hcloud-mcp

create_storage_box

Provision a Hetzner Storage Box with a specified type, location, password, SSH keys, and access settings; returns an action to poll until provisioning completes.

Instructions

Create a Storage Box (billed hourly, capped at the monthly price; see list_storage_box_types for prices). Returns an Action; poll get_storage_box_action until status is success; provisioning can take several minutes and username/server stay null until status is active

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": {
      "name": "<name>",
      "location": "<location>",
      "storage_box_type": "<storage_box_type>",
      "password": "<password>"
    },
    "name": "create_storage_box"
  }
}

Input Schema

Name	Required	Description
`name`	Yes	Storage Box name
`labels`	No
`location`	Yes	Location ID or name, e.g. fsn1, hel1 (see list_storage_box_types prices for availability)
`password`	Yes	Password policy: 12-128 chars from a-z A-Z ÄÖÜäöüß 0-9 ^°!§$%/()=?+#-.,;:~*@{}_& with at least one upper case letter, lower case letter, digit and special character; must not appear in known data breaches. Generate a strong random one; never echo it back to the user unless they asked for it
`ssh_keys`	No	SSH public keys in OpenSSH format to install
`access_settings`	No	Initial access settings
`storage_box_type`	Yes	Storage Box Type ID or name, e.g. bx11

Schema Changelog

Changes observed during successful MCP inspections.

Addedv0.1.1Nov 11, 2026

TDQS

A4.3/5.0

Behavior5/5

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

Goes well beyond the annotations (readOnlyHint=false, openWorldHint=true, idempotentHint=false, destructiveHint=false): discloses hourly billing capped at monthly, that the call returns an Action rather than the box, that provisioning takes several minutes, and that username/server are null until status is active. That is exactly the async-creation context an agent needs to avoid misreporting a half-provisioned box.

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?

Dense but front-loaded: the core action leads, then billing, then the async follow-up. Every clause carries information, though the return-value and polling clauses are packed into one long parenthetical that could be split for readability.

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 7-parameter creation tool with a nested access_settings object and no output schema, the description covers the essential unknowns: cost model, asynchronous completion, and which fields are not yet populated. It does not restate return values (none exist to document), but omits any note on what happens on repeated invocation, leaving that to idempotentHint=false.

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 86%, so the schema already documents name, location, password policy, ssh_keys, access_settings and storage_box_type. The description adds no parameter-level meaning beyond what the schema states, which is the expected baseline when coverage is high.

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?

Opens with a specific verb+resource ("Create a Storage Box") and immediately qualifies the scope with billing behavior and the return type. The name plus the explicit mention of provisioning an actual box distinguishes it from create_storage_box_subaccount and create_storage_box_snapshot.

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?

Gives concrete follow-up guidance: poll get_storage_box_action until status is success, and consult list_storage_box_types for prices/availability. It does not state when-not to use it (e.g. that a subaccount or snapshot should be created instead), so it falls short of 5.

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

Deploy Server