Skip to main content
Glama
harbor-mcp

harbor-mcp

by si-essence

harbor_repositories

Destructive

Manage Harbor registry repositories with actions to list, inspect, update descriptions, and delete; write operations run only after explicit confirmation and enabled write permissions.

Instructions

Repository list, get, description update, and delete. Repository names with slashes are double-URL-encoded. Writes run only when confirm is true and HARBOR_ALLOW_WRITES=true. Actions: list, list_all, get, update, 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_repositories"
  }
}

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
page_sizeNo
project_nameNo
repository_nameNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A3.5/5.0
Behavior4/5

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

Annotations already flag destructiveHint=true and readOnlyHint=false, and the description is consistent with that, adding the operational detail an agent actually needs: the double gating on confirm plus HARBOR_ALLOW_WRITES, the fact that a missing/false confirm sends nothing, and the double-URL-encoding quirk for repository names containing slashes. What is not disclosed is the blast radius of delete (does it remove artifacts too?) or the return shape of any action.

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?

Four tight sentences, with the operation list and the write gate up front where they matter most. The trailing 'Actions:' line partly duplicates the schema enum and the opening sentence, but it does add 'list_all', which the prose omits, so the redundancy earns its keep.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness2/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For an 8-parameter, multi-action tool with a destructive delete and no output schema, the description leaves major gaps: what each action returns, what 'description update' actually modifies (presumably the document parameter), whether delete cascades, and how pagination interacts with list vs list_all. The write-safety disclosure is good, but an agent could still call this incorrectly at the parameter level.

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 only 25%, so the description must carry weight — and it partially does, explaining confirm's gating behavior, the encoding requirement for repository_name, and the action enum. The remaining parameters (q, page, page_size, project_name, document) receive no mention at all, leaving the payload of update and the meaning of the query/pagination parameters to inference.

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?

Names the resource (repositories) and enumerates the operations handled: list, get, description update, delete. The 'Actions:' line disambiguates the multi-action design, and the sibling set (admin/artifacts/projects/robots/system) makes plain this is the repository-scoped tool. It never explains what 'list_all' means relative to 'list', which keeps it short of 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 Guidelines3/5

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

The write guard ('Writes run only when confirm is true and HARBOR_ALLOW_WRITES=true') is a genuine when-to-use condition, and it briefly frames confirm=false as a dry-run. However, it gives no guidance on choosing list vs list_all vs get, and no hint about which actions are destructive versus read-only beyond the generic write gate.

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