confirm_action
Runs a generated DELETE operation that another tool staged and returned as status: "approval_required" with a summary and a one-time approval token. Intended for use after the user approves that summary. A token that is never confirmed expires after 5 minutes, and the staged action does not run. ...
This record as markdown: /tools/doit/confirm-action.md
What confirm_action does on Doit
AI agents call confirm_action to permanently remove resources in Doit, typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
| Parameter | Type | Required | Description |
|---|---|---|---|
token | string | Yes | The one-time, user-bound approval token returned by a staged generated DELETE call. Expires after five minutes. Exactly as received, no quoting changes. |
Parameters from the server's own tool schema.
Why confirm_action is rated Critical
An AI agent that decides to call confirm_action doesn't hesitate, doesn't double-check, and doesn't stop at one. Whatever it removes from Doit is gone. There is no undo for destructive operations.
Risk signalsHandles credentials or secrets (token)
Attacks that exploit this kind of access
The rule that runs confirm_action safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Doit, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For confirm_action, this is the rule to start with:
confirm_action is removed from the agent's tool list entirely, so the agent never calls it. The rest of the server keeps working.
The button opens the PolicyLayer dashboard: create your workspace, connect Doit, apply this rule, and every confirm_action call is checked against it from then on.
Questions about confirm_action
Runs a generated DELETE operation that another tool staged and returned as status: "approval_required" with a summary and a one-time approval token. Intended for use after the user approves that summary. A token that is never confirmed expires after 5 minutes, and the staged action does not run. The token is bound to the authenticated caller and must match exactly. An attempted confirmation consumes it even if the caller differs or execution fails. Creates and updates are not staged by the current tool registry. It is categorised as a Destructive tool in the Doit MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
confirm_action accepts 1 parameter: token. Required: token. The full parameter table on this page comes from the server's own tool schema.
Register the Doit MCP server in PolicyLayer and add a rule for confirm_action: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Doit. Nothing to install.
confirm_action is a Destructive tool with critical risk. Critical-risk tools should be blocked by default and only enabled with explicit human approval.
Yes. Add a rate_limit block to the confirm_action rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for confirm_action. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
confirm_action is provided by the Doit MCP server (@doitintl/doit-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Doit, and thousands of servers like it.
Across the catalogue