GitLab MCP Server

GitLab MCP Server

An MCP server for the GitLab API that enables comprehensive project management, file operations, and issue tracking. It supports automated branch creation, batch file pushes, and interaction with merge requests and CI/CD logs.

Category
访问服务器

README

🦊 GitLab MCP Server

🚀 MCP Server for the GitLab API, enabling project management, file operations, and more.

✨ Features

  • 🌿 Automatic Branch Creation: When creating/updating files or pushing changes, branches are automatically created if they don't exist
  • 🛡️ Comprehensive Error Handling: Clear error messages for common issues
  • 📚 Git History Preservation: Operations maintain proper Git history without force pushing
  • 📦 Batch Operations: Support for both single-file and multi-file operations

🔧 Tools

  1. create_or_update_file

    • Create or update a single file in a project
    • Inputs:
      • project_id (string): Project ID or URL-encoded path
      • file_path (string): Path where to create/update the file
      • content (string): Content of the file
      • commit_message (string): Commit message
      • branch (string): Branch to create/update the file in
      • previous_path (optional string): Path of the file to move/rename
    • Returns: File content and commit details
  2. push_files

    • Push multiple files in a single commit
    • Inputs:
      • project_id (string): Project ID or URL-encoded path
      • branch (string): Branch to push to
      • files (array): Files to push, each with file_path and content
      • commit_message (string): Commit message
    • Returns: Updated branch reference
  3. search_repositories

    • Search for GitLab projects
    • Inputs:
      • search (string): Search query
      • page (optional number): Page number for pagination
      • per_page (optional number): Results per page (default 20)
    • Returns: Project search results
  4. create_repository

    • Create a new GitLab project
    • Inputs:
      • name (string): Project name
      • description (optional string): Project description
      • visibility (optional string): 'private', 'internal', or 'public'
      • initialize_with_readme (optional boolean): Initialize with README
    • Returns: Created project details
  5. get_file_contents

    • Get contents of a file or directory
    • Inputs:
      • project_id (string): Project ID or URL-encoded path
      • file_path (string): Path to file/directory
      • ref (optional string): Branch/tag/commit to get contents from
    • Returns: File/directory contents
  6. create_issue

    • Create a new issue
    • Inputs:
      • project_id (string): Project ID or URL-encoded path
      • title (string): Issue title
      • description (optional string): Issue description
      • assignee_ids (optional number[]): User IDs to assign
      • labels (optional string[]): Labels to add
      • milestone_id (optional number): Milestone ID
    • Returns: Created issue details
  7. create_merge_request

    • Create a new merge request
    • Inputs:
      • project_id (string): Project ID or URL-encoded path
      • title (string): MR title
      • description (optional string): MR description
      • source_branch (string): Branch containing changes
      • target_branch (string): Branch to merge into
      • draft (optional boolean): Create as draft MR
      • allow_collaboration (optional boolean): Allow commits from upstream members
    • Returns: Created merge request details
  8. get_merge_request_raw_diff

    • Get a merge request information of the difference in a raw format
    • Inputs:
      • project_id (string): Project ID or URL-encoded path
      • merge_request_id (string): ID of the merge request
    • Returns: The difference of the merge request in a raw format
  9. fork_repository

    • Fork a project
    • Inputs:
      • project_id (string): Project ID or URL-encoded path
      • namespace (optional string): Namespace to fork to
    • Returns: Forked project details
  10. create_branch

  • Create a new branch
  • Inputs:
    • project_id (string): Project ID or URL-encoded path
    • branch (string): Name for new branch
    • ref (optional string): Source branch/commit for new branch
  • Returns: Created branch reference
  1. get_job_logs
  • Retrieve the logs from a job
  • Inputs:
    • project_id (string): Project ID or URL-encoded path
    • job_id (string): ID of the job
  • Returns: The logs of the job

⚙️ Setup

🔑 Personal Access Token

Create a GitLab Personal Access Token with appropriate permissions:

  • Go to User Settings > Access Tokens in GitLab
  • Select the required scopes:
    • api for full API access
    • read_api for read-only access
    • read_repository and write_repository for repository operations
  • Create the token and save it securely

💻 Usage with Claude Desktop

Add the following to your claude_desktop_config.json:

🐳 Docker

{
  "mcpServers": {
    "gitlab": {
      "command": "docker",
      "args": [
        "run",
        "--rm",
        "-i",
        "-e",
        "GITLAB_PERSONAL_ACCESS_TOKEN",
        "-e",
        "GITLAB_API_URL",
        "mcp/gitlab"
      ],
      "env": {
        "GITLAB_PERSONAL_ACCESS_TOKEN": "<YOUR_TOKEN>",
        "GITLAB_API_URL": "https://gitlab.com/api/v4" // Optional, for self-hosted instances
      }
    }
  }
}

📦 NPX

{
  "mcpServers": {
    "gitlab": {
      "command": "npx",
      "args": ["-y", "@modelcontextprotocol/server-gitlab"],
      "env": {
        "GITLAB_PERSONAL_ACCESS_TOKEN": "<YOUR_TOKEN>",
        "GITLAB_API_URL": "https://gitlab.com/api/v4" // Optional, for self-hosted instances
      }
    }
  }
}

🏗️ Build

Docker build:

docker build -t vonwig/gitlab:mcp -f src/gitlab/Dockerfile .

🌍 Environment Variables

  • GITLAB_PERSONAL_ACCESS_TOKEN: Your GitLab personal access token (required)
  • GITLAB_API_URL: Base URL for GitLab API (optional, defaults to https://gitlab.com/api/v4)

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