Skip to main content
Glama

pve_backup

Back up a Proxmox VM or LXC container with vzdump. Supports snapshot (online), suspend, or stop modes. Dry-run by default; set confirm=true to execute.

Instructions

MUTATION: back up a guest with vzdump. Dry-run by default; confirm=True to execute. mode: snapshot (online, brief) | suspend | stop (HALTS the guest). Async — returns a task UPID. This is a one-off run; for a recurring schedule use pve_backup_job_create instead.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
kindNoGuest type: lxc or qemu.lxc
modeNoBackup mode: snapshot (online, brief) | suspend (RAM-quiesced pause) | stop (HALTS the guest).snapshot
nodeNoProxmox node hosting the guest; defaults to the configured node if omitted.
vmidYesNumeric ID of the guest (VM or CT) to back up.
confirmNoGate: false returns a dry-run PLAN, true executes the backup.
storageYesStorage ID to write the backup archive to.
compressNoCompression algorithm for the archive, e.g. zstd, gzip, lzo, or 0 (no compression).zstd
proximo_targetNoWhich configured Proxmox target to run this call against — a target name from your multi-target config (a specific PVE/PBS/PMG/PDM box). Omit to use the single/default target from the environment; the selection applies only to this call.

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
resultYes
Behavior4/5

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

The description discloses mutation action, dry-run behavior, async execution returning a UPID, and the effect of each mode (notably 'stop HALTS the guest'). Without annotations, this covers key behavioral traits. It could mention permission requirements or error handling but is already comprehensive.

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?

The description is very concise at three sentences, with bold keywords ('MUTATION', 'Async', 'Dry-run') and clear differentiation. Every sentence provides essential information with no redundancy.

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?

Given 8 parameters and the presence of an output schema (not shown), the description covers the core behavioral context: mutation, dry-run, async, modes, and one-off vs recurring. It lacks details on failure behavior or permissions but is adequate for an agent to select and invoke the tool correctly.

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 coverage is 100%, so baseline is 3. The description adds value by explaining 'confirm' as a dry-run gate and describing each mode option (snapshot, suspend, stop). This extends beyond the schema descriptions, improving parameter understanding.

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 clearly states the verb 'back up a guest' and the resource 'guest' via 'vzdump'. It specifies it is a one-off run and distinguishes from the sibling tool pve_backup_job_create for recurring schedules, making the purpose unambiguous.

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

Usage Guidelines5/5

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

The description explicitly says 'Dry-run by default; confirm=True to execute' and 'This is a one-off run; for a recurring schedule use pve_backup_job_create instead', providing clear when-to-use, when-not-to-use, and an alternative.

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

Install Server

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/john-broadway/proximo'

If you have feedback or need assistance with the MCP directory API, please join our Discord server