This project provides a GitLab Model Context Protocol (MCP) server, enhancing the original implementation with bug fixes and new features. It enables AI tools like Claude App, Cursor, and Roo Code to interact with GitLab repositories, offering a comprehensive suite of functionalities for code management, issue tracking, and CI/CD operations.

How It Works

The server acts as a bridge between AI applications and the GitLab API. It exposes a set of tools that allow for operations such as creating/updating files, managing issues and merge requests, forking repositories, and interacting with CI/CD pipelines. The server supports multiple transport protocols, including standard input/output (stdio), Server-Sent Events (SSE), and Streamable HTTP, allowing flexibility in integration.

Quick Start & Requirements

• Installation: Run via npx @zereight/mcp-gitlab or use the iwakitakuma/gitlab-mcp Docker image.
• Prerequisites: GitLab Personal Access Token with appropriate scopes.
• Configuration: Environment variables like GITLAB_PERSONAL_ACCESS_TOKEN, GITLAB_API_URL, and feature flags (USE_GITLAB_WIKI, USE_MILESTONE, USE_PIPELINE) control functionality.
• Documentation: README provides detailed configuration examples for various AI tools and transport methods.

Highlighted Details

• Extensive toolset covering file management, project operations, issue/merge request lifecycle, wiki, milestones, and pipelines.
• Support for multiple transport protocols (stdio, SSE, Streamable HTTP) for flexible integration.
• Configurable feature flags to enable/disable specific GitLab functionalities.
• Includes improvements and bug fixes over the original GitLab MCP server.

Maintenance & Community

The project is maintained by zereight. Further community engagement details are not specified in the README.

Licensing & Compatibility

The project's license is not explicitly stated in the README. Compatibility for commercial use or closed-source linking would require clarification on the licensing terms.

Limitations & Caveats

The README does not specify any known limitations, unsupported platforms, or alpha status. The exact licensing terms for commercial use are not provided, which may be a consideration for some users.