mshegolev

gitlab-ci-mcp

Community mshegolev
Updated

MCP server for GitLab CI/CD — pipelines, schedules, MRs, files. Works with any GitLab (SaaS or self-hosted).

gitlab-ci-mcp

PyPIPythonLicense: MITDownloads

MCP server for GitLab CI/CD. Lets an LLM agent (Claude Code, Cursor, OpenCode, DevX Agent, etc.) work with pipelines, jobs, schedules, branches, tags, merge requests and repository files.

Python, FastMCP, stdio transport.

Works with any GitLab — SaaS gitlab.com or self-hosted / on-prem. Designed with corporate networks in mind: configurable NO_PROXY handling, optional SSL-verify toggle, per-project scoping via env vars.

Design highlights

  • Tool annotations — every tool carries readOnlyHint / destructiveHint / idempotentHint / openWorldHint so MCP clients can classify operations (e.g. ask for confirmation only on destructive ones like gitlab_merge_mr, gitlab_delete_schedule).
  • Structured output on every tool — each tool declares a TypedDict return type, so FastMCP auto-generates an outputSchema and every result carries structuredContent alongside a pre-rendered markdown text block. Clients that can render structured data use it; agents that prefer compact text get the markdown. No response_format parameter needed.
  • Structured errors — authentication, 404, 403, 429 (rate-limit), 5xx, missing-env errors are converted to actionable ToolError messages (e.g. "GitLab authentication failed… verify GITLAB_TOKEN has api scope") and surfaced as isError=True results.
  • Pydantic input validation — every argument has typed constraints (ranges, lengths, literals) auto-exposed as JSON Schema.
  • Project scoping per call — every tool accepts an optional project_path that overrides GITLAB_PROJECT_PATH for cross-project queries.
  • Pagination — list tools return a pagination block with page, total, has_more, next_page and a next-page hint in the markdown footer.
  • MCP Context integrationgitlab_pipeline_health and gitlab_get_job_log are async and emit info logs / report_progress events through the MCP Context so clients can show progress bars.
  • MCP Resourcesgitlab://project/info and gitlab://project/ci-config mirror common lookups for clients that prefer the Resource model over tools.
  • Lifespan managementpython-gitlab HTTP sessions are closed cleanly on server shutdown via an asynccontextmanager lifespan hook.
  • Log grepgitlab_get_job_log accepts grep_pattern + grep_context (surrounding lines) for regex-filtering megabyte-scale CI logs without pulling the whole trace into agent context.

Threading model

FastMCP automatically runs synchronous tools in a worker thread(anyio.to_thread.run_sync), so they do not block the asyncio event loop —python-gitlab is a synchronous library and wrapping every call inasyncio.to_thread ourselves would be ceremony. Tools that benefit from theMCP Context (progress, info logs) are written as async def and explicitlywrap python-gitlab calls with asyncio.to_thread.

Features

23 tools covering the everyday CI/CD surface:

Pipelinesgitlab_list_pipelines · gitlab_get_pipeline · gitlab_get_pipeline_jobs · gitlab_get_job_log · gitlab_trigger_pipeline · gitlab_retry_pipeline · gitlab_cancel_pipeline · gitlab_pipeline_health

Schedulesgitlab_list_schedules · gitlab_create_schedule · gitlab_update_schedule · gitlab_delete_schedule

Branches & tagsgitlab_list_branches · gitlab_list_tags · gitlab_compare_branches

Merge requestsgitlab_list_merge_requests · gitlab_get_merge_request · gitlab_get_merge_request_changes · gitlab_create_merge_request · gitlab_merge_mr

Repository & projectgitlab_get_file · gitlab_list_repository_tree · gitlab_project_info

Pipeline health report

gitlab_pipeline_health returns a ready-to-read summary over 7/30 days:

Last 7d:  96.4%  up   | 27/28 success
Last 30d: 92.1%       | 105/114 success
Last 10:  success success success failed success ...

Handy for on-call / triage: покажи health master за последние 7 дней.

Installation

Requires Python 3.10+.

# via uvx (recommended)
uvx --from gitlab-ci-mcp gitlab-ci-mcp

# or via pip/pipx
pipx install gitlab-ci-mcp

Configuration

All config is via environment variables:

Variable Required Description
GITLAB_URL yes Base URL, e.g. https://gitlab.example.com
GITLAB_TOKEN yes Personal Access Token with api scope
GITLAB_PROJECT_PATH yes Default project, e.g. my-org/my-repo
GITLAB_SSL_VERIFY no true (default) / false
GITLAB_NO_PROXY_DOMAINS no Comma-separated domains to add to NO_PROXY (useful in corp networks behind a local HTTP proxy — e.g. .corp.example.com,gitlab.internal)

Every tool accepts an optional project_path arg that overrides GITLAB_PROJECT_PATH per call — useful for cross-project queries.

Claude Code

Full walkthrough: docs/claude-code.md — prerequisites, two install paths, multi-project setup, self-hosted GitLab behind a corp proxy, troubleshooting, uninstall.

Short version:

claude mcp add gitlab uvx --from gitlab-ci-mcp gitlab-ci-mcp \
  --env GITLAB_URL=https://gitlab.example.com \
  --env GITLAB_TOKEN=glpat-xxxxxx \
  --env GITLAB_PROJECT_PATH=my-org/my-repo

Or in ~/.claude.json / project .mcp.json:

{
  "mcpServers": {
    "gitlab": {
      "type": "stdio",
      "command": "uvx",
      "args": ["--from", "gitlab-ci-mcp", "gitlab-ci-mcp"],
      "env": {
        "GITLAB_URL": "https://gitlab.example.com",
        "GITLAB_TOKEN": "${GITLAB_TOKEN}",
        "GITLAB_PROJECT_PATH": "my-org/my-repo",
        "GITLAB_SSL_VERIFY": "true"
      }
    }
  }
}

Check:

claude mcp list
# gitlab: uvx --from gitlab-ci-mcp gitlab-ci-mcp - ✓ Connected

Cursor / OpenCode / DevX Agent

Same idea — point the MCP config to uvx --from gitlab-ci-mcp gitlab-ci-mcp with the env vars above. See each tool's own MCP config syntax.

Example prompts

что сломалось в последнем pipeline master
покажи health master за 7 дней для проекта my-org/other-repo
создай MR из feature/foo в master с title "feat: foo"
покажи содержимое .gitlab-ci.yml из master

Rate limits & connection reuse

GitLab enforces a per-user rate limit (typically 2000 req/h for the REST API,configurable by the admin — see your instance's /admin/application_settings/network).

  • The server caches one python-gitlab HTTP session per project_path, sorepeated tool calls against the same project reuse the connection and do notre-authenticate each time.
  • List tools default to per_page=20 to keep a single call within a smallnumber of API requests.
  • If you hit a 429 Too Many Requests, the error handler returns an actionablemessage — wait and try again with larger per_page or fewer calls.

Self-hosted GitLab behind a corporate proxy

When your laptop has a local HTTP proxy (e.g. http://127.0.0.1:3128 for corp web access) but GitLab is on the intranet, the proxy intercepts and kills internal requests. Two options:

  1. Set GITLAB_NO_PROXY_DOMAINS — the server will add them to NO_PROXY at startup and clear HTTP_PROXY/HTTPS_PROXY from its own process so they don't affect GitLab traffic.
  2. Pass explicitly empty HTTP_PROXY="" etc. in the MCP env section.

Development

git clone https://github.com/mshegolev/gitlab-ci-mcp
cd gitlab-ci-mcp
python -m venv .venv && . .venv/bin/activate
pip install -e '.[dev]'
pytest

Run the server directly (stdio transport, waits on stdin for MCP messages):

GITLAB_URL=... GITLAB_TOKEN=... GITLAB_PROJECT_PATH=... gitlab-ci-mcp

License

MIT — see LICENSE.

Acknowledgements

Built on python-gitlab and the MCP Python SDK.

MCP Server · Populars

MCP Server · New

    YV17labs

    ghostdesk

    Give any AI agent a full desktop — it sees the screen, clicks, types, and runs apps like a human. Automate anything with a UI: browsers, legacy software, internal tools. No API needed. One Docker command.

    Community YV17labs
    remotebrowser

    mcp

    Free your data

    Community remotebrowser
    Decodo

    Decodo MCP Server

    The Decodo MCP server which enables MCP clients to interface with services.

    Community Decodo
    kuberstar

    Qartez MCP

    Semantic code intelligence MCP server for Claude Code - project maps, symbol search, impact analysis, and more

    Community kuberstar
    aovestdipaperino

    tokensave

    Rust port of CodeGraph — a local-first code intelligence system that builds semantic knowledge graphs from codebases. Ported from the original TypeScript implementation by @colbymchenry.

    Community aovestdipaperino