pve-mcp

pve_agent_exec

Run a command inside a VM via the QEMU guest agent and return its exit code and output. Use argv-style commands to check or control services without opening a console.

Instructions

Run a command inside a VM through the QEMU guest agent and return exit code and output. command is argv, e.g. ["systemctl", "is-active", "nginx"]. Requires the agent to be installed and enabled.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "vmid": "<vmid>",
      "command": "<command>"
    },
    "name": "pve_agent_exec"
  }
}

Input Schema

Name	Required	Description	Default
`vmid`	Yes
`command`	Yes
`timeout`	No
`input_data`	No

Output Schema

Name	Required	Description	Default
No arguments

Schema Changelog

Changes observed during successful MCP inspections.

First observedv0.1.0Nov 10, 2026

TDQS

A3.9/5.0

Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are supplied, so the description carries the full burden, and it does disclose two real behavioral facts: the call returns an exit code plus output, and it fails unless the guest agent is installed and enabled. It stops short of saying the command runs with guest-level privileges, that arbitrary execution can mutate VM state, or how the timeout aborts a hung command.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Three short sentences, front-loaded with the action and mechanism, followed by the one parameter example that prevents a real mistake, then the prerequisite. Nothing is padded and every sentence carries information.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Return values are covered by the existing output schema, and the description correctly avoids re-explaining them at length. For a no-annotation execution tool with four fully undocumented parameters, though, it omits stdin behavior, timeout semantics, and the execution context of the command, leaving real operational gaps.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, and the description rescues the most error-prone parameter by defining command as argv with a concrete example, implying no shell interpolation. However, timeout and input_data (presumably stdin) get no explanation at all, so half the parameters remain undocumented in both schema and prose.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource ('Run a command inside a VM') and names the exact mechanism ('through the QEMU guest agent'), which is what separates it from node-level execution via pve_node_ssh or generic pve_api calls. An agent can decide between this and the other execution tools without opening a schema.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The prerequisite 'Requires the agent to be installed and enabled' is a genuine gate on use, so the agent knows when the call will fail. But there is no explicit statement of when to prefer this over pve_node_ssh or pve_api, and no guidance on what to do when the agent is absent; usage is only implied.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.