Unofficial-Proxmox-MCP

pve_exec_guest_command

Execute non-interactive shell commands inside QEMU VMs via the QEMU Guest Agent, returning exit code, stdout, and stderr for remote troubleshooting.

Instructions

Execute a non-interactive shell command inside a QEMU VM via the QEMU Guest Agent. Returns exit code, stdout, and stderr.

Args: vmid: Target QEMU Virtual Machine ID. command: Shell command string to execute (e.g. 'ip a', 'uptime', 'docker ps'). node: Optional node name. timeout: Execution timeout in seconds (default: 30).

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_exec_guest_command"
  }
}

Input Schema

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

Output Schema

Name	Required	Description	Default
`result`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

First observedv0.2.0Nov 9, 2026

TDQS

A3.6/5.0

Behavior3/5

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

With no annotations at all, the description carries the full behavioral burden; it does disclose useful traits (non-interactive only, 30s default timeout, returns exit code/stdout/stderr). It omits the significant behavioral facts for an arbitrary-code-execution tool: required permissions, which user context the command runs as, and what happens on timeout (kill vs. partial output).

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

Conciseness4/5

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

The core behavior and return contract are front-loaded in two sentences, followed by a compact Args block. Nearly every line earns its place; only the repeated default/timeout detail is mildly redundant with the schema defaults.

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?

An output schema exists, so the return-value explanation is a bonus rather than a requirement, and parameter coverage is solid. For a remote code execution tool with zero annotations, however, the definition should still flag the guest-agent/running-VM prerequisite and the risk profile before an agent invokes it.

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

Parameters4/5

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

Schema description coverage is 0%, so the description must carry all parameter meaning, and it does: it names all four parameters and explains vmid as the target VM, command as a shell string with concrete examples ('ip a', 'uptime', 'docker ps'), node as optional, and timeout in seconds with its default.

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 ('Execute a non-interactive shell command inside a QEMU VM') plus the exact mechanism (QEMU Guest Agent), and the return contract. No sibling tool in the list performs guest command execution, so the agent can select this one unambiguously.

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

Usage Guidelines2/5

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

There is no explicit when-to-use or when-not-to-use guidance and no stated prerequisites, even though this tool only works if the VM is running and the guest agent is installed and responsive. The 'non-interactive' qualifier hints at a constraint but is not framed as a usage rule or contrasted with any alternative.

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