Skip to main content
Glama
harbor-mcp

harbor-mcp

by si-essence

harbor_robots

Destructive

Manage Harbor robot accounts: list, inspect, create, update, refresh secrets, or delete them; writes require explicit confirmation and secrets return only once.

Instructions

Robot account list, get, create, update, secret refresh, and delete. Create and refresh return secret once in the tool result and never in logs. Writes run only when confirm is true and HARBOR_ALLOW_WRITES=true. Actions: list, create, get, update, refresh_secret, delete.

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": {
      "action": "<action>"
    },
    "name": "harbor_robots"
  }
}

Input Schema

NameRequiredDescriptionDefault
qNo
pageNo
actionYesHarbor operation to call.
confirmNoBoolean true runs the write when HARBOR_ALLOW_WRITES is true. Omit it or pass false for a dry-run preview that sends nothing. The string true is rejected.
documentNo
robot_idNo
page_sizeNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A3.9/5.0
Behavior4/5

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

Annotations already declare destructiveHint=true, readOnlyHint=false and openWorldHint=true, yet the description adds genuinely new facts: create/refresh return the secret once and never write it to logs, and writes are gated by confirm plus an environment flag. What is missing is the blast radius of delete (e.g., that existing robot tokens/CI break).

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?

Three short sentences, front-loaded with the operation set, then the secret-handling and write-gating semantics, then the action enum. The telegraphic first sentence is slightly awkward but wastes no space.

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?

For a destructive, open-world tool with a nested object parameter and no output schema, the definition covers security semantics well but leaves the caller without the document shape needed for create/update or any hint about pagination fields. An agent can pick the right action but may not know what to put in the body.

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 coverage is only 29% across 7 parameters, so the description must compensate and does not: q, page, page_size, robot_id, and especially the free-form nested document object for create/update are never explained. Only the confirm gating is restated, and that is already documented in the schema.

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?

Names the specific resource (robot accounts) and enumerates the exact six operations supported, ending with an explicit action list that matches the schema enum. An agent can distinguish this from the harbor_projects/repositories/artifacts siblings because the resource is stated verb+noun.

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?

Explicitly states the condition under which writes execute (confirm=true and HARBOR_ALLOW_WRITES=true) and that omitting confirm yields a dry-run preview, which tells the agent how to safely probe. It stops short of when-to-use-vs-alternative guidance, but no sibling here plausibly overlaps on robot accounts.

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