GitLab MCP Server (in Python)

Model Context Protocol (MCP) server for GitLab integration, built on FastMCP.

This server is implemented in Python, with fastmcp.

Quick Start

Build the Docker image:

docker build -t gitlab-mcp-server .

Integration with Cursor/Claude

In MCP Settings -> Add MCP server, add this config:

{
  "mcpServers": {
    "gitlab": {
      "command": "docker",
      "args": [
        "run",
        "--rm",
        "-i",
        "-e",
        "GITLAB_TOKEN",
        "-e",
        "GITLAB_URL",
        "gitlab-mcp-server:latest"
      ],
      "env": {
        "GITLAB_TOKEN": "token",
        "GITLAB_URL": "https://gitlab.com/"
      }
    }
  }
}

Note: Don't forget to replace GITLAB_TOKEN and GITLAB_URL values with your actual GitLab credentials and instance URL.

Getting GitLab Token

Log in to your GitLab account
Go to Settings -> Access Tokens
Create a new token:
- Scopes: select the necessary permissions:
  - api - for API access
  - read_repository - for reading repositories
  - write_repository - for writing to repositories
Click "Create personal access token"
Copy the generated token (it will be shown only once!)

Functions

✅1.create_repository
✅2.fork_repository
✅3.delete_repository
✅4.search_repositories
✅5.create_or_update_file
✅6.push_files
✅7.get_file_contents
✅8.create_issue
✅9.get_issues
✅10.create_merge_request
✅11.get_merge_request_diff
✅12.create_branches
✅13.delete_branches
✅14.create_tags
✅15.delete_tags

superglue

superglue integrates & orchestrates APIs from natural language. Agents use it to build deterministic workflows across apps, APIs and databases. Humans use it to generate insights, build automations and manage data.

docs

GitLab MCP Server (in Python)