BetaFree during the beta — limits apply

Your agent answers customer email. Your rules decide what leaves.

Mailtender hosts your team's email on your own domain. Your agent reads threads and submits replies through the API; every reply passes a send gate — hard rules, review, kill switches and a full audit trail — before it is delivered.

Mailtender never calls an AI model. You bring the agent.

Never calls an AI model

Your agent, your model, your stack. Mailtender never sends customer mail to a model.

Reply-only agents

An agent can only reply inside an existing thread, to people already on it.

Untrusted by default

Everything a sender wrote reaches your agent as data, never as instructions.

How a reply travels

Every agent reply passes the send gate before it leaves

Your agent decides what to say. Mailtender decides whether it may be sent, holds it for a person when your rules say so, and records every step.

  1. 01 · Your agent

    Proposes a reply

    It reads the thread through the API, SDKs, CLI or MCP and submits a reply with an idempotency key.

    • Threads arrive in an untrusted envelope
    • A retry never sends twice
    • Events and webhooks for every state
  2. 02 · Send gate

    Decides what may leave

    Hard rules first, then the agent's mode, your policy rules and the kill switches.

    • Hard rules can't be turned off
    • Shadow, review or autonomous per agent
    • Approve, edit or reject when held
  3. 03 · Delivery

    Leaves from your domain

    Through Mailtender's own mail plane, with the decision recorded next to the message.

    • DKIM and SPF aligned to your domain
    • A decision snapshot for every reply
    • One audit trail for agent and human mail
Three modes

Autonomy is earned on evidence

Start every agent in shadow mode, compare its replies with what your team sent, and give it more room only when the record supports it.

shadow

Record, never send

The agent's replies are stored next to the reply your team actually sent, so you can compare them before trusting it.

Use it forA new agent, a new category, or a change to your prompt.

review

Hold for a person

Every reply waits for a supervisor to approve, edit or reject it — from the dashboard, webmail or the phone.

Use it forRefunds, billing and anything your policy rules mark as sensitive.

autonomous

Send within your rules

Replies go out without approval, still checked by the hard rules and your policy rules, and still audited.

Use it forCategories the evidence supports, such as password resets or shipping questions.

Kill switchStops one agent — or every agent in your organisation — in one action.

In every plan

Safety is never a paid upgrade

Plans differ in limits and support. The controls that keep a wrong reply from leaving are the same on every plan, including the beta.

Compare plans
  • Hard rulesReply only inside the thread, only to its recipients.
  • Kill switchesStop one agent or all of them at once.
  • Shadow, review, autonomousSet per agent, change it at any time.
  • Policy rulesOrdered and deterministic: hold, allow or block.
  • Untrusted envelopeSender content arrives as data, never as instructions.
  • Audit and snapshotsWhat the agent saw, proposed, and what left.
  • Events and webhooksSigned deliveries for every reply state.
  • API, SDKs, CLI, MCPTypeScript and Python SDKs from one OpenAPI file.
Mailtender Mail

Complete mailboxes for the people around your agent

Personal and shared mailboxes on your domain, so support, the agent and everyone's own mail live in one place. People's own mail passes its own, lighter rule set.

  • Webmail
  • Mobile app
  • Outlook
  • Apple Mail
  • Thunderbird
  • Gmail app
Explore Mailtender Mail
For developers

Wire your agent in an afternoon

A typed API with idempotent replies, events and webhooks. Generated SDKs, a CLI and an MCP server — so your coding agent can do the integration too.

  • REST API/v1 · OpenAPI
  • SDKs@mailtender/sdk · mailtender
  • CLIthreads, replies, approvals
  • MCP serverstdio · for coding agents
reply.ts
import { Mailtender } from "@mailtender/sdk";

const mt = new Mailtender({
  apiKey: process.env.MAILTENDER_API_KEY,
});

// Open threads in the shared mailbox your agent was granted
const threads = await mt.threads.list({
  mailbox: "support@acme.com",
  status: "open",
});

for (const thread of threads.data) {
  // Sender content arrives inside the untrusted envelope
  const body = await yourAgent.answer(thread.untrusted);

  const reply = await mt.threads.reply(thread.id, {
    body,
    idempotencyKey: `answer-${thread.lastMessageId}`,
  });

  console.log(reply.status); // "held": waiting for a person
}
Pricing

Free during the beta

Every plan includes the full safety baseline. During the beta there is nothing to pay — plan limits apply, and prices will be on the pricing page before charging starts.

FAQ

Questions, answered plainly

Something else? Write to hello@mailtender.net.

Does Mailtender write or edit replies with AI?

No. Mailtender never calls an AI model — no drafts, summaries or classifications. Your own agent writes the reply; Mailtender checks it against your rules, holds it for a person when you ask, and delivers it.

Can our agent email anyone it wants?

No. An agent credential can only reply inside an existing thread, to addresses already on inbound mail in that thread. It can't start a conversation or add a recipient — that is a hard rule, not a setting.

What about prompt injection in customer email?

Every subject, body, header and attachment name reaches your agent inside an untrusted envelope, marked as data. Whatever your agent proposes still has to pass the send gate before anything leaves.

Do we have to move our whole domain?

No. Start with forwarding or a subdomain for support, and move the root domain when you're ready. Import brings your existing mail with you.

Which mail clients can people use?

The built-in webmail, the mobile app, or any IMAP and SMTP client — Outlook, Apple Mail, Thunderbird or the Gmail app.

What does it cost?

Nothing during the beta; plan limits apply. Prices will be on the pricing page before charging starts.

Put your agent on email, with a person still in charge

Create a free account, connect a domain or start with forwarding, and hold your agent's first reply for review.