MCP Task List Server

A persistent, queryable task list MCP server for AI agents

Problem

Developers using AI agents like Claude Code, Codex, or Cursor often need agents to remember the state of multi-step tasks, but agents lack persistent task management; they have to re-explain the task list every session and cannot track progress across conversations; some try to build their own MCP server but struggle with protocol, storage, and concurrency.

Solution

An out-of-the-box MCP server that exposes standard tools for creating, updating, querying, and deleting tasks; agents can call these tools via natural language to maintain a persistent task list; supports local SQLite storage with optional cloud sync; includes a simple web panel for viewing and manually adjusting tasks.

Users

Developers, indie hackers, and small teams using AI agents for multi-step workflows

MVP

Implement a local MCP server with CRUD for tasks; persist with SQLite; provide a simple web UI to view tasks; support task status (todo/in-progress/done) and priority; publish as an npx package for one-command run

Revenue

Open-source core + paid cloud sync/team collaboration; or one-time purchase desktop version; also donations and sponsorships

Why now

AI agents are shifting from single-turn chat to multi-step task execution, and the MCP protocol is becoming the de facto standard for connecting agents with tools, yet task management lacks a lightweight solution—indie developers can fill this gap quickly