Agent sandbox →Least privilege for MCP →