Skip to main content
Glama
harbor-mcp

harbor-mcp

by si-essence

harbor_projects

Destructive

Manage Harbor projects, members, and metadata by listing, inspecting, summarizing, creating, updating, or deleting records; writes require explicit confirmation.

Instructions

Project list, get, summary, create, update, delete, members, and metadata. Writes run only when confirm is true and HARBOR_ALLOW_WRITES=true. Actions: list, create, get, update, delete, deletable, summary, members_list, members_add, member_get, member_update, member_remove, metadata_list, metadata_add, metadata_get, metadata_update, metadata_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_projects"
  }
}

Input Schema

NameRequiredDescriptionDefault
midNo
nameNo
pageNo
ownerNo
actionYesHarbor operation to call.
publicNo
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
meta_nameNo
page_sizeNo
with_detailNo
project_nameNo
project_name_or_idNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

B3/5.0
Behavior4/5

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

Annotations already flag destructiveHint=true and readOnlyHint=false, so the safety profile is known. The description adds value beyond that by explaining the write-gating mechanism, the dry-run preview behavior, and that the string 'true' is rejected for confirm. It does not say which actions are the destructive ones (delete vs. member_remove), which would have pushed this higher.

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?

Two sentences with no filler, and the write-safety rule is placed early. However, the long action enumeration duplicates the schema's action enum exactly, spending most of the description's length on information the agent already has in structured form.

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?

This is a 13-parameter multiplexed, destructive tool with 15% schema coverage and no output schema, so the description carries a heavy burden. It covers the write gate but omits the per-action parameter contract and return shape, which is the critical missing piece for correct invocation.

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 15% across 13 parameters, so the description needs to compensate and does not. It repeats the action enum verbatim but says nothing about mid, project_name_or_id, owner, public, document, meta_name, page_size, or with_detail, leaving an agent 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.

Purpose3/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description names the resource (projects) and enumerates the operations, but the opening is a bare keyword list ('Project list, get, summary, create, update, delete, members, and metadata') rather than a statement of what the tool does. An agent can infer the scope, but there is no sentence distinguishing this from harbor_repositories or harbor_artifacts beyond the noun.

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?

It gives one real usage rule: writes only execute when confirm=true and HARBOR_ALLOW_WRITES=true, otherwise a dry-run preview. That is useful precondition guidance. It offers no when-to-use-this-vs-sibling guidance and no mapping of which action should be paired with which parameters.

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