hetzner-mcp

Audit log

audit_log

Read-onlyIdempotent

Inspect recent tool calls with mode, result, and summary; filter by tool or errors to audit actions and troubleshoot failures.

Instructions

Most recent calls through this MCP, newest first: tool, mode (read/dry_run/execute/refused), result, summary.

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": "audit_log"
  }
}

Input Schema

Name	Required	Description
`mode`	No
`tool`	No	Substring of the tool name
`limit`	No
`errors_only`	No

Schema Changelog

Changes observed during successful MCP inspections.

First observedv0.1.0Nov 6, 2026

TDQS

B3.1/5.0

Behavior3/5

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

Annotations already declare readOnly, idempotent, non-destructive and open-world, so safety is covered. The description adds ordering ('newest first') and the shape of each entry, which is useful behavioral context. It does not disclose retention window, default truncation at 50 rows, or what 'refused' means operationally.

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?

A single tight sentence with the ordering constraint and the returned columns front-loaded. No filler and nothing redundant with the schema.

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?

With no output schema, describing the returned fields is valuable and appropriate. But for a 4-parameter tool with low schema coverage, the description leaves key facts unstated: what errors_only filters, that limit defaults to 50 and caps at 500, and whether the list is truncated.

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

Parameters2/5

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

Schema description coverage is only 25%: just 'tool' is documented, as a substring match. The description enumerates the mode values but gives no meaning for read/dry_run/execute/refused as filters, and says nothing about limit or errors_only. It adds little beyond the schema and does not compensate for the coverage gap.

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 precisely what the tool returns: recent MCP calls, newest first, with the fields tool, mode, result, summary. That is a specific resource plus ordering, so an agent can tell it is a log-reader rather than a host-management call like its siblings. It stops short of naming or contrasting with any sibling, so not a 5.

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?

There is no explicit when-to-use guidance, no mention of alternatives, and no prerequisites or exclusions. The auditing purpose is only implied by the phrase 'most recent calls through this MCP'. An agent must infer that this is the tool for inspecting prior activity.

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

Deploy Server