infrastructure-mcp

Overview Schema Source Related Servers Discussions Admin

proxmox_snapshot

Take a snapshot of a QEMU VM or LXC container on a Proxmox node. Requires confirm and returns a task UPID to check completion.

Instructions

Take a snapshot of a QEMU VM or LXC container on a Proxmox node. This is a state-changing action: it requires confirm: true, and returns without acting if confirmation is missing. Snapshotting is asynchronous — the response carries a task UPID, not confirmation the snapshot has finished; check it with proxmox_tasks. Set dry_run: true to see the exact API call that would be made without needing confirm at all.

Input Schema

TableJSON Schema

Name	Required	Description
`name`	Yes	name for the new snapshot
`node`	Yes	the cluster node the guest lives on
`type`	No	guest type: 'qemu' (default) or 'lxc'
`vmid`	Yes	the guest's numeric VM/container ID
`confirm`	No	must be true to actually take the snapshot; otherwise the tool reports what it would do without acting
`dry_run`	No	if true, report the exact API call that would be made and return without acting or requiring confirm
`instance`	Yes	the inventory proxmox instance name

Output Schema

TableJSON Schema

Name	Required	Description	Default
`name`	Yes
`node`	Yes
`type`	Yes
`upid`	No
`vmid`	Yes
`status`	Yes
`message`	Yes
`instance`	Yes
`timestamp`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedv0.8.1Oct 15, 2026

addedInput schema / properties / dry_run

Added value: +{
+  "description": "if true, report the exact API call that would be made and return without acting or requiring confirm",
+  "type": "boolean"
+}

First observedv0.1.0Oct 15, 2026

TDQS

A4.5/5.0

Behavior5/5

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

With no annotations, the description carries the full burden and does so well: it discloses that this is state-changing, that it no-ops without confirm, that the success response is a UPID rather than completion, and that dry_run bypasses confirmation. This is exactly the context an agent needs to avoid assuming the snapshot finished.

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?

Four sentences, zero filler, and the most important constraint (state-changing, needs confirm) is front-loaded before the async and dry_run details. Each sentence delivers a distinct operational fact.

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

Completeness5/5

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

An output schema exists, yet the description goes further by interpreting the asynchronous UPID return and pointing to the tool that resolves it. Combined with the confirmation and dry_run semantics, nothing needed to invoke this correctly is missing.

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 100%, so the schema already documents all seven parameters, including confirm and dry_run. The description restates the confirm/dry_run contract in behavioral terms but adds no syntax, constraints, or default details beyond the schema, so the baseline 3 applies.

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 ('Take a snapshot of a QEMU VM or LXC container on a Proxmox node') and scopes it to both guest types. No sibling tool performs snapshots, so the agent can distinguish it immediately from proxmox_start_vm, proxmox_stop_vm, or proxmox_tasks.

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?

Clearly explains the gating condition (confirm: true required, otherwise it reports and returns) and names proxmox_tasks as the way to follow up on the async operation, plus dry_run as a no-confirm preview path. It lacks an explicit 'use this before making changes' framing, but the when/how conditions are concrete.

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