Aidderall

Provides hierarchical task management with living document approach where completed tasks remain visible, enabling non-linear workflow navigation, flexible priority switching, and persistent completion history for complex project management and research workflows.

This MCP server provides AI assistants with hierarchical task management capabilities through a living document approach where completed tasks remain visible in the structure, creating a comprehensive work history. Built by Briam R. using Python with the MCP SDK and Pydantic for data validation, it implements a flexible focus system that allows switching between any tasks in any order via switch_focus, separating task completion (status change) from task removal (structural cleanup), and achieving "zen state" when either no tasks exist or all tasks are completed. The implementation features tools for creating independent tasks versus extending current work into subtasks, non-linear workflow navigation, breadcrumb trails and context peeking, and persistent completion history, making it valuable for complex project management, research workflows with multiple threads, and building AI assistants that need structured task decomposition with flexible priority switching.