What Is an MCP Task Manager?

In short: An MCP task manager is a to-do app that speaks the Model Context Protocol (MCP), the open standard AI assistants use to call external tools. Rather than copy-pasting between a chat window and your task list, you connect the two: your assistant reads your tasks, adds new ones, edits them, and marks them done, all with your permission and an OAuth sign-in. Done Bear is an MCP task manager. It hosts a server at https://mcp.donebear.com/mcp that Claude, ChatGPT, Cursor, Claude Code, and any other MCP client can connect to in about a minute.

Most “AI plus to-do list” workflows are transcription. The assistant suggests a plan, you retype it into your task manager. An MCP task manager closes that loop. The Model Context Protocol is the open standard, introduced by Anthropic and now adopted across the industry, that lets an assistant use your tools directly instead of describing what you should do.

When your task manager ships an MCP server, your assistant can act on your real list: triage the inbox, plan your day around what’s in there, file follow-ups the moment a call ends.

The key word is your. It’s the task manager you already trust, reachable by whatever assistant you prefer, over a permissioned connection you can revoke whenever you like.

MCP task manager vs. AI coding-task tools

Task Master and Shrimp Task Manager get described as “MCP task managers” too, but they’re coding-task planners. They help an agent break a software feature into sub-tasks and track them for the duration of a coding session. They live in your editor and vanish when the work is done. Good at shipping code.

They are not where your dentist appointment goes. They don’t hold “call the plumber,” “review the Q3 budget,” or “buy a birthday present.” Those belong in your real to-do list, the one you check on your phone, share with a partner, and carry across weeks.

Done Bear is an MCP task manager for that list. It’s a full GTD-native, local-first task manager first, with the five views (Inbox, Today, Upcoming, Anytime, Someday) and a Logbook, and it happens to expose an MCP server so your assistant can help you run it.

What you can do with one

Once your assistant is connected to Done Bear’s MCP server, you can ask for things like:

• “Look at my Done Bear inbox and suggest where each task belongs.”
• “Plan my Wednesday: pick five tasks from Anytime that fit around my meetings.”
• “I just got off a call, add follow-ups: send Sam the proposal, book the venue, chase the invoice.”
• “What did I finish this week?”

Every action runs through OAuth. The assistant acts as you, only after you’ve signed in, and only while the connection is enabled. Read access is scoped to your workspace, and write actions surface as tool calls you can review.

How the connection works

Done Bear hosts its MCP server over Streamable HTTP with OAuth 2.1, so there’s no local package to install and no API key to manage. Setup is client-specific but short. With Claude and ChatGPT you add a custom connector and paste the URL. Cursor takes a one-click deeplink, or a two-line mcp.json entry.

Claude Code is one claude mcp add command, and Windsurf wants the server added with serverUrl in your MCP config.

The full menu is on the MCP hub. For the client setup matrix, the tool inventory, and how auth and scopes behave, see the free task manager MCP resources.

Why GTD-native and local-first matter here

Any task manager can bolt on an MCP endpoint. Turns out the endpoint isn’t the hard part. The structure underneath is what makes an assistant good at this.

The five GTD views give it real semantics: “move this to Someday” means something specific, so it files things instead of inventing a tagging scheme. And because Done Bear is local-first, the changes it makes show up on your devices straight away, next to the edits you made offline.

Todoist and TickTick ship MCP servers as well (TickTick’s is a paid beta), and Things 3 has none. No competitor pairs agent access with GTD-native views and local-first sync on a free plan.

You can start free, connect your assistant, and let it help you run the list you already keep.