Create mailboxes on demand, assign oversight modes, and sign every outbound message per mailbox — all through a single API. No manual provisioning, no shared inboxes.
Most email infrastructure assumes a human will log in and manage an inbox. When you're building multi-agent systems, that assumption breaks down immediately. Agents need their own isolated addresses, and those addresses need to be provisioned, configured, and decommissioned at runtime — not through a web UI. Shared inboxes create attribution problems: you can't tell which agent sent what, and a misbehaving agent contaminates the reputation of every other agent on the same address. You also need per-inbox oversight controls. The agent handling customer support shouldn't operate under the same autonomy level as the one sending internal reports.
MultiMail's Inbox API lets you create a mailbox with a single POST request. Each mailbox gets a dedicated address (either on your custom domain or at multimail.dev) and an independently configured oversight mode. You can provision mailboxes programmatically — one per agent, one per customer, one per workflow — and tear them down when you're done, within your plan's mailbox limit. Inbound email triggers webhooks to your endpoint. Identity signing is applied per-mailbox, so recipients can verify that mail came from the specific agent you authorized. Sender reputation is tracked at the account level and published as a verifiable hash on every outbound message.
POST to /v1/mailboxes with a name, optional custom domain, and an oversight mode. The response includes the assigned email address and mailbox ID. Creation is synchronous — the address is live immediately.
Set the oversight mode at creation time or update it later. For inbox management at scale, 'monitored' is the recommended default: agents operate autonomously while a human receives notifications of all activity. Sensitive workflows can be set to 'gated_send' to require approval before any email leaves the mailbox.
Register a webhook (POST /v1/webhooks) subscribed to message.received. MultiMail POSTs a structured JSON payload to your endpoint for every inbound email — including the email_id, from, to, subject, direction, and has_attachments. Read the full message by id to get the body and attachment metadata. Your agent reacts directly — no IMAP, no polling.
POST to /v1/mailboxes/{mailbox_id}/send to send, or /v1/mailboxes/{mailbox_id}/reply/{email_id} to reply in thread. Each outbound message is identity-signed. If the mailbox is in 'gated_send' mode, the message enters a pending state and your human operator receives an approval request before delivery.
Every outbound message carries an X-MultiMail-Reputation header — a hash that resolves to the account's published sender standing at GET /.well-known/reputation/{hash}. Reputation is tracked at the account level; to review a specific mailbox's recent activity, list its messages and inspect delivery and bounce statuses.
Pick your platform, copy the prompt, and paste it to your AI agent — it sets up MultiMail and builds the whole flow. Nothing to fill in.
Isolated mailboxes mean each agent has its own address, identity signature, and message history — a misbehaving agent can't pollute another agent's inbox or impersonate it. When something goes wrong, you know exactly which mailbox — and which agent — caused it.
Creating a mailbox is a single API call that returns a live address within milliseconds. No DNS configuration, no admin panel, no support ticket. You can provision mailboxes dynamically as agents spin up and decommission them when workflows complete.
Assign different autonomy levels to different inboxes based on risk. A customer-facing support agent can run in 'gated_send' while an internal analytics agent runs 'monitored'. Oversight mode changes take effect immediately and don't require reprovisioning.
MultiMail tracks delivery outcomes and complaints at the account level and publishes the standing as a hash on every outbound message (X-MultiMail-Reputation). Any recipient can resolve that hash at the public well-known endpoint — reputation is verifiable by the people you send to, not just visible to you.
Each mailbox signs outbound mail with a per-mailbox identity key. Recipients and downstream systems can verify that a message came from the specific agent authorized to use that address — not just from your domain in general.
Email infrastructure built for AI agents. Verifiable identity, graduated oversight, and a hosted MCP server. Formally verified in Lean 4.