GitLab MCP

GitLab MCP

Enables AI assistants to manage GitLab projects by providing tools for issues, milestones, and team reports through a read/write interface. Users can interact with project data using natural language directly within Claude Desktop or Claude Code.

Category
访问服务器

README

GitLab MCP

A Model Context Protocol (MCP) server that exposes GitLab project management capabilities to AI assistants like Claude.

Overview

This project provides an MCP server built with FastMCP that connects to a GitLab project and exposes tools for managing issues, milestones, members, and generating team reports — all accessible directly from Claude Desktop or Claude Code.

Goal

The goal is to give AI assistants a structured, read/write interface into GitLab so that team leads and developers can manage their projects through natural language. Instead of navigating the GitLab UI, you can ask Claude to list open issues, create a new issue, check milestone progress, or generate a team workload report.

Available Tools

Tool Description
get_project_overview Fetch high-level project info
list_project_members List all members of the project
list_issues List issues with optional filters
get_issue Get details of a specific issue
create_issue Create a new issue
edit_issue Edit an existing issue
add_issue_comment Add a comment to an issue
list_milestones List project milestones
get_milestone Get details of a specific milestone
get_team_workload Report on issue distribution across members
get_milestone_report Summary report for a milestone

Setup

Prerequisites

  • Python 3.14+
  • uv package manager
  • A GitLab account with a Personal Access Token (PAT)

Install dependencies

uv sync

Configure environment

Create a .env file in the project root:

GITLAB_URL=https://gitlab.com
GITLAB_PAT=your_personal_access_token
GITLAB_PROJECT_ID=your_project_id
  • GITLAB_URL: Your GitLab instance URL (use https://gitlab.com for GitLab.com)
  • GITLAB_PAT: A GitLab Personal Access Token with api scope
  • GITLAB_PROJECT_ID: The numeric ID or namespace/project path of your project

Claude Desktop Setup

Add the following to your Claude Desktop config file (~/Library/Application Support/Claude/claude_desktop_config.json on macOS):

{
  "mcpServers": {
    "gitlab": {
      "command": "uv",
      "args": [
        "--project",
        "/absolute/path/to/gitlab-mcp",
        "run",
        "/absolute/path/to/gitlab-mcp/main.py"
      ],
      "cwd": "/absolute/path/to/gitlab-mcp",
      "env": { // Or put into .env
        "GITLAB_URL": "https://gitlab.com",
        "GITLAB_PAT": "your_personal_access_token",
        "GITLAB_PROJECT_ID": "your_project_id"
      }
    }
  }
}

Restart Claude Desktop after saving the config. The GitLab tools will appear in Claude's tool list.

Claude Code Setup

Add the MCP server to Claude Code by running:

claude mcp add gitlab -- uv --directory /absolute/path/to/gitlab-mcp run main.py

Then set the required environment variables either in your shell profile or by passing them inline:

GITLAB_URL=https://gitlab.com \
GITLAB_PAT=your_personal_access_token \
GITLAB_PROJECT_ID=your_project_id \
claude mcp add gitlab -- uv --directory /absolute/path/to/gitlab-mcp run main.py

You can verify the server is registered with:

claude mcp list

Todo

  • [ ] Merge Request support — Add tools for listing, creating, reviewing, and merging MRs (list_merge_requests, get_merge_request, create_merge_request, approve_merge_request, merge)

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