glab · GitLab

GitLab CLI for AI Agents

Work with GitLab merge requests, issues, pipelines, and releases from scripts.

Official toolOperational risk: R0–R3verified

Install for an Agent Report broken data

Agent readiness

84/100

Evidence confidence

verified

Documentation checked

2026-07-10

Independently tested version

1.92.1

Install for an Agent

Choose an official installation path that matches the runtime. Pin a version for team or CI use, then record the version before the first task.

HomebrewRecommended

macos · linux

$ shell

brew install glab

winget

windows

$ shell

winget install GLab.GLab

Authentication and Minimum Permissions

Grant only the permissions the task needs. Pass credentials through environment variables or a platform secret store, never through prompts, repositories, or logs.

Authentication requiredHeadless authentication supported

Use a project-scoped token with read_api until a write is approved.

Methods: OAuth, personal access token, CI job token
Secret environment variables: GITLAB_TOKEN, GITLAB_HOST
Credential storage: For headless runs, inject GITLAB_TOKEN, GITLAB_HOST from the CI or platform secret manager at process start. For local interactive use, prefer the CLI or operating-system credential store when the official client supports one. Never save values in repository files.

Agent and Environment Compatibility

Confirm shell access first, then check the platform, network boundary, and credential path.

claude-codecodexgemini-clicopilot-cli

Environments: local, ci, container, headless, remote
Platforms: macos, linux, windows

Structured Output for Reliable Automation

Prefer a machine-readable format. Treat stdout as the result channel and stderr as diagnostics so the agent can parse failures separately.

json · text

Use --output json where supported and keep diagnostic logs on stderr.

--output json

No independently captured output sample

Structured-output support currently comes from official documentation. CLI Finder does not show a guessed example or invented schema before a bounded, non-destructive execution captures stdout.

R0–R3 Command Risk Guide

Risk is assigned per command. R0 is local or remote read-only, R1 is reversible local write, R2 changes remote state, and R3 can be irreversible or production-impacting.

Read-only does not mean public

R0 only means the command does not change local or remote state. A read-only command may still return secrets, identity data, configuration, or production data. Expose only the minimum needed for the task, and never place it in logs, prompts, or commits.

R0List merge requests

Reads merge request metadata for review and triage.

$ shell

glab mr list --output json

IdempotentSensitive output

R2Update an issue

Changes remote issue fields and requires approval.

$ shell

glab issue update 123 --label bug

Confirmation requiredMay repeat a change

How the Agent Readiness Score Is Built

Readiness describes how reliably an agent can operate the tool. It does not make every command safe and it does not replace an independent execution test.

Documentation indicates an agent-readiness score of 84/100. A bounded local smoke test is recorded for 1.92.1; review its limitations before relying on untested commands.

Structured output

Use --output json where supported and keep diagnostic logs on stderr.

18/20

Headless operation

Official documentation describes a non-interactive authentication or execution path.

14/15

Safety controls

CLI Finder separates read commands from commands that require confirmation.

11/15

Determinism

Commands use explicit arguments and documented output controls where available.

8/10

Authentication

Use a project-scoped token with read_api until a write is approved.

8/10

Documentation

This entry cites official documentation checked on 2026-07-10.

9/10

Installation

Official installation paths cover macOS, Linux, and Windows.

8/8

Maintenance

An official source repository is linked for release and maintenance review.

6/7

Agent artifacts

CLI Finder can generate registry-derived skills and policies; the tool itself was not credited with shipping them.

2/5

Generate a Skill or Agent Policy

Choose an agent and safety mode to generate a copyable artifact with installation, allowed commands, approval boundaries, and the evidence limitation.

Artifact typeTarget agentSafety mode

Generated artifact preview

SKILL.md

---
name: gitlab-cli-agent-workflow
description: Use GitLab CLI for merge requests, GitLab issues, pipelines with explicit command risk and evidence boundaries.
---

# GitLab CLI agent workflow

Use this skill when the task needs merge requests, GitLab issues, pipelines, releases.

## Evidence boundary

- Registry confidence: `verified`
- Documentation checked: `2026-07-10`
- Locally tested version: `1.92.1`
- Treat only the recorded executed checks as independently verified; every unlisted command remains documentation-only.

## Executed smoke checks

- `glab --version` — passed; exit 0. The recorded smoke check completed successfully.
- `glab --help` — passed; exit 0. The recorded smoke check completed successfully.

## Installation

- Homebrew (macos, linux): `brew install glab`
- winget (windows): `winget install GLab.GLab`

## Authentication

- Methods: OAuth, personal access token, CI job token
- Secret environment variables: `GITLAB_TOKEN`, `GITLAB_HOST`
- Minimum permissions: Use a project-scoped token with read_api until a write is approved.
- Credential storage: For headless runs, inject GITLAB_TOKEN, GITLAB_HOST from the CI or platform secret manager at process start. For local interactive use, prefer the CLI or operating-system credential store when the official client supports one. Never save values in repository files.
- Never print, persist, or commit credential values.

## Allowed commands (read-only)

- `glab mr list --output json` — R0: Reads merge request metadata for review and triage.

## Commands requiring explicit approval (read-only)

- None recorded.

## Forbidden commands (read-only)

- R2 `glab issue update 123 --label bug` — Changes remote issue fields and requires approval.

## Execution rules

1. Mode boundary: R0 exact commands may be used; R1, R2, and R3 commands are forbidden.
2. Confirm the selected account, project, context, database, namespace, or environment before any command.
3. Prefer structured output using `--output json`.
4. Capture the exact command, exit code, stdout, and stderr separately.
5. A generated prefix policy must prompt unless that exact prefix is explicitly marked suffix-safe; do not infer safety from the executable name.
6. Never broaden credentials or disable safety controls to make a command succeed.

## Official sources

- [GitLab CLI documentation](https://docs.gitlab.com/cli/)
- [GitLab CLI documentation source repository](https://gitlab.com/gitlab-org/cli)

CLI vs MCP vs API for This Task

CLI

Use the CLI on a developer machine, in CI, or in a container when the task should reuse existing shell state, credentials, and scripts and remain directly observable.

MCP

Consider MCP when the agent benefits from controlled tool definitions, delegated identity, or centrally governed server-side access.

API

Use the direct API for persistent application integrations, high-volume requests, or event-driven work where starting a process adds unnecessary overhead.

Read the full CLI vs MCP guide

Verification History and Official Evidence

CLI Finder records documentation review separately from real execution. Installation, help, exit codes, and output cannot be called Verified until they were run.

Current evidence boundary

The installed glab binary, version output, help rendering, and zero exit status were checked locally. Authentication, GitLab host access, merge-request JSON output, writes, and destructive commands were not executed.

Evidence confidence: verified
Independently tested version: 1.92.1 · 2026-07-10
Test environment: macOS 26.5.1 (arm64), local non-interactive shell

Executed checks

PassedExit code: 0
glab --version
The recorded smoke check completed successfully.
stdout excerpt
glab 1.92.1 (fcecef55)
PassedExit code: 0
glab --help
The recorded smoke check completed successfully.