GitLab Merge Request Server

编码与调试

by kevinlin

让 AI agents 通过协议直接操作 GitLab 仓库,管理 merge requests 和 issues,列出项目、获取 diff、添加评论并更新元数据,提升协作与自动化效率。

什么是 GitLab Merge Request Server

让 AI agents 通过协议直接操作 GitLab 仓库,管理 merge requests 和 issues,列出项目、获取 diff、添加评论并更新元数据,提升协作与自动化效率。

README

GitHub stars License smithery badge

🚀 GitLab MR MCP

An MCP server that enables AI agents to seamlessly interact with GitLab repositories, manage merge requests, review code, and post comments directly from your AI assistant.

📌 Overview

This project implements a server using the Model Context Protocol (MCP) that allows AI agents to interact with GitLab repositories. It provides tools for:

  • Listing available GitLab projects
  • Fetching merge request details and comments
  • Getting merge request diffs
  • Adding comments to merge requests
  • Adding line-specific comments to code in merge request diffs
  • Fetching issue details
  • Setting merge request title and description

📦 Installation

🚀 Using npx (Recommended)

You can run this package directly using npx without installation:

bash
# Set environment variables
export MR_MCP_GITLAB_HOST="your_gitlab_host"
export MR_MCP_GITLAB_TOKEN="your_gitlab_token"

# Run with npx
npx gitlab-mr-mcp@0.1.0

For MCP client configuration when using npx:

json
{
  "mcpServers": {
    "gitlab-mr-mcp": {
      "command": "npx",
      "args": ["gitlab-mr-mcp@0.1.0"],
      "env": {
        "MR_MCP_GITLAB_HOST": "your_gitlab_host",
        "MR_MCP_GITLAB_TOKEN": "your_gitlab_token"
      }
    }
  }
}

🛠️ Manual Installation

🔧 Prerequisites

  • Node.js
  • GitLab access token with API access
  • GitLab project ID(s)

📖 Setup

  1. Clone this repository
  2. Install dependencies:
bash
npm install
  1. Add the following to your MCP client configuration:
json
{
  "mcpServers": {
    "gitlab-mr-mcp": {
      "command": "node",
      "args": ["/path/to/gitlab-mr-mcp/index.js"],
      "env": {
        "MR_MCP_GITLAB_HOST": "your_gitlab_host",
        "MR_MCP_GITLAB_TOKEN": "your_gitlab_token"
      }
    }
  }
}

🛠️ Available Tools

  • get_projects Gets a list of GitLab projects accessible with your token.

  • list_open_merge_requests Lists all open merge requests in the specified project.

  • get_merge_request_details Gets detailed information about a specific merge request.

  • get_merge_request_comments Gets comments from a specific merge request, including discussion notes and diff notes.

  • add_merge_request_comment Adds a general comment to a merge request.

  • add_merge_request_diff_comment Adds a comment to a specific line in a file within a merge request.

  • get_merge_request_diff Gets the diff for a merge request.

  • get_issue_details Gets detailed information about a specific issue.

  • set_merge_request_title Set the title of a merge request

  • set_merge_request_description Set the description of a merge request

🏗️ Development

🔍 Running Inspector

Set up environment variables:

bash
export MR_MCP_GITLAB_TOKEN=your_gitlab_token
export MR_MCP_GITLAB_HOST=your_gitlab_host

# Optional evn vars to filter the projects the `get_projects` tool has access to:
# https://docs.gitlab.com/api/access_requests/#valid-access-levels
export MR_MCP_MIN_ACCESS_LEVEL=min_access_level
# Search term that should match the project path or name 
export MR_MCP_PROJECT_SEARCH_TERM=term 

For use with MCP clients, you can run:

bash
npx -y @modelcontextprotocol/inspector npm start

🛠️ Troubleshooting

If you encounter issues with the GitLab MR MCP server:

  1. Check MCP client logs first - Enable debug logging in your MCP client to see detailed error messages and connection status. This will help identify if the issue is with the server connection, authentication, or specific tool calls.

  2. If you encounter permissions issues (403 Forbidden), check:

    • Your GitLab token has the proper scopes (api, read_api)
    • The token user has proper access to the projects
    • The project IDs are correct

📜 License

MIT

常见问题

GitLab Merge Request Server 是什么?

让 AI agents 通过协议直接操作 GitLab 仓库,管理 merge requests 和 issues,列出项目、获取 diff、添加评论并更新元数据,提升协作与自动化效率。

相关 Skills

网页构建器

by anthropics

Universal
热门

面向复杂 claude.ai HTML artifact 开发,快速初始化 React + Tailwind CSS + shadcn/ui 项目并打包为单文件 HTML,适合需要状态管理、路由或多组件交互的页面。

在 claude.ai 里做复杂网页 Artifact 很省心,多组件、状态和路由都能顺手搭起来,React、Tailwind 与 shadcn/ui 组合效率高、成品也更精致。

编码与调试
未扫描172.7k

网页应用测试

by anthropics

Universal
热门

用 Playwright 为本地 Web 应用编写自动化测试,支持启动开发服务器、校验前端交互、排查 UI 异常、抓取截图与浏览器日志,适合调试动态页面和回归验证。

借助 Playwright 一站式验证本地 Web 应用前端功能,调 UI 时还能同步查看日志和截图,定位问题更快。

编码与调试
未扫描172.7k

前端设计

by anthropics

Universal
热门

面向组件、页面、海报和 Web 应用开发,按鲜明视觉方向生成可直接落地的前端代码与高质感 UI,适合做 landing page、Dashboard 或美化现有界面,避开千篇一律的 AI 审美。

想把页面做得既能上线又有设计感,就用前端设计:组件到整站都能产出,难得的是能避开千篇一律的 AI 味。

编码与调试
未扫描172.7k

相关 MCP Server

GitHub

编辑精选

by GitHub

热门

GitHub 是 MCP 官方参考服务器,让 Claude 直接读写你的代码仓库和 Issues。

这个参考服务器解决了开发者想让 AI 安全访问 GitHub 数据的问题,适合需要自动化代码审查或 Issue 管理的团队。但注意它只是参考实现,生产环境得自己加固安全。

编码与调试
89.7k

by Context7

热门

Context7 是实时拉取最新文档和代码示例的智能助手,让你告别过时资料。

它能解决开发者查找文档时信息滞后的问题,特别适合快速上手新库或跟进更新。不过,依赖外部源可能导致偶尔的数据延迟,建议结合官方文档使用。

编码与调试
60.2k

by tldraw

热门

tldraw 是让 AI 助手直接在无限画布上绘图和协作的 MCP 服务器。

这解决了 AI 只能输出文本、无法视觉化协作的痛点——想象让 Claude 帮你画流程图或白板讨论。最适合需要快速原型设计或头脑风暴的开发者。不过,目前它只是个基础连接器,你得自己搭建画布应用才能发挥全部潜力。

编码与调试
49.9k

评论