pve-mcp

pve_node_ssh

Run shell commands on a Proxmox node over SSH to handle tasks the API cannot, such as pct exec, log inspection, and file operations.

Instructions

Run a shell command on a node over SSH, for what the API cannot do (pct exec, logs, files). Needs PVE_SSH_ENABLED=true and PVE_ALLOW_WRITES=true, since commands can change the system.

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": {
      "node": "<node>",
      "command": "<command>"
    },
    "name": "pve_node_ssh"
  }
}

Input Schema

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

Output Schema

Name	Required	Description	Default
No arguments

Schema Changelog

Changes observed during successful MCP inspections.

First observedv0.1.0Nov 10, 2026

TDQS

A4.1/5.0

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 load, and it does disclose the critical traits: transport is SSH, commands 'can change the system' (destructive capability), and two environment flags (PVE_SSH_ENABLED, PVE_ALLOW_WRITES) must be enabled or the call presumably fails. It stops short of describing what happens on non-zero exit, how output/errors are returned, or whether execution blocks.

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?

Two sentences, both load-bearing, with the capability statement front-loaded and the prerequisite/risk note second. No filler or restatement of the tool name.

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

Completeness4/5

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

An output schema exists, so return values need no explanation, and the mutation risk plus required enablement flags are covered. What remains thin is the timeout parameter and failure/exit-code behavior, which an agent invoking arbitrary shell commands would benefit from knowing.

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

Parameters2/5

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

Schema description coverage is 0%, so the description must compensate, and it largely does not. It implies 'node' and 'command' exist but adds no format detail (node naming, shell/quoting semantics, single vs multi-line commands), and the 'timeout' parameter with its 120 default is never mentioned at all.

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 shell command on a node over SSH') and immediately delimits scope to what the Proxmox API cannot do, naming concrete examples (pct exec, logs, files). This lets an agent separate it from pve_api and the other guest-level tools without opening any schema.

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

Usage Guidelines4/5

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

Gives a clear selection rule: use it for operations the API cannot perform, and it lists example categories. It does not explicitly say when to prefer pve_api or a guest-level exec tool instead, but the 'what the API cannot do' framing implies the fallback ordering.

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