feat: Kanban MCP — persistent boards with multi-session, semantic search, and web UI#24
Conversation
…i-session, semantic search, and web UI - 12 MCP tools: list_boards, create_board, get_board, get_card, create_card, update_card, move_card, claim_card, release_card, search_cards, archive_card, delete_card - Multi-session: claim/release cards with session_log for cross-chat coordination - Semantic search via LanceDB with multilingual embeddings - Subtasks via parent_card_id - HTTP server (KANBAN_UI=true) with Express API + React web UI - Web UI: Linear-style dark theme, shadcn/ui, dnd-kit drag-and-drop, hotkeys, context menus - KANBAN_DEFAULT_RELEASE_STATUS defaults to review - Atomic JSON writes with .tmp + rename, re-read from disk for multi-process visibility
|
Warning Rate limit exceeded
Your organization is not enrolled in usage-based pricing. Contact your admin to enable usage-based pricing to continue reviews beyond the rate limit, or try again in 5 minutes and 13 seconds. ⌛ How to resolve this issue?After the wait time has elapsed, a review can be triggered using the We recommend that you space out your commits to avoid hitting the rate limit. 🚦 How do rate limits work?CodeRabbit enforces hourly rate limits for each developer per organization. Our paid plans have higher rate limits than the trial, open-source and free plans. In all cases, we re-allow further reviews after a brief timeout. Please see our FAQ for further information. ℹ️ Review info⚙️ Run configurationConfiguration used: defaults Review profile: CHILL Plan: Pro Run ID: 📒 Files selected for processing (42)
✨ Finishing Touches🧪 Generate unit tests (beta)
Thanks for using CodeRabbit! It's free for OSS, and your support helps us grow. If you like it, consider giving us a shout-out. Comment |
What
New
@arvoretech/kanban-mcppackage — persistent kanban boards for AI agents with multi-session coordination, semantic search via LanceDB, and a Linear-style web UI.Why
Agents lose track of work between sessions. When multiple chats are open in parallel, there's no way to know what each one is doing. This MCP gives agents a shared kanban board where they can claim cards, track progress, and coordinate.
Changes
MCP Server (
packages/kanban/)list_boards,create_board,get_board,get_card,create_card,update_card,move_card,claim_card,release_card,search_cards,archive_card,delete_cardclaim_card/release_cardwithsession_logfor cross-chat coordinationparent_card_id.tmp+ rename)KANBAN_DEFAULT_RELEASE_STATUSdefaults toreviewHTTP Server + Web UI (
packages/kanban/ui/)KANBAN_UI=true)Ccreate,/search,Escclose,←→navigate,BackspacearchiveEnv vars
KANBAN_PATH./kanbanKANBAN_EMBEDDING_MODELXenova/paraphrase-multilingual-MiniLM-L12-v2KANBAN_DEFAULT_RELEASE_STATUSreviewKANBAN_UIfalseKANBAN_PORT4799How to test