Skip to main content
Glama
harbor-mcp

harbor-mcp

by si-essence

harbor_artifacts

Destructive

Manage Harbor registry artifacts: list and inspect details, handle tags and labels, check vulnerabilities, trigger scans, and delete entries, with confirmation-gated writes and dry-run previews.

Instructions

Artifact list and get, tags, artifact labels, vulnerability addition, scan trigger, and delete. Writes run only when confirm is true and HARBOR_ALLOW_WRITES=true. Actions: list, get, delete, tags_list, tag_create, tag_delete, label_add, label_remove, vulns, scan, accessories.

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_artifacts"
  }
}

Input Schema

NameRequiredDescriptionDefault
nameNo
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
label_idNo
tag_nameNo
with_tagNo
page_sizeNo
referenceNo
with_labelNo
project_nameNo
repository_nameNo
with_scan_overviewNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

B3.3/5.0
Behavior4/5

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

Annotations already flag destructiveHint=true, readOnlyHint=false and non-idempotency; the description goes beyond them by disclosing the two-key write gate, the dry-run preview when confirm is omitted or false, and that the string 'true' is rejected. That is genuine behavioral context an annotation cannot convey. It loses a point for never saying which of the eleven actions are the destructive ones (delete, tag_delete, label_remove presumably) since the annotations apply coarsely to the whole bundle.

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 compact sentences with the safety gate front-loaded right after the operation overview, zero filler. The action enumeration is slightly list-dump-ish and duplicates the enum, but it aids scanning. No padding or hedging.

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 a 14-parameter, eleven-action bundled tool with no output schema and very low schema description coverage, the description should map parameters to actions and describe return shapes at least coarsely. It does neither, so an agent cannot construct a valid get versus tag_create versus label_add call without reverse-engineering the schema. The write-gate detail is the only real completeness win.

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 14% across 14 parameters, so the description must compensate and largely does not. It clarifies only confirm-style semantics that the schema already spells out, and never explains name vs project_name vs repository_name, reference, tag_name, label_id, document, or the with_* toggles. An agent is left to guess which parameters each action consumes.

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?

The description names the resource (Harbor artifacts) and enumerates concrete operations, then repeats them as a canonical action enum: list, get, delete, tags_list, tag_create, tag_delete, label_add, label_remove, vulns, scan, accessories. That lets an agent separate artifact work from sibling domains like repositories or projects. It falls short of 5 because the opening phrase 'vulnerability addition' is ambiguous against the 'vulns' action and nothing states the boundary with harbor_repositories explicitly.

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 description gives a real operational gate: writes run only when confirm is true and HARBOR_ALLOW_WRITES=true, so an agent knows when a call will actually mutate. However it gives no guidance on which action to pick for a given intent, and no indication of when to prefer a sibling tool. Usage is implied by the action list rather than explained.

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