Skip to main content
Glama

List tasks

proxmox_list_tasks
Read-only

List Proxmox VE tasks cluster-wide or by node to review backups, migrations, starts, clones, and failures. Filter by type, user, VM, running state, or errors to find failed or active jobs.

Instructions

List Proxmox tasks (backups, migrations, starts, clones...). Without node, lists recent tasks across the whole cluster; with node, reads that node's task history with server-side filters. Use errors=true to find failures.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "proxmox_list_tasks"
  }
}

Input Schema

NameRequiredDescriptionDefault
nodeNoOnly this node, with full history and server-side filters (default: recent tasks cluster-wide)
typeNoOnly this task type, e.g. vzdump, qmstart, qmigrate, vzcreate, qmclone
userNoOnly tasks started by this user, e.g. root@pam
vmidNoOnly tasks for this VM/container
limitNoMaximum number of results (default 50)
sinceNoOnly tasks started after this UNIX time (node only)
errorsNoOnly failed tasks
fieldsNo
searchNoCase-insensitive substring filter on names, IDs, tags and similar fields
runningNoOnly tasks that are still running

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.6.1

TDQS

A4.4/5.0
Behavior4/5

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

Annotations already declare readOnlyHint=true, so safety is covered; the description adds genuinely new behavior: cluster-wide results are only recent by default, while per-node reads return full history with server-side filtering. That distinction affects results materially and isn't in the annotations. Default limit/pagination behavior is left to the schema.

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 tight sentences, front-loaded with what is listed, then the mode distinction, then a single tip. No filler or restatement of the title.

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?

For a read-only list tool with 10 optional parameters and a well-documented schema, the description covers the modedependent behavior that an agent could otherwise get wrong. It lacks any note on output shape or default ordering, but with no output schema and a strong input schema this is a minor gap.

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 90%, so baseline is 3, and the description adds real meaning on top: it explains that `node` switches on full history and server-side filters, and highlights errors=true as the failure filter. It doesn't extend `type`, `user`, `vmid`, or `limit`, but the schema already documents those.

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 ("List Proxmox tasks") and names the concrete task kinds covered (backups, migrations, starts, clones). The node/no-node split immediately separates it from the other list_* endpoints, which are all different resources.

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?

Explicitly says which mode to pick: omit `node` for recent cluster-wide tasks, supply `node` for a single node's full history with server-side filters. It also points at errors=true for failure hunting. It doesn't name a separate sibling tool to use instead, but the mode-selection guidance is concrete.

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

Deploy Server

Other Tools