agentleFS
Sign inStart free
zereightzereight/gitlab-mcp/docs/llms.txt

gitlab-mcp

llms.txt2.1k starsChanged 20 days agoMITView on GitHub

Agent-workflow-optimized GitLab MCP. Default list: 40 tools (38 core + discovertools + help). 278 tools exist in total. Activate more at runtime with discovertools. Package: @zereight/mcp-gitlab · Binary: zereight-mcp-gitlab · License: MIT Docs: https://zereight.github.io/gitlab-mcp/ · Full text: ./llms-full.txt

We split this llms.txt into the rules it gives an agent

1 rule. About 0 are common, 0 are distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈0

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 1

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Do not enable the api toolset unless you accept that gitlab_api_request bypasses allowlists and tool filters.

    line 34

≈ “Common” is an estimate: at least 1 in 5 of the 3,225 llms.txt files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
llms.txt
# GitLab MCP Server

> Agent-workflow-optimized GitLab MCP. Default list: 40 tools (38 `core` + `discover_tools` + `help`). 278 tools exist in total. Activate more at runtime with `discover_tools`.

Package: `@zereight/mcp-gitlab` · Binary: `zereight-mcp-gitlab` · License: MIT
Docs: https://zereight.github.io/gitlab-mcp/ · Full text: ./llms-full.txt

## Install

- Local IDE (stdio + PAT): Claude Code / Codex one-liners in the README; Cursor deeplink in the README
- Shared HTTP: Streamable HTTP at `https://mcp.example.com/mcp`
- Claude.ai: public HTTPS + `GITLAB_MCP_OAUTH`
- Equal non-MCP path: `npx skills add zereight/gitlab-mcp --skill gitlab-mcp-skill` + `zereight-mcp-gitlab` CLI

## Docs

- [Getting Started](getting-started/index.md): auth and transport
- [CLI without MCP](getting-started/cli-without-mcp.md): Skill + CLI
- [Claude Code](clients/claude-code.md)
- [Cursor](clients/cursor.md)
- [VS Code](clients/vscode.md)
- [Codex](clients/codex.md)
- [JSON clients](clients/json-clients.md)
- [OAuth2](auth/oauth-setup.md)
- [Environment variables](configuration/environment-variables.md)
- [Tools](tools/index.md): generated reference
- [Skill](https://github.com/zereight/gitlab-mcp/blob/main/skills/gitlab-mcp/SKILL.md)

## Agent rules

- `project_id` is a numeric ID or URL-encoded path (`group%2Fproject`). MR `!123` → `merge_request_iid=123`.
- MR review: `list_merge_request_changed_files` then batched `get_merge_request_file_diff`. Do not dump full `get_merge_request_diffs`.
- Shrink results with `jmespath` or `GITLAB_MCP_COMPACT_RESULTS`. Paginate job logs. Use the CLI for full payloads.
- Do not enable the `api` toolset unless you accept that `gitlab_api_request` bypasses allowlists and tool filters.

Download now (ZIP)

Trending

Steady: 0 new projects took it in the last 4 weeks, none the 4 weeks before.thin data

Week of Aug 30: 0 new projectsWeek of Sep 6: 0 new projectsWeek of Sep 13: 0 new projectsWeek of Sep 20: 0 new projectsWeek of Sep 27: 0 new projectsWeek of Oct 4: 0 new projectsWeek of Oct 11: 0 new projectsWeek of Oct 18: 0 new projects
Aug 2026Sep 2026Oct 2026
New projects taking a version of this file each week, over the 8 weeks our latest run read: only 0 in all, so this is a hint, not a trend.

Who's talking about zereight/gitlab-mcp

The biggest 5 of 48 mentions linking to the repository that our crawl found. Each line is their own headline.

See all 48

Talked about on GitHub and Bluesky (48 times).

On GitHub · 47

42 more on GitHub

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free