GitLab
@GitLab
About GitLab
GitLab connects AI tools securely to repository, issue, merge request, and DevSecOps data. Its connector gives assistants GitLab project context for understanding code work, collaboration, security workflows, and delivery status.
Connection details
https://gitlab.com/api/v4/mcpSetup
claude mcp add gitlab --transport http https://gitlab.com/api/v4/mcpTools
No tools detected
Fetch the live tool list directly from this server's endpoint using the button above.
Frequently asked questions
What is the GitLab remote MCP server?
The GitLab remote MCP server is a hosted Model Context Protocol endpoint at https://gitlab.com/api/v4/mcp, so AI assistants can connect to it without installing or running anything locally.
How do I connect to the GitLab MCP server?
Add the endpoint https://gitlab.com/api/v4/mcp to any MCP-compatible client such as Claude Code, Cursor, or VS Code. The setup snippets on this page configure each client in one step.
Does the GitLab MCP server require authentication?
Yes. GitLab uses OAuth: the first time you connect, your MCP client opens a browser window to sign in and authorize access, then reuses the credentials for future sessions.
Which transport does the GitLab MCP server use?
GitLab exposes a Streamable HTTP endpoint, the transport used by remote MCP servers and supported by all major MCP clients.
Basic information
More remote MCP servers
Agent Utility MCP
Production remote MCP server with exactly 100 bounded tools: 85 paid tools and 15 free tools for text, JSON, encoding, identifiers, numbers, dates, URLs, validation, and secure web intelligence. Paid calls are charged on
Adobe for creativity
Ideate, create, and deliver with Adobe pro tools
Alice Flights
Real-time flight search for Claude and any MCP client. Ask for flights by origin, destination, dates, passengers, and cabin class — results come back categorized as best, cheapest, and fastest, each with price, full itin
Agentic Atlas
Consult field-tested agent-system design patterns through 8 hosted, read-only tools for orientation, deep reading, relationships, provenance, glossary terms, and publication decisions.
Asana
Tasks, projects, workspaces
Comments