Skip to main content
Glama
harbor-mcp

harbor-mcp

by si-essence

harbor_system

Read-only

Check Harbor registry health, ping status, system info, volume usage, statistics, and current user permissions, and search registry resources; optional writes run only with explicit confirmation.

Instructions

Harbor health, ping, search, statistics, systeminfo, volumes, and the current user. Writes run only when confirm is true and HARBOR_ALLOW_WRITES=true. Actions: health, ping, search, statistics, systeminfo, volumes, current_user, current_permissions.

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_system"
  }
}

Input Schema

NameRequiredDescriptionDefault
qNo
pageNo
scopeNo
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.
relativeNo
page_sizeNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

C2.6/5.0
Behavior1/5

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

Annotations declare readOnlyHint=true, but the description states 'Writes run only when confirm is true and HARBOR_ALLOW_WRITES=true,' asserting a write path on a tool annotated as read-only — and none of the enumerated actions are writes, so the claim is both contradictory and unexplained. The environment-variable gate is useful context, but it directly conflicts with the structured safety signal an agent relies on.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness3/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Only two sentences, but the action list is stated twice in near-identical form ('Harbor health, ping, search, statistics, systeminfo, volumes, and the current user' then 'Actions: health, ping, search, ...'), which is pure duplication. The write-gate sentence is front-loaded poorly at the middle rather than leading with what the tool does.

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 seven-parameter tool with 29% schema coverage, no output schema, and a possible write path, the description omits how search querying works, what scope and relative mean, and pagination behavior. The unresolved read-only-versus-write signal is exactly the kind of thing an agent needs settled before calling.

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 29% (action and confirm only), so the description must carry q, scope, page, page_size, and relative. It adds nothing about any of them — not even that q/page pair with the 'search' action or that page_size caps at 100 — leaving five parameters undocumented in both places.

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 enumerates concrete resources the tool surfaces (health, ping, statistics, systeminfo, volumes, current user/permissions), which is far more specific than the bare name 'harbor_system'. It does not, however, say how this differs from siblings like harbor_admin or harbor_projects, so an agent must infer the boundary from the resource list alone.

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?

Listing the eight actions implies when this tool is the right pick (system-level, non-artifact queries), and the write gate gives one conditional rule. There is no explicit when-not guidance and no routing to harbor_admin, harbor_statistics-like alternatives, or other siblings, leaving selection to inference.

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