Skip to main content
Glama
mjmirza

hetzner-mcp

by mjmirza
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Remote

cloud raw request

cloud_request

Send authenticated requests to any Hetzner Cloud API endpoint by relative path; reads are free while writes follow read-only and cost guards.

Instructions

Call any Hetzner Cloud (api.hetzner.cloud) endpoint directly. Use a relative path like /servers. Reads are free. Writes obey the read-only and cost guards. If an endpoint you need is missing or misbehaving, use the contribute_or_report tool to open a prefilled issue or pull request.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
bodyNoRequest body for write methods, as a JSON object, for example {"name":"web1","type":"spread"}. A JSON string is also accepted and parsed.
pathYesRelative API path, for example /servers or /servers/123.
queryNoQuery string parameters.
methodNoHTTP method. Defaults to GET.
confirmNoMust be true to create a billed resource. Reads and free resources do not need it.
verboseNoReturn the full payload. Default false returns a compact, token-efficient view.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changedv0.7.0
    • removedInput schema / properties / query / additionalProperties / anyOf
      Removed value: -[
-  {
-    "type": "string"
-  },
-  {
-    "type": "number"
-  },
-  {
-    "type": "boolean"
-  }
-]
    • addedInput schema / properties / query / additionalProperties / type
      Added value: +[
+  "string",
+  "number",
+  "boolean"
+]
  2. First observedv0.3.0

TDQS

A4/5.0
Behavior4/5

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

With no annotations, the description carries the full burden and does disclose real behavior beyond the schema: reads are free, writes are subject to read-only and cost guards, and confirm is needed for billed resources. It still omits auth requirements, error/retry behavior, and rate limits, but the safety and cost profile is unusually well surfaced.

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 short sentences, front-loaded with the core capability, then the cost/guard behavior, then the escalation path. Every sentence earns its place 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?

For a generic 6-parameter proxy tool with no output schema and no annotations, the description covers purpose, cost, guards, and verbose/token tradeoffs adequately. It leaves auth and error-handling expectations unstated, but nothing critical to making a correct call is missing.

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 coverage is 100%, so the baseline is 3; each parameter (path, method, body, query, confirm, verbose) is already documented in the schema. The description reinforces path format and read/write cost semantics but adds no syntax or format detail the schema lacks.

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 ('Call any Hetzner Cloud endpoint directly' at api.hetzner.cloud) with a concrete path example. This clearly differentiates the raw escape hatch from the dozens of typed siblings like cloud_list_servers and robot_request.

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

Usage Guidelines3/5

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

It gives operational context (relative paths, reads free, writes guarded) and routes missing/broken endpoints to contribute_or_report, which is a useful escape instruction. However, it never says when to prefer this raw tool over the many specific siblings (cloud_list_servers, cloud_create_server, etc.), which is the main selection decision an agent faces.

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