Local-first task manager: create, edit, and complete tasks, projects, and checklists via MCP. Connect the official Done Bear MCP server to Claude, ChatGPT, or Cursor through gate — one gateway URL, no config files, security-checked.
Free to start · No credit card · No hosting needed
Real prompts you can type the moment it's connected — no setup, no docs to read.
“Use “guide”: Read Done Bear's guide for one topic: what the data means, how it relates to the rest of the product, and how to use it well. Load a topic b.”
“Use “get_context”: Get a snapshot of the current workspace: user info, task counts, recent tasks, and active projects. Use it to resolve a name or answer what.”
“Use “task_list”: List tasks in the workspace, most recently updated first. Filter by view (inbox, today, upcoming, anytime, someday) and/or state (open, done.”
“Use “task_show”: Get full details for a single task including its labels and checklist items. Pass its workspace-scoped task number.”
Every server in the gate directory has to pass the same four checks before your AI can touch it. Here's how Done Bear holds up.
Operated by Done Bear (donebear.com) at its documented MCP endpoint — not a third-party mirror or community re-host.
This server only exposes public data — no account and no credentials are involved when you connect.
gate checks every tool for prompt injection, hidden instructions, data-exfiltration hints, and over-broad permissions before the server is available through your gateway.
If Done Bear adds or changes tools later, gate re-scans and alerts you — before your AI acts on the change.
Add one gateway URL to Claude, ChatGPT, or any MCP client. One-time setup, about two minutes.
Choose Done Bear in the gate directory. No sign-in needed.
Done Bear's tools are live in every AI client you've connected — with rules and logging built in.
Free to start · No credit card · No hosting needed
Fetched live from the official endpoint and re-checked daily by gate — not marketing copy.
guide — Read Done Bear's guide for one topic: what the data means, how it relates to the rest of the product, and how to use it well. Load a topic b
get_context — Get a snapshot of the current workspace: user info, task counts, recent tasks, and active projects. Use it to resolve a name or answer what
task_list — List tasks in the workspace, most recently updated first. Filter by view (inbox, today, upcoming, anytime, someday) and/or state (open, done
task_show — Get full details for a single task including its labels and checklist items. Pass its workspace-scoped task number.
task_add — Create a new task. The `when` parameter controls which GTD view it appears in: today (default), inbox, upcoming, anytime, or someday. A new
task_edit — Update one or more fields on an existing task. Only the provided fields are changed; omitted fields are left untouched. To remove a value, l
task_done — Mark a task as complete. It moves to the Logbook view.
task_reopen — Reopen a completed task. It returns to its previous view.
+ 27 more tools once connected
https://mcp.donebear.com/mcpYes — Done Bear operates its own remote MCP server at mcp.donebear.com. gate connects you to that official endpoint and adds security scanning, per-tool access rules, and an activity log on top.
Add gate's gateway URL to your AI client once, then pick Done Bear in the directory. No account or sign-in is needed. From then on, Done Bear's tools are available in every client you've connected to gate.
No. Done Bear runs the server, and gate is fully managed. You just connect one URL — there's nothing to install, deploy, or maintain.
It's the vendor's official endpoint, and gate scans its tools for prompt injection and hidden instructions before it goes live, re-checks it whenever it changes, and lets you allow, block, or require approval for every single tool.
Yes — you can get started with gate for free and connect Done Bear in minutes. No credit card required.
Every server below works through the same gateway URL — connect once, add tools anytime.
Set up Done Bear in: Claude · Claude Code · ChatGPT · Cursor · VS Code