← All MCP tools
What it does
Approve a task that's pending_approval, marking it done. Human-only — this always errors when called by an agent (there's no way to tell a supervising agent from the one that proposed it); a human approves it in the app.
Parameters
| Name | Type | Required | Description |
|---|---|---|---|
id | string | Required |
Annotations
The hints the server sends with this tool. A host reads them to decide whether to ask you before a call.
- Read-only
readOnlyHint: false - Changes data in your Done account.
- Destructive
destructiveHint: false - Only adds or reads; nothing already there is removed or overwritten.
- Idempotent
idempotentHint: false - Each call can add something new, such as a comment, a run or a task.
- Open world
openWorldHint: false - Touches only your own Done account.
Which tokens can call it
A connection made with OAuth has full access. A token from Settings → Agent access → Extra MCP tokens can be narrowed, and a narrowed token never sees beyond its project or workspace.
- Full accessAllowed
- Read-only tokenRefused
- Single-project tokenRefused
- Single-workspace tokenAllowed
Try it
There's nothing to ask an agent here: only a person can do this, in the app's Needs you queue. An agent that calls it gets an error, by design.
Connect Done to your assistant
One MCP endpoint per account, over OAuth or a token. Step-by-step setup for each client: