MCPInstall

gitlab-mcp-skill

Use this skill when working with the GitLab MCP server tools for merge requests, issues, repositories, pipelines, work items, variables, dependency proxy, vulnerabilities, webhooks, search, CI catalog, and related GitLab workflows.

Installs
1.1K
Last 24h
+10
Trending rank
#8910
Security
Not audited

Install

Works with every agent the skills CLI supports.

npx skills add https://github.com/zereight/gitlab-mcp --skill gitlab-mcp-skill
  1. 01

    Install

    Run the command in your project. The CLI asks which agents to install for.

  2. 02

    Describe the task

    Ask your agent for something this skill covers. It loads gitlab-mcp-skill automatically when relevant.

  3. 03

    Review the result

    The agent follows the SKILL.md steps, scripts and references bundled with the skill.

SKILL.md

The instructions your agent reads when the skill is triggered.

gitlab-mcp

GitLab MCP server providing 278 tools: 275 tools across 24 toolsets, plus execute_graphql, the always-available discover_tools meta-tool, and help.

For exact generated parameter tables, see docs/tools/. Use this file for workflow shape and high-signal parameter hints.

Toolsets

ToolsetDefaultEnable with
core (38 tools)yesdefault lean starter set
merge_requests (46 tools)noGITLAB_TOOLSETS=merge_requests
issues (24 tools)noGITLAB_TOOLSETS=issues
repositories (7 tools)noGITLAB_TOOLSETS=repositories
branches (16 tools)noGITLAB_TOOLSETS=branches
projects (11 tools)noGITLAB_TOOLSETS=projects
labels (5 tools)noGITLAB_TOOLSETS=labels
ci (4 tools)noGITLAB_TOOLSETS=ci
groups (1 tool)noGITLAB_TOOLSETS=groups
users (7 tools)noGITLAB_TOOLSETS=users
pipelines (58 tools)noGITLAB_TOOLSETS=core,pipelines (deprecated USE_PIPELINE; if GITLAB_TOOLS is unset, set GITLAB_TOOLS=validate_ci_lint,validate_project_ci_lint, otherwise append those tools instead of replacing the list)
milestones (17 tools)noGITLAB_TOOLSETS=core,milestones (deprecated USE_MILESTONE)
wiki (10 tools)noGITLAB_TOOLSETS=core,wiki (deprecated USE_GITLAB_WIKI)
releases (7 tools)noGITLAB_TOOLSETS=releases
tags (9 tools)noGITLAB_TOOLSETS=tags
snippets (5 tools)noGITLAB_TOOLSETS=snippets
workitems (18 tools)noGITLAB_TOOLSETS=workitems
webhooks (6 tools)noGITLAB_TOOLSETS=webhooks
search (3 tools)noGITLAB_TOOLSETS=search
variables (10 tools)noGITLAB_TOOLSETS=variables
dependency_proxy (4 tools)noGITLAB_TOOLSETS=dependency_proxy
vulnerabilities (4 tools)noGITLAB_TOOLSETS=vulnerabilities
orbit (4 tools)noGITLAB_TOOLSETS=orbit
api (1 tool)noGITLAB_TOOLSETS=api only (not all, not discover_tools, not GITLAB_TOOLS)

Enable all discoverable toolsets: GITLAB_TOOLSETS=all (does not enable api). Restore the pre-lean default with GITLAB_TOOLSETS=merge_requests,issues,repositories,branches,projects,labels,ci,groups,users. Use GITLAB_TOOLS to enable individual tools outside their toolset, except explicit-only tools such as gitlab_api_request. discover_tools can list and activate opt-in categories for the current session, except api. execute_graphql is not in a toolset; enable it explicitly with GITLAB_TOOLS=execute_graphql. USE_GITLAB_WIKI, USE_MILESTONE, and USE_PIPELINE are deprecated (removed in next major (v3.0.0)). If you already set GITLAB_TOOLSETS, append the toolset to your existing list instead of replacing it. If GITLAB_TOOLS is unset, set GITLAB_TOOLS=validate_ci_lint,validate_project_ci_lint. If it is already set, append those two tools instead of replacing that list.

gitlab_api_request bypasses GITLAB_ALLOWED_GROUPS and other group restrictions, project allowlists, tool-level restrictions (GITLAB_TOOLS, GITLAB_DENIED_TOOLS_REGEX on other tools), and individual tool safety checks. The full token permission scope is exposed. Prompt injection can drive this tool. Operators who rely on these restrictions must NOT enable it. With GITLAB_ALLOWED_PROJECT_IDS or a session project scope, only /projects/:id paths for an allowed project are accepted; /search, /users, /groups/:id, /runners, and other paths are rejected. Body and query parameters that name another project are not checked. GITLAB_PROJECT_ID and OAuth group allowlists are not enforced.

The per-toolset counts above sum to 315 because the 38 core tools are each also listed in their full category (get_branch and list_branches additionally appear in both merge_requests and branches); the unique tool count across all toolsets is 275.

Key Workflows

Code Review (see reference/code-review.md)

  1. list_merge_request_changed_files - get file paths only (no diffs)
  2. get_merge_request_file_diff - get diffs for 3-5 files per call (batch)
  3. create_merge_request_thread or create_draft_note - leave review comments
  4. bulk_publish_draft_notes - publish all drafts at once

MR Lifecycle (see reference/merge-requests.md)

create_merge_request -> review -> approve_merge_request -> merge_merge_request

Issue Management (see reference/issues.md)

create_issue -> create_issue_link -> create_issue_note -> update_issue

Use update_issue_description_patch for small edits to long issue descriptions instead of resending the full body.

Projects & Namespaces

  • get_project, list_projects, update_project - inspect or change project settings
  • list_project_members, list_group_members - search members by name or username within a project or group
  • list_namespaces, get_namespace, verify_namespace - find target namespaces before creating projects/groups
  • verify_namespace.parent_id scopes nested namespace checks
  • create_repository.namespace_id creates a project under a group namespace

Branches & Commits

  • create_branch, list_branches, get_branch, delete_branch
  • Protected branches: list_protected_branches, get_protected_branch, protect_branch, update_protected_branch, unprotect_branch, update_default_branch (protect_branch only creates a rule and returns 409 when one exists; change an existing rule with update_protected_branch, using record ids from get_protected_branch, instead of unprotect + protect)
  • Commits: list_commits, get_commit, get_commit_diff, get_file_blame, list_commit_statuses, create_commit_status

Tags

  • list_tags, get_tag, create_tag, delete_tag, get_tag_signature
  • Protected tags: list_protected_tags, get_protected_tag, protect_tag, unprotect_tag (create_access_level is 0, 30, or 40; wildcards such as v* are supported)

CI

  • Lint configs: validate_ci_lint, validate_project_ci_lint
  • Catalog: list_ci_catalog_resources, get_ci_catalog_resource
  • Pipelines/jobs/deployments: see reference/pipelines.md

Work Items (see reference/work-items.md)

list_work_items -> get_work_item -> update_work_item -> create_work_item_note

Variables & Dependency Proxy

Enable with GITLAB_TOOLSETS=variables or GITLAB_TOOLSETS=dependency_proxy.

  • Variables: project/group CRUD tools (list_*_variables, get_*_variable, create_*_variable, update_*_variable, delete_*_variable)
  • Dependency proxy: get_dependency_proxy_settings, update_dependency_proxy_settings, list_dependency_proxy_blobs, purge_dependency_proxy_cache

Webhooks & Search

  • Webhooks: see reference/webhooks.md
  • Code search: see reference/search.md

Vulnerability Triage (see reference/vulnerability-triage.md)

Enable with GITLAB_TOOLSETS=vulnerabilities (requires GitLab Ultimate).

list_project_vulnerabilities -> get_vulnerability -> dismiss_vulnerability or confirm_vulnerability

File Operations

  • Read: get_file_contents, get_repository_tree
  • Write: create_or_update_file (single file), push_files (multiple files in one commit)

Token-saving rules

  • Do not dump a full get_merge_request_diffs payload into the conversation. List paths with list_merge_request_changed_files, then fetch 3–5 files per get_merge_request_file_diff call.
  • Prefer a jmespath filter or GITLAB_MCP_COMPACT_RESULTS / --compact-results before asking the model to read a large JSON reply.
  • Paginate get_pipeline_job_output with limit and offset instead of fetching an entire job log in one call.

Parameter Hints

  • project_id: numeric ID or URL-encoded path (group%2Fsubgroup%2Fproject)
  • namespace_id: numeric namespace ID for create_repository; use list_namespaces/verify_namespace first
  • parent_id: scope subgroup creation or verify_namespace for nested groups
  • MR lookup: provide merge_request_iid or source_branch
  • list_issues: default scope = created by current user. Use scope: "all" for all issues
  • list_merge_requests: without project_id returns user's MRs across all projects
  • rebase_merge_request: with wait true (default) returns the merge request plus previous_sha and head_changed
  • CI catalog resource lookup: provide exactly one of id or full_path
  • emoji reactions: merge request, issue, and work item reaction tools use GitLab emoji names like thumbsup, rocket, or eyes
  • work items: status and custom fields require GitLab Premium/Ultimate features
  • execute_graphql: escape double quotes in query strings

Destructive Tools (require caution)

cancel_pipeline, cancel_pipeline_job, delete_branch, delete_deployment, approve_deployment, delete_draft_note, delete_environment, erase_pipeline_job, delete_group_milestone, delete_group_variable, delete_group_wiki_page, delete_issue, delete_issue_emoji_reaction, delete_issue_link, delete_issue_note_emoji_reaction, delete_label, delete_merge_request_discussion_note, delete_merge_request_emoji_reaction, delete_merge_request_note, delete_merge_request_note_emoji_reaction, delete_milestone, delete_pipeline, delete_pipeline_schedule, delete_pipeline_schedule_variable, delete_pipeline_trigger, delete_project_variable, delete_release, delete_review_app_environments, delete_snippet, delete_tag, delete_webhook, delete_wiki_page, delete_work_item_emoji_reaction, delete_work_item_note_emoji_reaction, merge_merge_request, protect_branch, protect_tag, purge_dependency_proxy_cache, push_files, rebase_merge_request, stop_environment, stop_stale_environments, unprotect_branch, unprotect_tag, update_default_branch, update_protected_branch, gitlab_api_request

Advanced

  • Dynamic discovery: discover_tools lists and activates opt-in toolsets at runtime. It cannot activate api
  • Workflow guide: help returns on-demand guides (code-review, pipelines, issues, token-saving). Omit topic for the overview
  • Raw API: gitlab_api_request only when GITLAB_TOOLSETS lists api. Readonly is GET-only; modify rejects DELETE
  • GraphQL: execute_graphql for queries not covered by REST tools
  • Tool docs: docs/tools/ is generated from tools/registry.ts; prefer it for exact schemas
  • Remote MCP OAuth: when GITLAB_MCP_OAUTH=true, POST /register (DCR) is rate-limited per client IP (default 20/hour via MCP SDK; tune with OAUTH_REGISTER_RATE_LIMIT_PER_HOUR). Separate from MAX_REQUESTS_PER_MINUTE and GitLab API quotas — see environment-variables.md
  • Zoekt search: search_code, search_project_code, search_group_code (requires advanced search enabled)
  • Work Items: GraphQL-based alternative to issues (Premium/Ultimate features)

FAQ

What does the gitlab-mcp-skill skill do?

Use this skill when working with the GitLab MCP server tools for merge requests, issues, repositories, pipelines, work items, variables, dependency proxy, vulnerabilities, webhooks, search, CI catalog, and related GitLab workflows.

How do I install gitlab-mcp-skill?

Run npx skills add https://github.com/zereight/gitlab-mcp --skill gitlab-mcp-skill in your project. The skills CLI detects the agents you use and copies the skill into the right folder. For Claude Code you can also place the skill folder at ~/.claude/skills/gitlab-mcp-skill/ (personal) or .claude/skills/gitlab-mcp-skill/ (project).

Which AI agents can use gitlab-mcp-skill?

Any agent that supports the open Agent Skills format (a folder with a SKILL.md file), including Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, Windsurf, Cline, OpenCode and more.

Is gitlab-mcp-skill safe to install?

No partner security audit is available yet. Skills can run commands and scripts, so read the SKILL.md and any bundled files before installing.

Who maintains gitlab-mcp-skill?

It is published by zereight in zereight/gitlab-mcp. It has 1,121 recorded installs.

Popular ai & agents skills

View category →

google-agents-cli-publish

google/agents-cli

This skill should be used when the user wants to "publish an agent", "publish my ADK agent", "register an agent with Gemini", "publish to Gemini" (formerly Gemini Enterprise), or needs guidance on the agents-cli publish gemini command. Also use when the user wants to "manage agents in Agent Registry", "list/update/delete registered agents", or "register an MCP server". Covers ADK vs A2A registration modes, programmatic and interactive usage, flag reference, auto-detection from deployment metadata, Agent Registry fleet management, and troubleshooting. Part of the agents-cli skills suite. Do NOT use for deployment (use google-agents-cli-deploy).

AI & Agents513.9K installs

google-agents-cli-eval

google/agents-cli

This skill should be used when the user wants to "run an evaluation", "evaluate my agent", "evaluate my ADK agent", "write an eval dataset", "analyze eval failures", "compare eval results", "optimize agent", or needs guidance on the Gemini platform eval methodology and the Quality Flywheel. Covers eval metrics, dataset schema, LLM-as-judge scoring, and common failure causes. Applies to any agents-cli project, whatever framework the agent is written in. Do NOT use for agent API code patterns (ADK: use google-agents-cli-adk-code), deployment (use google-agents-cli-deploy), or project scaffolding (use google-agents-cli-scaffold).

AI & Agents513.5K installs

skill-creator

anthropics/skills

Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.

OfficialAI & Agents416.4K installs

codex-pet

prime-skills/runcomfy-agent-skills

Codex Pet generator on RunComfy. Build a Codex-compatible Codex Pet spritesheet.webp + pet.json from a single reference image, drop it into ${CODEXHOME:-$HOME/.codex}/pets/ / and Codex picks it up as a custom Codex Pet next to the 8 built-ins. This skill produces the exact Codex Pet atlas Codex expects (1536x1872 PNG/WebP, 8 cols x 9 rows, 192x208 cells, 9 animation states — idle, running-right, running-left, waving, jumping, failed, waiting, running, review). Calls OpenAI GPT Image 2 edit ONCE via the local RunComfy CLI as runcomfy run openai/gpt-image-2/edit to produce a canonical Codex Pet pose, then assembles all 9 animation rows programmatically with ImageMagick micro-transforms — no Codex Pro, no $imagegen, no OPENAIAPIKEY required, only RUNCOMFYTOKEN. Triggers on "codex pet", "create codex pet", "make codex pet", "hatch codex pet", "/hatch image", "desktop pet codex", "codex pets", "spritesheet.webp", or any explicit ask to build a custom pet for OpenAI Codex.

AI & Agents402.1K installs

full-output-enforcement

leonxlnx/taste-skill

Overrides default LLM truncation behavior. Enforces complete code generation, bans placeholder patterns, and handles token-limit splits cleanly. Apply to any task requiring exhaustive, unabridged output.

AI & Agents401K installs

executing-plans

obra/superpowers

Use when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is available

AI & Agents245.7K installs