GitLab MCP Server

@owayo

リポジトリ

基本情報

カテゴリ

バージョン管理

ライセンス

MIT license

トランスポート

stdio

作者

owayo

GitLab MCP Server について

概要はまだありません

GitLab MCP Server の設定

以下の設定を使って、このサーバーを MCP 対応クライアントに追加してください。

{
  "mcpServers": {
    "gitlab-mcp-server-owayo": {
      "command": "uv",
      "args": [
        "sync"
      ]
    }
  }
}

GitLab MCP Server のツール

ツール一覧はまだありません

この掲載には表示できるツール一覧がまだありません。サーバーにツールがないという意味ではありません。対応機能はプロジェクトのドキュメントをご確認ください。

ツールは README から自動的に抽出されます。メンテナーは ## Tools という見出しの下に記載することで、このタブに反映できます。

概要

What is GitLab-MCP-Server?

GitLab-MCP-Server is a Model Context Protocol (MCP) server that integrates with GitLab to fetch pipeline failure details, unresolved merge request review comments, and MR changes from a specific project. It provides this data to AI assistants (e.g., Claude) so they can help diagnose issues, address review feedback, and review code changes.

How to use GitLab-MCP-Server?

Install via uv (uv sync), obtain a GitLab API token with read_api scope, and set the environment variables GITLAB_URL, GITLAB_PROJECT_NAME, GITLAB_API_KEY, and GIT_REPO_PATH. Add the server configuration to Claude for Desktop (claude_desktop_config.json) or Cursor (.cursor/mcp.json) using the uv command and main.py script.

Key features of GitLab-MCP-Server

Fetches console output from failed pipeline jobs.
Retrieves unresolved, file‑linked MR review comments.
Obtains MR diff between base commit and local repository state.
Provides data directly to AI assistants via MCP tools.

Use cases of GitLab-MCP-Server

AI assistant analyzes pipeline failures and suggests fixes.
AI assistant reviews unresolved MR comments and helps address them.
AI assistant reviews MR changes against local working state for code review.
Integration with coding tools (Claude Desktop, Cursor) for automated assistance.

よくある質問

What GitLab API token permissions are required?

A token with the `read_api` scope is needed.

What tools does GitLab-MCP-Server expose?

Three tools: `get_pipeline_failed_jobs()`, `get_review_comments()`, and `get_review_changes()`.

How do I configure GitLab-MCP-Server for Claude for Desktop?

Add an entry in `claude_desktop_config.json` with `uv` as the command, the server directory, `main.py`, and the required environment variables.

What environment variables are required?

`GITLAB_URL`, `GITLAB_PROJECT_NAME`, `GITLAB_API_KEY`, and `GIT_REPO_PATH`.

Can GitLab-MCP-Server be used with Cursor?

Yes, by adding a configuration in `.cursor/mcp.json` that passes the environment variables as arguments to the command.

「バージョン管理」の他のコンテンツ

AIO-MCP Server

athapong

🚀 All-in-one MCP server with AI search, RAG, and multi-service integrations (GitLab/Jira/Confluence/YouTube) for AI-enhanced development workflows. Folk from https://github.com/nguyenvanduocit/all-in-one-model-context-protocol

Github Mcp Server

github

GitHub's official MCP Server

31.3K

Jira MCP

nguyenvanduocit

A Go-based MCP (Model Control Protocol) connector for Jira that enables AI assistants like Claude to interact with Atlassian Jira. This tool provides a seamless interface for AI models to perform common Jira operations including issue management, sprint planning, and workflow tra

Atlassian Data Center MCP

b1ff

MCP servers for the Atlassian products (Bitbucket, Confluence, JIRA) of the Data Center version

🚀 GitLab MR MCP

kopfrechner

Interact seamlessly with GitLab repositories to manage merge requests and issues. Fetch details, add comments, and streamline your code review process with ease.