mcp-gitlab MCP Server

mcp-gitlab MCP Server

By MCP-Mirror GitHub

Mirror of

gitlab mcp-server
Overview

what is mcp-gitlab MCP Server?

The mcp-gitlab MCP Server is a GitLab integration server built on the Model Context Protocol (MCP) framework, providing various GitLab RESTful API tools for integration with platforms like Claude and Smithery.

how to use mcp-gitlab MCP Server?

To use the mcp-gitlab MCP Server, install the dependencies, build the project, and start the server. Configure the environment variables for GitLab API URL and access token.

key features of mcp-gitlab MCP Server?

  • GitlabSearchUserProjectsTool: Search for users and their active projects by username.
  • GitlabGetUserTasksTool: Retrieve the current user's to-do tasks.
  • GitlabSearchProjectDetailsTool: Search for project details.
  • GitlabCreateMRCommentTool: Add comments to merge requests.
  • GitlabAcceptMRTool: Accept and merge merge requests.
  • GitlabUpdateMRTool: Update the assignee, reviewer, title, description, and labels of a merge request.
  • GitlabCreateMRTool: Create new merge requests with assignee and reviewers.
  • GitlabRawApiTool: Custom calls to any GitLab API.

use cases of mcp-gitlab MCP Server?

  1. Automating GitLab project management tasks.
  2. Integrating GitLab functionalities into other applications.
  3. Enhancing collaboration through automated merge request handling.

FAQ from mcp-gitlab MCP Server?

  • What is the purpose of the mcp-gitlab MCP Server?

It serves as a bridge for integrating GitLab functionalities into various platforms using the MCP framework.

  • Is there documentation available for the tools?

Yes, detailed usage examples can be found in the USAGE.md file.

  • What programming language is used for this project?

The project is developed in TypeScript.

Content

English Version

mcp-gitlab MCP Server

smithery badge MCP Server

基于 Model Context Protocol (MCP) 框架构建的 GitLab 集成服务器,提供多种 GitLab RESTful API 工具,支持 Claude、Smithery 等平台集成。

功能概览

  • GitlabSearchUserProjectsTool:根据用户名搜索用户及其活跃项目
  • GitlabGetUserTasksTool:获取当前用户的待办任务
  • GitlabSearchProjectDetailsTool:搜索项目及详细信息
  • GitlabCreateMRCommentTool:为合并请求添加评论
  • GitlabAcceptMRTool:接受并合并合并请求
  • GitlabUpdateMRTool:更新 Merge Request 的指派人、评审人、标题、描述、标签
  • GitlabCreateMRTool:创建新的 Merge Request,支持指派 assignee 和 reviewers
  • GitlabRawApiTool:自定义调用任意 GitLab API

快速开始

# 安装依赖
bun install

# 构建项目
bun run build

# 启动服务
bun run start

环境变量配置

GITLAB_API_URL=https://your-gitlab-instance.com
GITLAB_TOKEN=your_access_token

工具示例

详见 USAGE.md,包括每个工具的参数示例。

项目结构

src/
├── server/
│   └── GitlabMCPServer.ts          # MCP 服务器入口
├── tools/
│   ├── GitlabAcceptMRTool.ts
│   ├── GitlabCreateMRCommentTool.ts
│   ├── GitlabGetUserTasksTool.ts
│   ├── GitlabRawApiTool.ts
│   ├── GitlabSearchProjectDetailsTool.ts
│   ├── GitlabSearchUserProjectsTool.ts
│   └── gitlab/
│       ├── FieldFilterUtils.ts
│       ├── GitlabApiClient.ts
│       └── GitlabApiTypes.ts
├── utils/
│   ├── is.ts
│   └── sensitive.ts
smithery.json                      # Smithery 配置
USAGE.md                          # 使用示例
package.json
tsconfig.json

集成方式

Claude 桌面客户端

在配置文件中添加:

{
  "mcpServers": {
    "@zephyr-mcp/gitlab": {
      "command": "npx",
      "args": ["-y", "@zephyr-mcp/gitlab@0.1.0"]
    }
  }
}

配置参数:

  • GITLAB_API_URL: GitLab API 的基础 URL
  • GITLAB_TOKEN: 用于验证 GitLab API 请求的访问令牌

相关链接

No tools information available.

Mirror of

image-generation mcp-server
View Details

Secure MCP server for analyzing Excel files with oletools

oletools mcp-server
View Details

Mirror of

bigquery mcp-server
View Details

MCPHubs is a website that showcases projects related to Anthropic's Model Context Protocol (MCP)

mcp mcp-server
View Details
Dealx
Dealx by DealExpress

-

dealx mcp-server
View Details

Google Analytics MCP server for accessing analytics data through tools and resources

google-analytics mcp-server
View Details

A Python-based MCP server that lets Claude run boto3 code to query and manage AWS resources. Execute powerful AWS operations directly through Claude with proper sandboxing and containerization. No need for complex setups - just pass your AWS credentials and start interacting with all AWS services.

aws mcp-server
View Details