Local kanban board & harness for coding agents over MCP: agents claim and move tasks, read and write notes, and build Auto-code workflows, within per-folder permissions and an audit log.
Exposes a local-first task board over stdio JSON-RPC so MCP-capable agents can list and create projects and tasks, atomically claim the next ready task with a lease, heartbeat, log progress, manage dependency graphs, and mark tasks done or failed with results. All state lives in a single local SQLite file, so no shell command assembly or external services are needed.
Enables AI agents to create and manage small project plans—including tasks, assignees, status, progress, dates, and dependencies—and retrieve Gantt-friendly project views over MCP stdio. State is stored in SQLite without external dependencies.
Enables AI coding agents to manage a SQLite-backed task board directly through MCP, with tools to add, list, update status, and delete tasks and a markdown board resource.
An AI-native kanban board MCP server where agents pull tasks via the Model Context Protocol. It provides tools for task discovery, claiming, progress updates, and review workflows.