Inbox Triage
Start free trial

My AI said it was not allowed to do that

The block comes from your AI app's own safety rules, not from Inbox Triage. Ask again in your own words in the same chat, approve the prompt if the app shows one, or do the step yourself on the website: Inboxes to add or connect an inbox, Screened to rescue or report mail, Settings for VIPs and rules.

Last updated

What happened

AI apps decide for themselves which actions need your say-so. Adding an inbox, reporting spam, or changing a setting can be refused when the app is not sure the request came from you, for example when it arrived through another chat, a schedule, or a message relayed from somewhere else. Inbox Triage never saw the request, so nothing changed on your account.

What to do

  1. Ask again yourself, in the same chat. A plain request in your own words ("add matthew@yahoo.com as an inbox") is what the app is looking for.
  2. Approve the prompt. Some apps show an Allow button when a connector wants to make a change. Choose it once for the action, or always for this connector.
  3. Do it on the website. Everything your AI can change, you can change here: Inboxes to add, connect, pause or remove an inbox; Screened to rescue or report mail; Settings for VIPs, junk screening and rules.

Claude Code and other command-line agents

These tools keep a permission list. To let this connector make changes without a prompt each time, add its tools to the allow list in the project's settings, for example mcp__claude_ai_Inbox_Triage__add_inbox, or run the agent in a mode that asks you instead of deciding on its own. Your AI can tell you the exact rule name for the action it was refused.

Connect links last about 10 minutes. Ask for a new one, or choose Connect on Inboxes.

Related articles

Still stuck? Email help@getinboxtriage.com.