Skip to main content
Glama

gitlab_repo

Read-only

Inspect GitLab repositories read-only: list projects, branches, tags, and directory trees; read files; review commits; and compare refs to understand code changes.

Instructions

Read-only inspection of GitLab repositories, branches, directory trees, files, and commits.

Actions:

  • 'projects': List allowlisted GitLab project aliases and permissions.

  • 'refs': List branches and tags for a project.

  • 'tree': List directory files/folders at a ref.

  • 'read_file': Read file content at a ref with pagination (start_line/max_lines).

  • 'commits': View recent commit history with author, date, and commit message.

  • 'compare': Diff two branches/commits with per-file change summaries.

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": "gitlab_repo"
  }
}

Input Schema

NameRequiredDescriptionDefault
refNoBranch, tag, or commit SHA
shaNoSpecific commit SHA to inspect
kindNoRef kindboth
pathNoFile or directory path
limitNoItems limit
sinceNoISO date filter start
untilNoISO date filter end
actionYes
searchNoSearch filter
to_refNoTarget ref for compare
projectNoProject alias from gitlab_projects
from_refNoBase ref for compare
max_linesNoMax lines to read
recursiveNoRecursive tree listing
start_lineNoFile start line (1-based)

Output Schema

NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv0.1.3

TDQS

A3.5/5.0
Behavior3/5

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

Annotations already declare readOnlyHint=true, destructiveHint=false and openWorldHint=true, so the 'Read-only' phrasing is largely redundant. The description does add useful behavior beyond annotations: pagination for read_file via start_line/max_lines, and that 'compare' returns per-file change summaries and 'commits' includes author/date/message. It says nothing about rate limits, permission failures, or behavior when the project alias is not allowlisted.

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

Conciseness5/5

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

One scope sentence followed by a compact action list; front-loaded, zero filler, and each bullet earns its place by naming a distinct operation.

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?

Output schema and annotations carry return format and safety, so the description needn't repeat them. However, with 15 parameters across 6 actions, the missing piece is a parameter-to-action mapping (e.g. that 'project' comes from gitlab_projects aliases and that ref/kind apply only to refs), leaving the agent to cross-reference the flat schema itself.

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 description coverage is 93%, so the schema already documents nearly every parameter and the baseline is 3. The description adds only marginal meaning — it ties start_line/max_lines to read_file pagination and implies from_ref/to_ref belong to compare — but never states which of the 15 parameters apply to which action.

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 opening sentence names a specific verb and resource ('Read-only inspection of GitLab repositories, branches, directory trees, files, and commits') and the action list maps one-to-one onto the six enum values, so an agent can see exactly what each action retrieves. It does not explicitly contrast itself with siblings such as gitlab_ci or gitlab_deploy, though the 'read-only inspection' framing implies the boundary.

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?

Each action has a short gloss ('tree': List directory files/folders at a ref) which implies when to pick it, but there is no explicit when-to-use/when-not guidance or routing to alternatives. An agent must infer selection from the action names and one-line summaries.

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