Gitlab MCP Server

GitLab MCP Server

A Model Context Protocol (MCP) server that exposes GitLab operations as MCP tools, resources, and prompts for AI assistants. Written in Go — single static binary per platform.

Highlights

• 1006 MCP tools — complete GitLab REST API v4 coverage across 162 domain sub-packages: projects, branches, tags, releases, merge requests, issues, pipelines, jobs, groups, users, wikis, environments, deployments, packages, container registry, runners, feature flags, CI/CD variables, templates, admin settings, access tokens, deploy keys, and more
• 42 meta-tools (57 with GITLAB_ENTERPRISE=true) — domain-grouped dispatchers that reduce token overhead for LLMs (optional, enabled by default). 15 additional enterprise meta-tools available for Premium/Ultimate features
• 11 sampling tools — LLM-assisted code review, issue analysis, pipeline failure diagnosis, security review, release notes, milestone reports, and more via MCP sampling capability
• 4 elicitation tools — interactive creation wizards (issue, MR, release, project) with step-by-step user prompts
• 24 MCP resources — read-only data: user, groups, group members, group projects, projects, issues, pipelines, members, labels, milestones, branches, MRs, releases, tags, workspace roots, and 5 workflow best-practice guides
• 38 MCP prompts — AI-optimized: code review, pipeline status, risk assessment, release notes, standup, workload, user stats, team management, cross-project dashboards, analytics, milestones, audit
• 6 MCP capabilities — logging, completions, roots, progress, sampling, elicitation
• 43 tool icons — SVG data-URI icons on all tools, resources, and prompts for visual identification in MCP clients
• Pagination on all list endpoints with metadata (total items, pages, next/prev)
• Transports: stdio (default for desktop AI) and HTTP (Streamable HTTP for remote clients)
• Cross-platform: Windows, Linux & macOS, amd64 & arm64
• Self-hosted GitLab with self-signed TLS certificate support

Example Prompts

Once connected, just talk to your AI assistant in natural language:

"List my GitLab projects" "Show me open merge requests in my-app" "Create a merge request from feature-login to main" "Review merge request !15 — is it safe to merge?" "List open issues assigned to me" "What's the pipeline status for project 42?" "Why did the last pipeline fail?" "Generate release notes from v1.0 to v2.0"

The server handles the translation from natural language to GitLab API calls. You do not need to know project IDs, API endpoints, or JSON syntax — the AI assistant figures that out for you. See Usage Examples for more scenarios.

Quick Start

1. Download

Download the latest binary for your platform from GitHub Releases and make it executable:

chmod +x gitlab-mcp-server-*  # Linux/macOS only

2. Configure your MCP client

Recommended: Run the built-in setup wizard — it configures your GitLab connection and MCP client in one step:

./gitlab-mcp-server --setup

Tip: The wizard supports Web UI, Terminal UI, and plain CLI modes. On Windows, double-click the .exe to launch the wizard automatically.

Or configure manually — expand your client below:

Add to .vscode/mcp.json in your workspace:

{
  "servers": {
    "gitlab": {
      "type": "stdio",
      "command": "/path/to/gitlab-mcp-server",
      "env": {
        "GITLAB_URL": "https://gitlab.example.com",
        "GITLAB_TOKEN": "glpat-xxxxxxxxxxxxxxxxxxxx"
      }
    }
  }
}

Add to claude_desktop_config.json:

{
  "mcpServers": {
    "gitlab": {
      "command": "/path/to/gitlab-mcp-server",
      "env": {
        "GITLAB_URL": "https://gitlab.example.com",
        "GITLAB_TOKEN": "glpat-xxxxxxxxxxxxxxxxxxxx"
      }
    }
  }
}

Add to .cursor/mcp.json:

{
  "mcpServers": {
    "gitlab": {
      "command": "/path/to/gitlab-mcp-server",
      "env": {
        "GITLAB_URL": "https://gitlab.example.com",
        "GITLAB_TOKEN": "glpat-xxxxxxxxxxxxxxxxxxxx"
      }
    }
  }
}

claude mcp add gitlab /path/to/gitlab-mcp-server \
  -e GITLAB_URL=https://gitlab.example.com \
  -e GITLAB_TOKEN=glpat-xxxxxxxxxxxxxxxxxxxx

Add to ~/.codeium/windsurf/mcp_config.json:

{
  "mcpServers": {
    "gitlab": {
      "command": "/path/to/gitlab-mcp-server",
      "env": {
        "GITLAB_URL": "https://gitlab.example.com",
        "GITLAB_TOKEN": "glpat-xxxxxxxxxxxxxxxxxxxx"
      }
    }
  }
}

Add to the MCP configuration in Settings → Tools → AI Assistant → MCP Servers:

{
  "servers": {
    "gitlab": {
      "type": "stdio",
      "command": "/path/to/gitlab-mcp-server",
      "env": {
        "GITLAB_URL": "https://gitlab.example.com",
        "GITLAB_TOKEN": "glpat-xxxxxxxxxxxxxxxxxxxx"
      }
    }
  }
}

Add to Zed settings (settings.json):

{
  "context_servers": {
    "gitlab": {
      "command": "/path/to/gitlab-mcp-server",
      "args": [],
      "env": {
        "GITLAB_URL": "https://gitlab.example.com",
        "GITLAB_TOKEN": "glpat-xxxxxxxxxxxxxxxxxxxx"
      }
    }
  }
}

Add to .kiro/settings/mcp.json:

{
  "mcpServers": {
    "gitlab": {
      "command": "/path/to/gitlab-mcp-server",
      "args": [],
      "env": {
        "GITLAB_URL": "https://gitlab.example.com",
        "GITLAB_TOKEN": "glpat-xxxxxxxxxxxxxxxxxxxx"
      }
    }
  }
}

3. Verify

Open your AI client and try:

"List my GitLab projects"

See the Getting Started guide for detailed setup instructions.

Tool Modes

Two registration modes, controlled by the META_TOOLS environment variable:

Meta-tool summary:

Plus 11 sampling tools, 4 elicitation tools, and additional domain tools. See Meta-Tools Reference for the complete list with actions and examples.

Compatibility

Tested with: VS Code + GitHub Copilot, Claude Desktop, Claude Code, Cursor, Windsurf, JetBrains IDEs, Zed, Kiro.

See the full Compatibility Matrix for detailed client support.

Documentation

Full documentation is available at jmrplens.github.io/gitlab-mcp-server.

Tech Stack

Building from Source

git clone https://github.com/jmrplens/gitlab-mcp-server.git
cd gitlab-mcp-server
make build

See the Development Guide for cross-compilation and contributing guidelines.

Docker

docker pull ghcr.io/jmrplens/gitlab-mcp-server:latest

docker run -d --name gitlab-mcp-server -p 8080:8080 \
  -e GITLAB_URL=https://gitlab.example.com \
  -e GITLAB_SKIP_TLS_VERIFY=true \
  ghcr.io/jmrplens/gitlab-mcp-server:latest

Clients authenticate via PRIVATE-TOKEN or Authorization: Bearer headers. See HTTP Server Mode and Docker documentation for Docker Compose and configuration options.

FAQ

Yes. Set GITLAB_URL to your instance URL. Self-signed TLS certificates are supported via GITLAB_SKIP_TLS_VERIFY=true.

The server runs locally on your machine (stdio mode) or on your own infrastructure (HTTP mode). No data is sent to third parties — all API calls go directly to your GitLab instance. See SECURITY.md for details.

Yes. Set GITLAB_READ_ONLY=true to disable all mutating tools (create, update, delete). Only read operations will be available.

Alternatively, set GITLAB_SAFE_MODE=true for a dry-run mode: mutating tools remain visible but return a structured JSON preview instead of executing. Useful for auditing, training, or reviewing what an AI assistant would do.

Both Community Edition (CE) and Enterprise Edition (EE). Set GITLAB_ENTERPRISE=true to enable 15 additional tools for Premium/Ultimate features (DORA metrics, vulnerabilities, compliance, etc.).

The server includes retry logic with backoff for GitLab API rate limits. Errors are classified as transient (retryable) or permanent, with actionable hints in error messages.

Any MCP-compatible client: VS Code + GitHub Copilot, Claude Desktop, Cursor, Claude Code, Windsurf, JetBrains IDEs, Zed, Kiro, and others. The built-in setup wizard can auto-configure most clients.

Related Projects

• Redmine MCP Server — Sister project: MCP server for Redmine with 152 tools
• MCP Go SDK — The official Go SDK this server is built on
• Model Context Protocol — The MCP specification
• Awesome MCP Servers — Curated list of MCP servers

Contributing

See CONTRIBUTING.md for development guidelines, branch naming, commit conventions, and pull request process.

Security

See SECURITY.md for the security policy and vulnerability reporting.

Code of Conduct

See CODE_OF_CONDUCT.md. This project follows the Contributor Covenant v2.1.