Skip to main content
Glama

pve_storage_create

Define a new cluster storage entry in Proxmox VE, supporting dir, nfs, pbs, and cifs types. Dry-run mode returns a plan; confirm writes the configuration.

Instructions

MUTATION: define a new cluster storage entry in storage.cfg (dir / nfs / pbs / cifs / …).

This registers a storage definition the cluster can use; it does NOT format disks or provision a backend — to create a disk-backed backend (lvm/zfs/directory) on a node use pve_node_storage_backend_create. Required params depend on storage_type (dir needs path; nfs needs server+export). MEDIUM risk — a bad definition can fail to mount and slow cluster storage enumeration; no existing data is touched. Dry-run by default (returns a PLAN); confirm=True writes storage.cfg (the confirm result payload is typically null).

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
pathNoFilesystem path (required for storage_type='dir').
nodesNoComma-separated node list this storage is available on; omit for all nodes.
exportNoNFS export path (required for storage_type='nfs').
serverNoRemote host address (required for nfs/cifs/pbs).
sharedNoIf True, marks storage as shared across all nodes.
confirmNoFalse (default) returns a dry-run PLAN only; True executes the creation.
contentNoComma-separated content types to allow, e.g. 'iso,backup,images'.
disableNoIf True, storage is created in a disabled state.
storageYesNew storage ID (name used across the cluster).
storage_typeYesPVE storage driver type, e.g. 'dir', 'nfs', 'pbs'.
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
Behavior5/5

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

Discloses mutation nature, dry-run default, confirm behavior, risk level (MEDIUM), and that no existing data is touched. Compensates fully for lack of annotations.

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?

Concise yet comprehensive: starts with MUTATION label, groups information logically, no filler. Every sentence adds unique value.

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?

Covers all key aspects: purpose, risks, behavioral nuances, parameter dependencies, and output behavior. Output schema exists, so return details aren't needed.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters5/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Adds significant value beyond schema: explains dependency of required params on storage_type, gives type-specific examples, and describes the confirm parameter's effect on output (PLAN vs null).

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 it defines a new cluster storage entry in storage.cfg, listing storage types (dir, nfs, pbs, cifs), and explicitly distinguishes itself from the sibling pve_node_storage_backend_create for disk-backed backends.

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?

Provides explicit guidance: use for storage definitions, not for disk-backed backends (pve_node_storage_backend_create). Also notes required params vary by storage_type, with examples.

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