Skip to main content
Glama

gitlab_ci

Inspect GitLab CI/CD pipelines, tail masked job logs, and trigger, retry, or cancel jobs and pipelines with preview confirmations.

Instructions

Inspect pipelines, read build logs, and trigger or cancel GitLab CI/CD jobs.

Actions:

  • 'pipelines': List pipelines or jobs within a pipeline.

  • 'job_log': Tail execution log of a CI job (secrets masked).

  • 'retry_job': Retry a failed CI job (confirm=false previews).

  • 'cancel_job': Cancel a running CI job (confirm=false previews).

  • 'retry_pipeline': Retry failed jobs in a pipeline (confirm=false previews).

  • 'cancel_pipeline': Cancel an active pipeline (confirm=false previews).

  • 'trigger_pipeline': Trigger a new pipeline on an allowed ref (confirm=false previews).

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>",
      "project": "<project>"
    },
    "name": "gitlab_ci"
  }
}

Input Schema

NameRequiredDescriptionDefault
refNoGit branch/tag ref
limitNoPipelines limit
linesNoLog lines count
actionYes
job_idNoJob ID
statusNoPipeline status filter
confirmNofalse = preview only; true = apply
projectYesProject alias from gitlab_projects
pipeline_idNoPipeline ID

Output Schema

NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed11 schema fields changedv0.1.3
    • changedInput schema / properties / action / enum
      Previous value: -[
      -  "retry_job",
      -  "cancel_job",
      -  "retry_pipeline",
      -  "cancel_pipeline",
      -  "trigger_pipeline"
      -]New value: +[
      +  "pipelines",
      +  "job_log",
      +  "retry_job",
      +  "cancel_job",
      +  "retry_pipeline",
      +  "cancel_pipeline",
      +  "trigger_pipeline"
      +]
    • addedInput schema / properties / confirm / default
      Added value: +false
    • changedInput schema / properties / confirm / description
      Previous value: -"false = preview only; true = apply (operator approved)"New value: +"false = preview only; true = apply"
    • addedInput schema / properties / job_id / description
      Added value: +"Job ID"
    • addedInput schema / properties / limit
      Added value: +{
      +  "default": 10,
      +  "description": "Pipelines limit",
      +  "maximum": 50,
      +  "minimum": 1,
      +  "title": "Limit",
      +  "type": "integer"
      +}
    • addedInput schema / properties / lines
      Added value: +{
      +  "default": 200,
      +  "description": "Log lines count",
      +  "maximum": 2000,
      +  "minimum": 1,
      +  "title": "Lines",
      +  "type": "integer"
      +}
    • addedInput schema / properties / pipeline_id / description
      Added value: +"Pipeline ID"
    • removedInput schema / properties / project / maxLength
      Removed value: -40
    • addedInput schema / properties / ref / description
      Added value: +"Git branch/tag ref"
    • addedInput schema / properties / status
      Added value: +{
      +  "anyOf": [
      +    {
      +      "type": "string"
      +    },
      +    {
      +      "type": "null"
      +    }
      +  ],
      +  "default": null,
      +  "description": "Pipeline status filter",
      +  "title": "Status"
      +}
    • changedInput schema / required
      Previous value: -[
      -  "project",
      -  "action",
      -  "confirm"
      -]New value: +[
      +  "action",
      +  "project"
      +]
  2. First observedv0.1.0

TDQS

A4.2/5.0
Behavior4/5

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

Annotations declare readOnlyHint=false and destructiveHint=false, so safety framing is partly covered, but the description adds real context beyond them: job log secrets are masked, and mutate actions (retry/cancel/trigger) preview unless confirm=true. It does not disclose required token scopes or whether cancellations are irreversible, which keeps it below a 5.

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?

A one-sentence summary followed by a bulleted action map – front-loaded, scannable, and every line carries information (action name plus behavior). No filler or repetition of schema fields.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Covers all seven actions of a 9-parameter, multi-mode tool with high schema coverage and an output schema, so return values needn't be described. Small gaps remain: it doesn't explain how 'pipelines' behaves with or without pipeline_id, nor which actions require job_id or pipeline_id.

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 89%, so the schema already documents ref, limit, lines, job_id, status, confirm, project and pipeline_id. The description only adds the constraint that trigger_pipeline requires an 'allowed ref', which is modest additional meaning; the pipelines action's dependence on pipeline_id is left implicit.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

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

Opens with a specific verb+resource summary ('Inspect pipelines, read build logs, and trigger or cancel GitLab CI/CD jobs') and then enumerates all seven actions with a one-line purpose for each. An agent can distinguish this from gitlab_deploy/gitlab_repo purely from CI/CD scope without opening the schema.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The action list effectively serves as per-operation when-to-use guidance (list vs. read log vs. retry vs. cancel vs. trigger), and it states that mutating actions default to preview via confirm=false. It stops short of naming when to prefer a sibling tool or what preconditions (permissions, target refs) select one action over another.

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