MCP.Market

Done Bear MCP server

online · 100% uptime
by donebear.com·com.donebear/donebear·v1.0.0

Local-first task manager: create, edit, and complete tasks, projects, and checklists via MCP.

C61/100grade C
What users say
No reviews yet
Be the first
Safety scan
C61/100

full report

Adoption
New

Little public usage data yet

Reviews

Write one

Nobody has reviewed Done Bear yet.

If you have run it, two minutes of your experience saves the next person an afternoon.

Done Bear tools (17, 5 write)

write = sends, deletes, buys or posts
  • attachmentFree

    Add a file to a task or remove one. `action: "add"` fetches the given HTTPS `url`: the server downloads it, verifies its size and type, and stores it, so the model never sends file bytes. Pass a stable idempotency_key and reuse it for retries so a lost response cannot upload the file twice. `action: "remove"` deletes the named `attachment`. Read a task's files with task_show and `include: ["attachments"]`. Limited to 10 attachments per task and 10 MB per file. Allowed types: images (jpeg, png, gif, webp, heic), PDF, CSV, Markdown, and plain text.

  • checklistFree

    Change the checklist on a task. `action: "add"` appends items, unchecked, after the existing ones: pass every title for a multi-item list in one call (`titles` keeps the given order, while parallel single adds land in arrival order). `action: "edit"` renames an item and/or checks it (`completed: true`) or unchecks it (`completed: false`). `action: "remove"` deletes one. Read the list, with each item's id and state, from task_show.

  • commentwrite actionFree

    Write on a task's comment thread. `action: "add"` posts a comment, attributed to the connected user and visible to everyone in the workspace, so write it as a message to the user's teammates rather than a note to the user; nobody is notified. `action: "edit"` rewrites one of your own (only its author may, and it is then marked edited). `action: "remove"` deletes one permanently — comments have no Trash — so confirm with the user first. Read the thread with task_show and `include: ["comments"]`.

  • get_contextFree

    Get a snapshot of the current workspace: task counts per view, recent open tasks, and every project, label, team and member. This is the tool that answers what is in the workspace and resolves a project, label, team or member by name — there is no separate list tool for those. Use it for that, not as a warm-up before every turn. For tasks themselves use task_list (a view), search (by words) or task_show (one task): the recent tasks here are only the latest few.

  • guideFree

    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 before doing that kind of work for the first time in a session. - `views`: Placing a task in Inbox/Today/Upcoming/Anytime/Someday, reading a view, or working out why Today looks wrong. - `dates`: Setting or clearing a due date, or deciding between a deadline and a start date. - `editing`: Changing a task's fields, clearing a value, appending to notes, or moving a task between projects. - `bulk`: Completing, moving, or editing more than one task at a time, or sweeping a whole view. - `checklists`: Adding sub-steps to a task, building a list inside a task, or ticking items off. - `comments`: Discussing a task with teammates: reading its thread, replying, or correcting a comment. - `projects`: Deciding where a task belongs, creating a project or label, changing a project's status, or joining/leaving a project. - `search`: Looking a task up, listing a view, paging through results, or orienting in a new workspace. - `workspaces`: Working across multiple workspaces, hitting a permission or rate-limit error, or making retries safe. - `agents`: Starting work in a Done Bear workspace for the first time. - `importing`: The user asks how to move their tasks in from Todoist, Things, Trello or a CSV.

  • label_createwrite actionFree

    Create a new label in the workspace and return its id. Only creates the label: to put it on a task, pass it to task_add `labels` or task_edit `add_labels` afterwards (both take the title). Titles are not unique, so a second call with the same title makes a duplicate — check the labels get_context returns first, and reuse one that already exists.

  • projectwrite actionFree

    Create or change a project. `action: "add"` creates one (name required). `action: "edit"` updates the named project: only the fields given change, and an empty string clears description or target_date. `action: "join"` puts it in the caller's Your projects sidebar list and `action: "leave"` takes it out. Read projects with get_context.

  • searchFree

    Search tasks across the workspace. Ranked lexical search over title and description: exact and prefix matches rank first, then word-boundary, substring, and fuzzy matches, with recency and status factored in. Multi-word queries match in any order. Searches every state by default, completed and archived included. Use this when the user names a task by its words; use task_list to browse a view (Today, Inbox, …) and task_show once you have the task number.

  • task_addwrite actionFree

    Create a new task. An explicit `when` selects its start placement: today, inbox, upcoming, anytime, or someday; upcoming schedules tomorrow. Without `when`, a `deadline` or omitted `timezone` selects anytime first. Otherwise, a `project` or `team` selects inbox; an unfiled task selects today. Pass the user's known IANA `timezone` to resolve calendar days. Use `when: "inbox"` for capture without a commitment to today. `deadline` uses YYYY-MM-DD. Optionally assign the task, attach existing labels, or pass checklist item titles in `checklist`; their order is preserved. The result's `view` reports the selected start placement, while a due or overdue deadline can make the task appear in Today. To change an existing task, use task_edit for fields or the available checklist tools for items. Search first when the user may be describing an existing task.

  • task_agent_getFree

    Read the task-agent identity bound to this connection's existing API key in one explicit workspace. Returns only key metadata and the exact agent UUID or null; an inactive agent includes disabledAt. Requires an API-key connection and current workspace membership. Does not register, assign or start any task. Use this before task_agent_register and retain key.id as expected_key_id.

  • task_agent_registerFree

    Explicitly register one assignable task agent for this connection's existing key in one workspace, after the user approves that durable binding. Requires a write-scoped API key restricted to exactly this workspace and an owner/admin membership. Read task_agent_get first and pass its key.id as expected_key_id. Same key/workspace/name retries return the same UUID; conflicting or inactive bindings fail without takeover or reactivation. Creates no key, changes no scope, and does not assign/import/start tasks.

  • task_archiveFree

    Archive a task, or several at once with `tasks` (max 50). They move to the Trash view, out of every working list, and stay readable there (task_list `view: "trash"`). Archiving is not completing: use task_done for work that was finished, and task_archive only for tasks the user wants gone. Confirm with the user first.

  • task_doneFree

    Mark a task as complete, or several at once with `tasks` (max 50). They move to the Logbook view. A set of 50 is undone one task_reopen call at a time, so confirm the list with the user first.

  • task_editwrite actionFree

    Update fields on one task (`task`) or on several at once (`tasks`, max 50). Only the provided fields are changed; omitted fields are left untouched. To remove a value, list the field in `clear` (e.g. `clear: ["deadline"]`). Notes replace the existing notes (no append). `assignee` assigns the task; clear it to unassign. `add_labels` and `remove_labels` change which labels are on it. Editing several tasks applies the same changes to every one of them and cannot be undone in one call, so confirm the list with the user first. For status changes use task_done, task_reopen or task_archive, and for checklist items use the available checklist tools; this tool does not change either.

  • task_listFree

    List tasks in the workspace, most recently updated first. Completed tasks are ordered by completion time, newest first. Filter by view (inbox, today, upcoming, anytime, someday, logbook, trash) and/or state (open, done, archived, all); `search` ranks matches within that filter. `view: "logbook"` reads completed tasks and `view: "trash"` archived ones, whatever `state` says. Returns up to `limit` tasks; `hasMore` is true when more matched than were returned, and passing `nextCursor` back as `cursor` reads the next page. To find a task by its words across every view use search instead, and task_show for one task's checklist, comments and files.

  • task_reopenFree

    Reopen a completed task, or several at once with `tasks` (max 50). Each returns to its previous view.

  • task_showFree

    Get full details for a single task: its fields, labels and checklist items, by workspace-scoped task number. Add `include` for the parts that cost extra reads: `["comments"]` for the discussion thread (oldest first, with author and whether each was edited) and `["attachments"]` for the files on it, each with a short-lived signed URL.

Public scan report

scanner v0.1.10 · 2026-11-03 · same rubric, same numbers if you re-run it

1 high1 low
  • –Code scanremote-only server, no package to scann/a
  • Live reliabilityremote reachable in 4612ms17/20
  • Tool poisoning17 tool descriptions checked15/15
  • Auth qualityopen endpoint exposes 5 write-action tools with no auth3/15
  • Maintenanceno repository listed3/15
  • Maintainer identityendpoint served from the registry-verified namespace domain8/10

Findings (2)

  • highWrite-action tools reachable without authenticationauth.open-write
  • lowNo source repository listedmaint.no-repo
Overall 61/100. Components that don't apply are left out of the denominator. Any critical finding is an F.RubricAppeal a findingJSON

How Done Bear compares

Against every graded Productivity MCP server, from our own scans and uptime checks. Updated after each scan run.

Safety score
61/100
higher than 13% of 1,299 Productivity servers
Tools
17
the typical Productivity server has 7
Tools that change things
29%
typical: 0%. Fewer write tools means less an agent can break
Uptime
100%
of our recent checks; the typical remote Productivity server answers 100%
Response time
592 ms
faster than 22% of 655 Productivity servers

What its tools let an agent do: 12 read · 4 change · 1 send or post

Install Done Bear in Claude Code, Cursor or VS Code

claude mcp add --transport http donebear https://mcp.donebear.com/mcp
Add to Cursor

Grade history

  • 2026-11-03restoreD → Cscore 61: Write-action tools reachable without authentication; No source repository listed

Done Bear: common questions

Is Done Bear MCP server safe?
With care: it is graded C, so read the findings first (61/100). Read the Done Bear safety report
How do I install Done Bear?
It runs remotely at mcp.donebear.com. Add it to Claude Code, Cursor, VS Code or Claude Desktop with the snippets above, or call it through the mcp.market gateway without installing anything.
Does Done Bear need an API key?
Not as far as the registry entry and our scan can tell: no credentials are declared or required.
Is Done Bear maintained?
The latest release is v1.0.0.
Is Done Bear up?
100% of our last 28 checks got an answer. We check remote servers about four times a day.
What can I use instead of Done Bear?
Servers from other publishers that do the same job: Obsidian MCP server, Agent-Native Content MCP server and Nano Banana by Ace Data Cloud MCP server.
How does Done Bear compare with other Productivity MCP servers?
safety score 61/100 (higher than 13% of 1,299 Productivity servers); tools 17 (the typical Productivity server has 7); tools that change things 29% (typical: 0%. Fewer write tools means less an agent can break). Full comparison.

Alternatives to Done Bear

Same job from other publishers: the closest match first, then the best rated.

  • Obsidian
    Read, write, search, and surgically edit Obsidian notes, tags, and frontmatter via MCP.
    A
  • Agent-Native Content
    Open-source Obsidian for MDX - edit local docs with agent assistance
    A
  • Nano Banana by Ace Data Cloud
    Generate and edit Nano Banana images with Ace Data Cloud; retrieve the same task for results.
    A
  • loci
    Cross-session memory and hybrid RAG over your notes and docs. Local-first, with cited answers.
    A
  • Better Notion
    Markdown-first Notion for AI agents -- pages, databases, blocks, and comments in one call.
    B