Unofficial-Proxmox-MCP

pve_create_vm

Provision a QEMU virtual machine in Proxmox VE by specifying CPU cores, memory, disk size, storage pool, and optional ISO image.

Instructions

Create a new QEMU virtual machine.

Args: vmid: Unique Virtual Machine ID (e.g. 150). name: Name / hostname of the virtual machine. cores: Number of virtual CPU cores. memory_mb: Memory in megabytes. disk_gb: Boot disk size in gigabytes. storage: Target storage pool (e.g. 'local-lvm', 'fast-tier'). iso_image: Optional ISO image path (e.g. 'local:iso/ubuntu-24.04-live-server-amd64.iso'). net0: Network interface configuration string. node: Target 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>",
      "name": "<name>"
    },
    "name": "pve_create_vm"
  }
}

Input Schema

Name	Required	Default
`name`	Yes
`net0`	No	virtio,bridge=vmbr0,firewall=1
`node`	No
`vmid`	Yes
`cores`	No
`disk_gb`	No
`storage`	No	local-lvm
`iso_image`	No
`memory_mb`	No

Output Schema

Name	Required	Description	Default
`result`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

First observedv0.2.0Nov 9, 2026

TDQS

B3.1/5.0

Behavior2/5

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

No annotations are supplied, so the description carries the full behavioral burden. It doesn't say whether the new VM is started or left stopped, what permissions are required, whether the VMID must be unallocated, or what happens on ID collision. Only the bare mutation is conveyed.

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?

Front-loaded single-sentence purpose followed by a tidy per-parameter list; no filler prose. It is slightly longer than needed because some entries add nothing beyond the parameter name (e.g. 'node: Target node name').

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?

An output schema exists, so return values needn't be explained, and parameter meaning is largely covered. But for a 9-parameter creation tool with no annotations, the missing operational context – post-create power state, validation of storage/ISO, and required-field marking – leaves real gaps.

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 all meaning comes from the Args block, which does cover all 9 parameters with concrete examples for vmid ('e.g. 150'), storage ('local-lvm', 'fast-tier'), and iso_image (full ISO path). Gaps remain: net0 is only 'Network interface configuration string' with no format hint, and required-vs-optional is not indicated.

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?

States a specific verb and resource: 'Create a new QEMU virtual machine.' That implicitly separates it from pve_create_lxc (container create) and pve_clone_system (clone), but it never names those alternatives or says how they differ. Clear purpose, weak sibling differentiation.

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?

No guidance on when to use this versus cloning an existing system or creating an LXC container, and no prerequisites (valid node, ISO present in storage, free VMID). The Args list is purely mechanical.

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