Real email for AI agents.

1. GET /v1/inboxes/:id/verification

   Sign up for services and read the code

   The call waits for the email and returns the code or magic link, with a confidence score.

   const inbox = await mr.inboxes.create({ client_id: 'signup-agent' });
   const since = new Date().toISOString();
   await signUp({ email: inbox.address }); // your agent fills in the form
   const v = await mr.messages.waitForVerification(inbox.id, { since, timeout: 60 });
   console.log(v?.code ?? v?.link); // "48213907"

   Verification codes →

2. GET /v1/inboxes/:id/messages/wait

   Answer customers from a support inbox

   Wait for mail, read only the new part of the reply, and answer in the same thread.

   const inbox = await mr.inboxes.create({ client_id: 'support-bot' });
   const msg = await mr.messages.wait(inbox.id, { timeout: 60 });
   if (msg && !msg.labels.includes('ai:injection-risk')) {
     const text = await answer(msg.extracted_text); // the new part only
     await mr.messages.reply(inbox.id, msg.id, { text });
   }

   Support agent use case →

3. POST /v1/inboxes/:id/drafts

   Send and follow up with human approval

   The agent writes a draft; a person approves, edits or schedules it in the dashboard.

   // This agent's key may write drafts, not send them.
   const draft = await mr.drafts.create(inbox.id, {
     to: 'dana@example.com',
     subject: 'Following up on your refund',
     text: 'Hi Dana, the refund went out today.',
   }); // waits in the dashboard until a person approves or schedules it

   Drafts and approval →

All use cases →

1. DRAFT

   Drafts wait for a person

   An agent can write a draft that waits in the dashboard until a person approves, edits or schedules it. A key can allow drafts without allowing sends, and every sent draft records who approved it.

2. SUPPRESSED

   Dead addresses stay dead

   Hard bounces and complaints put the address on a suppression list. The next send to it fails with 422 recipient_suppressed instead of hurting everyone’s reputation.

3. 20 / 5 MIN

   Limits are on by default

   Every workspace has a 5-minute burst limit and a daily send cap from its plan (20 and 100 on Free), so a runaway loop stops early. Each inbox has its own daily limit and each API key a rate limit. Workspaces with high bounce or complaint rates are suspended automatically.

These are guardrails, not guarantees. Give each agent a key scoped to its job, and send payments, credential changes or forwarding data through a draft a person approves.

Hosted in the EU by default

The API, mail servers, database and stored mail run in France, with a second EU server for backups.

Privacy switch

One workspace setting decides whether any email content goes to a model. Off keeps everything on our servers; login codes still work.

AI disclosure on every email

Every email an agent sends says, in a DKIM-signed header, that an AI agent sent it and for whom. A visible line is optional per workspace. Helps you meet transparency duties.

Encrypted off-site backups and monitoring

Nightly backups, encrypted before they leave the server, restore-tested every quarter, and health checks every 5 minutes.

DPA and sub-processors

A Data Processing Addendum, and a list of every third party that handles customer data, what it receives and where. Subscribe to be emailed at least 30 days before a sub-processor is added or replaced.

• Honestly, Agentboxd is exactly what I'd been looking for. Real inboxes for an agent, with phishing and prompt injection scores already on every email, saved me days of work. The attachment text extraction was a nice surprise too.