GitLab Kanban

A server for managing GitLab Kanban board operations.

Install

Install and configure the MCP from https://github.com/Sunwood-ai-labs/gitlab-kanban-mcp-server now. Follow the repository's installation instructions, ask me for anything you can't complete yourself, and verify its tools load.

View source on GitHub

README

🎯 GitLab Kanban MCP Server

A Model Context Protocol server for managing GitLab Kanban board operations.

✨ Features

🛠️ Available Tools

list_tasks - Retrieve task list from project's Kanban board
create_task - Create a new task on the Kanban board
update_task - Update an existing task
delete_task - Delete a task from the board
add_comment - Add a comment to a task

🏗️ Project Structure

src/
├── api/
│   └── gitlab.ts      # GitLab API client and methods
├── config/
│   └── gitlab.ts      # GitLab configuration
├── tools/
│   ├── handlers.ts    # Tool handler implementations
│   └── schemas.ts     # Tool schema definitions
└── index.ts          # MCP server main entry point

🚀 Getting Started

📦 Installation

npm install

🔧 Configuration

Create a .env file with the following environment variables:

GITLAB_TOKEN=your_gitlab_token
GITLAB_URL=your_gitlab_url  # default: https://gitlab.com

🛠️ Build

npm run build

For development with auto-rebuild:

npm run watch

🔍 Debugging

Since MCP servers communicate over stdio, we recommend using the MCP Inspector:

npm run inspector

📝 Usage

Cline Configuration

Add the following to your cline_mcp_settings.json:

{
  "mcpServers": {
    "gitlab-kanban-mcp-server": {
      "command": "node",
      "args": ["path/to/gitlab-kanban-mcp-server/build/index.js"],
      "env": {
        "GITLAB_TOKEN": "your_gitlab_token",
        "GITLAB_URL": "your_gitlab_url"
      }
    }
  }
}

🤝 Contributing

Fork this repository
Create your feature branch (git checkout -b feature/amazing-feature)
Commit your changes (git commit -m '✨ feat: Add amazing feature')
Push to the branch (git push origin feature/amazing-feature)
Create a Pull Request

📄 License

This project is licensed under the MIT License.