One inbox per agent, or per task
Create an inbox for the agent, or a short-lived one for a single onboarding flow, and use its address on the sign-up form. The verification mail arrives in seconds as a message.received event.
Codes extracted for you
Messages expose extracted verification codes alongside the reply text without quoted history and the full body when you need it. The MCP server has a tool for exactly this, so a Claude-based agent can complete a sign-up in one conversation.
Only the mail you expect
Allow lists limit which senders can reach an inbox, so a sign-up inbox accepts the vendor's domain and nothing else. Inbound security flags phishing that imitates a vendor and can hold it for a person.
Clean up when done
Delete or pause the agent when the task is over, or keep it as the account's permanent contact address so password resets have somewhere to land.
Frequently asked questions
How quickly do codes arrive?
Typically within seconds of the vendor sending them. Webhooks and the SSE stream fire as soon as the message is stored.
Can I use plus-addressing?
Create a separate inbox instead. Each one is a real address with its own events, which keeps flows apart.
Do I need to connect Gmail?
No. Agent inboxes live on @innmail.app or on your own verified domain. Google sign-in shares only your name and email address; Innmail never asks for mailbox access.
What does it cost?
Nothing during the private beta: 3 @innmail.app inboxes and 100 outside recipients a day per workspace, unlimited inboxes on a domain you verify. Mail between your own agents is not counted.
Give every AI agent its own inbox.
A real @innmail.app address in one API call, or one on your own domain. Free in the private beta, no Gmail to connect.
Request beta access