Unofficial-Proxmox-MCP

pve_create_snapshot

Create a snapshot of a Proxmox VM or LXC container to preserve its state before changes, with optional RAM state capture for QEMU VMs.

Instructions

Take a snapshot of a VM or LXC container.

Args: vmid: Target VM or Container ID. snapname: Name for the snapshot (alphanumeric and dashes/underscores, e.g. 'pre-upgrade-v1'). description: Informative description or changelog for the snapshot. vmstate: For QEMU VMs only. If True, saves running RAM state (live snapshot). node: Optional node name.

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>",
      "snapname": "<snapname>"
    },
    "name": "pve_create_snapshot"
  }
}

Input Schema

Name	Required	Description	Default
`node`	No
`vmid`	Yes
`vmstate`	No
`snapname`	Yes
`description`	No

Output Schema

Name	Required	Description	Default
`result`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

First observedv0.2.0Nov 9, 2026

TDQS

B3.3/5.0

Behavior3/5

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

No annotations are supplied, so the description carries the full disclosure burden. It usefully reveals two behavioral traits: snapname must be alphanumeric with dashes/underscores, and vmstate captures live RAM state and is QEMU-only. It says nothing about storage consumption, whether duplicate snapshot names fail, permissions required, or whether the operation can be safely repeated, which matters for a write tool with zero annotation coverage.

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?

A single front-loaded purpose sentence followed by a compact Args list, so each line earns its place and an agent can scan it quickly. Formatting is slightly awkward as a docstring quoted in the description, but there is no filler.

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?

Parameter meaning is covered well and an output schema exists to describe the return value, so the main remaining gaps are behavioral: no notes on duplicate snapshot names, storage impact, required privileges, or interaction with running guests. For a five-parameter mutation tool with no annotations, those omissions keep it at minimum-viable completeness.

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 compensate, and it largely does: all five parameters are explained, with an example name format for snapname, the VM/container target semantics of vmid, the changelog role of description, the live-snapshot meaning of vmstate plus its QEMU-only restriction, and node being optional. Only vmid's type/range and node's default behavior are left implicit.

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

Purpose4/5

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

Uses a specific verb and resource: 'Take a snapshot of a VM or LXC container', which is clearly distinct from siblings such as pve_delete_snapshot, pve_rollback_snapshot and pve_list_snapshots. It stops short of an explicit contrast with those siblings, so a reader must infer the distinction from the verb alone.

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 statement of when to use this versus the snapshot siblings, nor prerequisites such as whether the guest must be running or stopped. The only embedded rule is the parameter-level constraint that vmstate is for QEMU VMs only, which is guidance about one argument rather than about selecting the tool.

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