# Kanban AI — Full Summary

> Transform your side projects from ideas to reality with AI-assisted project management.

Kanban AI is your personal AI-powered project companion that helps you build, track, and complete side projects with intelligent guidance. Whether you are a developer showcasing new skills, an entrepreneur building a SaaS, or a creator bringing ideas to life, Kanban AI provides structure and support through modern kanban boards, AI-assisted planning, and native MCP integration for coding agents.

## Key Features

### AI-Powered Project Planning

- **Smart Project Breakdown:** Describe your idea and let AI create a comprehensive development plan.
- **Personalized Roadmaps:** Tailored to your skills, tech stack, and learning goals.
- **Intelligent Task Generation:** AI creates specific, actionable tasks for each development phase.

### Intelligent Progress Tracking

- **Adaptive Planning:** AI adjusts your roadmap based on actual progress.
- **Smart Recommendations:** Personalized suggestions when ahead or behind schedule.
- **Progress Analytics:** Visual insights into your development journey.

### Modern Kanban Interface

- **Drag-and-Drop Management:** Intuitive task organization with visual kanban boards.
- **Project Members:** Invite editors by email; shared boards sync through Supabase.
- **Real-time Updates:** Seamless collaboration and progress tracking.
- **Dark/Light Mode:** Interface that adapts to your preferences.

### AI Assistant Integration

- **Contextual Guidance:** Ask questions and get project-specific advice.
- **Roadblock Resolution:** AI helps overcome technical challenges.
- **Learning Support:** Explanations and resources for new technologies.

## Public URLs

- Home: https://kanbanai.dev/
- Connect AI (MCP setup): https://kanbanai.dev/connect
- Documentation: https://kanbanai.dev/docs
- Blog: https://kanbanai.dev/blog
- GitHub: https://github.com/orholam/kanban_ai

## MCP Server

Kanban AI exposes a **remote MCP server** at `https://kanbanai.dev/api/mcp`. It talks directly to Supabase with the same board operations as the web app (projects, tasks, comments).

### Setup

1. Sign in at Kanban AI.
2. Open **Connect AI** (`/connect`).
3. Click **Copy config** — credentials are filled in server-side.
4. Paste into Cursor or Claude Desktop MCP settings and restart.

For stdio-only clients, the Connect page provides a Claude Desktop JSON block using `mcp-remote`.

### Authentication

Each MCP request must include:

1. `Authorization: Bearer <supabase_access_token>` — the signed-in user's Supabase session access token (required).
2. `X-MCP-API-Key: <MCP_API_SECRET>` — when `MCP_API_SECRET` is configured on the deployment (optional per deployment; required on kanbanai.dev production).

Authenticated users fetch full config from `GET /api/mcp-setup` with their session bearer token.

### MCP Tools

| Tool | Description |
|------|-------------|
| `list_projects` | List all Kanban AI projects the signed-in user can access. |
| `get_board` | Get a project and all of its tasks (with task comments) as JSON context. |
| `create_project` | Create a new Kanban AI project for the signed-in user. |
| `update_project` | Update project metadata (title, notes, privacy, sprint fields, etc.). |
| `delete_project` | Delete a project and all of its tasks and collaborator rows. |
| `create_task` | Create a task on a project board. |
| `update_task` | Update an existing task by id. |
| `delete_task` | Delete a task from a board. |
| `list_task_comments` | List comments on a task. |
| `add_task_comment` | Add a comment to a task thread. |
| `delete_task_comment` | Delete a task comment by id. |

### Example Prompts

- "List my Kanban AI projects and tell me which have tasks in progress."
- "On project `<uuid>`, move every todo task in sprint 2 to in-progress."
- "Create a task: Ship landing page copy review — feature, high priority, due Friday."

### Further Reading

- MCP setup docs: https://kanbanai.dev/docs/connect-mcp-claude-cursor
- Kanban + MCP comparison (2026): https://kanbanai.dev/blog/kanban-mcp-tools-compared

## Tech Stack

- **Frontend:** React 18, TypeScript, Vite
- **Styling:** Tailwind CSS
- **Backend:** Supabase (PostgreSQL, Auth, Real-time)
- **AI:** OpenAI GPT-4
- **Deployment:** Vercel
- **License:** MIT

## Use Cases

- **Developers:** Skill showcase, portfolio projects, structured learning paths.
- **Entrepreneurs:** MVP development, AI-guided roadmaps, rapid iteration.
- **Creators:** Project organization, goal breakdown, progress visualization.