GitLab MCP Server

GitLab MCP Server

Enables GitLab integration through MCP, supporting code review and project management via natural language.

Category
访问服务器

README

GitLab MCP Server (in Python)

Model Context Protocol (MCP) server for GitLab integration, built on FastMCP.

This server is implemented in Python, with fastmcp.

Quick Start

  1. Build the Docker image:
docker build -t gitlab-mcp-server .

Integration with Cursor/Claude

In MCP Settings -> Add MCP server, add this config:

{
  "mcpServers": {
    "gitlab": {
      "command": "docker",
      "args": [
        "run",
        "--rm",
        "-i",
        "-e",
        "GITLAB_TOKEN",
        "-e",
        "GITLAB_URL",
        "gitlab-mcp-server:latest"
      ],
      "env": {
        "GITLAB_TOKEN": "token",
        "GITLAB_URL": "https://gitlab.com/"
      }
    }
  }
}

Note: Don't forget to replace GITLAB_TOKEN and GITLAB_URL values with your actual GitLab credentials and instance URL.

Getting GitLab Token

  1. Log in to your GitLab account
  2. Go to Settings -> Access Tokens
  3. Create a new token:
    • Scopes: select the necessary permissions:
      • api - for API access
      • read_repository - for reading repositories
      • write_repository - for writing to repositories
  4. Click "Create personal access token"
  5. Copy the generated token (it will be shown only once!)

Prompt (rule) for review

Here are some suggestions to improve and clarify your review.mdc rules for code review:


review.mdc (Improved Version)

Purpose:
Guidelines for conducting code reviews in the current branch, focusing on diffs with the origin/master branch, and integrating with the MCP GitLab server.


1. Review Scope

  • Review only the changes in the current branch compared to the origin/master branch.
  • Locate the corresponding Merge Request (MR) for this branch in GitLab using MCP tools.

2. Review Structure

  • Summary of Changes:

    • Provide a concise summary divided into two sections:
      • Business Changes: Describe the impact on business logic, user experience, or requirements.
      • Code Changes: Summarize technical modifications, refactoring, or architectural shifts.
  • Logical Breakdown:

    • Divide the changes into logical blocks (e.g., features, bug fixes, refactoring).
    • List these blocks clearly.
  • Detailed Review:

    • For each block, provide:
      • A brief description.
      • Suggestions for improvement (code quality, readability, maintainability, performance, etc.).
      • Identification of potential bugs or issues.
      • Illustrate type of suggestion with emoji.
      • Link to line in code.
    • If the terms of reference (requirements/spec) are not provided, request them to ensure accurate review.

3. Suggestions and Comments

  • Propose to post line comments with suggestions directly in the Merge Request using the MCP GitLab server.
  • All line comments in Merge Request must:
    • Begin with "[AI]".
    • Be specific, actionable, and reference the relevant code line(s).
    • Do not write a lot of text. Smaller is better.

4. Additional Guidelines

  • Prioritize clarity, conciseness, and constructiveness in all feedback.
  • Focus on both business logic and code quality.
  • Ensure all suggestions are justified and, where possible, reference best practices or project standards.
  • If you identify a bug, explain the reasoning and potential impact.

Contributing

Feel free to:

  • Add new GitLab integration tools and features
  • Improve existing functionality
  • Fix bugs
  • Enhance documentation
  • Suggest improvements

To contribute:

  1. Fork the repository
  2. Create your feature branch
  3. Commit your changes
  4. Open a Pull Request

All contributions, big or small, are appreciated!

推荐服务器

Baidu Map

Baidu Map

百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。

官方
精选
JavaScript
Playwright MCP Server

Playwright MCP Server

一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。

官方
精选
TypeScript
Magic Component Platform (MCP)

Magic Component Platform (MCP)

一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。

官方
精选
本地
TypeScript
Audiense Insights MCP Server

Audiense Insights MCP Server

通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。

官方
精选
本地
TypeScript
VeyraX

VeyraX

一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。

官方
精选
本地
graphlit-mcp-server

graphlit-mcp-server

模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。

官方
精选
TypeScript
Kagi MCP Server

Kagi MCP Server

一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。

官方
精选
Python
e2b-mcp-server

e2b-mcp-server

使用 MCP 通过 e2b 运行代码。

官方
精选
Neon MCP Server

Neon MCP Server

用于与 Neon 管理 API 和数据库交互的 MCP 服务器

官方
精选
Exa MCP Server

Exa MCP Server

模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。

官方
精选