Ross ROSS = Recommend OSS · open-source software intelligence for agents

zereight/gitlab-mcp

First gitlab mcp for you, building together observed · 2026-08-28

github.com/zereight/gitlab-mcp · homepage · TypeScript · MIT (permissive) observed · 2026-08-28

Health v2 · maintenance only

83/100

  • Activity 99
  • Release rhythm 87
  • Longevity 40
How is this computed?

round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10) — computed 2026-09-03. Adoption (stars, forks) is never an input.

  • gap_med: 2
  • age_days: 569
  • days_rel: 11
  • days_push: 9
  • n_releases_24m: 110

Full methodology

Adoption not part of the score

1926 stars · 342 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-30, confidence not recorded

A Model Context Protocol (MCP) server exposing GitLab APIs (projects, merge requests, issues, pipelines, wikis, releases, and more) to AI clients like Claude, Cursor, and Copilot. It offers ~217 granular tools with runtime discovery, multiple auth methods, and stdio/SSE/Streamable HTTP transports.

Use cases

  • let an AI agent review and comment on GitLab merge requests
  • manage GitLab issues and pipelines from Claude or Cursor
  • connect my coding assistant to a self-hosted GitLab instance
  • browse repository files and diffs through an MCP client
  • automate GitLab release and milestone management via AI
  • set up a GitLab MCP server with OAuth or a personal access token

When to choose

  • you want an agent-workflow-optimized GitLab MCP with many granular tools and runtime tool discovery
  • you need flexible auth (PAT, OAuth2, proxy, remote authorization) and multiple transports
  • you use self-hosted GitLab instances or need dynamic API URL routing
  • you want batched two-step MR diff review for AI code review

When to avoid

  • you prefer a small grouped toolset (CQRS-style) for enterprise multi-instance setups
  • you need a non-GitLab platform like GitHub or Bitbucket
  • you don't use any MCP-compatible AI client

Facets

service · maturity active

mcp api-framework developer-tools auth developer-tools version-control large-language-models cli cross-platform self-hosted gitlab mcp-server model-context-protocol ai-agent-tools devops-automation merge-requests ci-pipelines ai-agents automation nodejs

2 sources

Member repositories

RepositoryRoleHealth v2
zereight/gitlab-mcpmain83

For agents

markdown · JSON · MCP: product_card(name="zereight/gitlab-mcp")

Data as of 2026-08-30T08:39:29.467469+00:00 · Report a problem