What is the GitLab MCP for Code Review?

The GitLab MCP (Model Context Protocol) for Code Review is a server that integrates AI assistants like Claude with GitLab’s merge requests, enabling automated code analysis and review.

What are the prerequisites for installing the GitLab MCP server?

You need Python 3.10+, a GitLab personal access token with API scope (read_api, api), and Cursor IDE for full MCP integration.

How do I install the GitLab MCP server?

Clone the repository, create and activate a virtual environment, install dependencies using pip, and configure a .env file with your GitLab token and other settings.

What environment variables can I configure?

You can configure GITLAB_TOKEN, GITLAB_HOST, GITLAB_API_VERSION, LOG_LEVEL, DEBUG, REQUEST_TIMEOUT, and MAX_RETRIES in your .env file.

How do I integrate the MCP with Cursor IDE?

Add the MCP configuration to your ~/.cursor/mcp.json file, specifying the command, arguments, working directory, and environment variables.

What tools are available in the MCP server?

The MCP server provides tools like fetch_merge_request, fetch_merge_request_diff, fetch_commit_diff, compare_versions, add_merge_request_comment, approve_merge_request, unapprove_merge_request, and get_project_merge_requests.

How do I fetch a merge request using the MCP server?

Use the fetch_merge_request tool with the project ID and merge request number (e.g., fetch_merge_request("123", "5")).

How do I add a comment to a merge request?

Use the add_merge_request_comment tool with the project ID, merge request number, and the comment text (e.g., add_merge_request_comment("123", "5", "This code looks good!")).

What should I do if I encounter issues during installation or usage?

Verify your GitLab token permissions, check your .env file settings, ensure your MCP configuration paths are correct, test the connection with curl, and set LOG_LEVEL=DEBUG for detailed logging.

How does UBOS enhance the GitLab MCP server?

UBOS allows you to build custom AI Agents tailored to your code review needs, integrate enterprise data sources, create multi-agent systems, and provides a centralized platform for managing and orchestrating your AI Agents.