pve-mcp

pve_snapshot

List, create, roll back, or delete Proxmox VE snapshots, with confirmation required for rollback and deletion and optional RAM state capture for VMs.

Instructions

List, create, roll back or delete snapshots. rollback and delete need confirm=true. vmstate=true also saves RAM (VMs only).

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>"
    },
    "name": "pve_snapshot"
  }
}

Input Schema

Name	Required	Default
`vmid`	Yes
`action`	No	list
`confirm`	No
`timeout`	No
`vmstate`	No
`snapshot`	No
`description`	No

Schema Changelog

Changes observed during successful MCP inspections.

First observedv0.1.0Nov 10, 2026

TDQS

A3.5/5.0

Behavior3/5

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

No annotations exist, so the description carries the full burden. It does add real behavioral context: a confirm gate on the destructive operations and the VM-only constraint on vmstate. It omits what an agent most needs to know about a destructive tool — that deleting a snapshot is irreversible, that rollback discards current disk state, and whether any permission is required.

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 operation list, then the safety constraint, then the optional flag behavior. Every sentence adds information; there is no filler.

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

Completeness2/5

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

This is an unannotated multi-action mutation tool with 7 undocumented parameters and no output schema. The description covers the destructive-confirm gate and vmstate, but leaves the per-action parameter requirements (which fields each action needs) and the timeout semantics entirely unaddressed, which is not enough for an agent to invoke create/rollback/delete confidently.

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% across 7 parameters, so the description must compensate. It explains confirm and vmstate, and implicitly ties the action values to the enumerated verbs, but says nothing about vmid, timeout (default 600 — what is being timed out?), snapshot (presumably required for rollback/delete), or description (presumably for create).

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?

The description names a specific resource (snapshots) and enumerates the four supported operations (list, create, roll back, delete), which maps directly onto the action enum. No sibling tool in the catalog covers snapshots, so the scope is unambiguous.

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?

It gives a concrete prerequisite ('rollback and delete need confirm=true') and a scoping rule ('vmstate=true ... VMs only'), which is useful conditional guidance. However it never states when to choose a snapshot versus a backup/clone, nor which parameters each action requires, so 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.