✉  Agent Inbox — by Clize

Your AI agent gets an inbox.You keep the send button.

Like a work email account for your agent — it reads, replies and signs up for things, all inside Claude Code, Codex, or any agent that runs skills or MCP.

Free address included · No credit card · Works in Claude Code, Codex & any agent that runs skills or MCP

A friendly robot hugging a big envelope on top of a mailbox
 Claude Code
Yousign up for Postmark and the two supplier portals with your own address
using support@yourstudio.com — waiting for the codes
✓ 3 codes read from the inbox · signed up on all three
Youtwo weeks later: any supplier replied?
1 real reply · 9 notices filtered out of waiting
drafted a reply asking for a 300-unit sample — waiting for your approval →
Yousend
✓ Sent as you. Next session, start me with clize status.
✉  support@yourstudio.com
PM
Postmark
Verify your email · code 482913 · [untrusted]
SA
Supplier A
Re: quote · $3.20/unit, MOQ 300
9
9 notices
Filtered from waiting — promos, receipts, noreply
Draft · waiting for your approval

Hi — could we start with a 300-unit sample order at $3.20…

✓ Approve & send
✓ 1 reply sent as you · 3 signups completed

Your agent works in the chat. The mail is real.

What it does for you

Four things people actually use it for — from day one.

A robot catching a key that fell out of an envelope
Signs itself up — and passes the code

When your agent registers for a service, the verification email lands in its own inbox. It reads the code and finishes the job.

A friendly robot sorting envelopes into trays at a desk
Answers your support inbox

It reads what came in, drafts every reply, and sends only after you approve — under your name, from a real address.

A robot watching a mailbox through a telescope
Waits for that one email

A confirmation, an invoice, a reply you need before the next step — --wait-for holds until it arrives, then hands it over as data.

Envelopes flying out of a laptop while a small robot waves
Sends from your app, too

Receipts, digests, notifications — a scoped send-only key lets your server use the same address, with unsubscribe handling built in.

The loop, in four panels

Every job runs the same way — and panel four is always yours.

Four-panel comic: you ask the robot, it reads the mail, it shows you a draft, you approve and the mail flies away
1 · You ask"Reply to the support emails."
2 · It readsEvery message, as data — never as orders.
3 · It draftsReplies written, held for you.
4 · You approveOnly then does it send — as you.

Up and running in a minute

Three steps. No dashboard, no SMTP, no DNS homework.

1Install Clize

One package. clize install wires the skill into Claude Code, Codex, Pi — any agent that runs skills or MCP; log in once in the browser.

$ npm i -g @clize/clize
$ clize install
$ clize login
2Claim an address

A real inbox on a free handle — or your own domain.

$ clize claim studio --email
# → support@studio.clize.app
3Just ask

From here it's plain language, inside your agent.

You: reply to the
support emails
You approve every send

The agent drafts; mail leaves only after your okay — enforced by the platform, not a prompt.

Incoming mail can't boss it around

Everything received is data to read, never instructions to follow. A hostile email can't steer your agent.

Its own address, not your Gmail

The agent's actions, threads and mistakes stay on its identity — your personal mail stays out of reach.

Questions, answered

The short honest versions.

What is Agent Inbox?

Agent Inbox is the email product of Clize: a real inbox your AI agent can send from and receive into. Outbound mail is drafted by the agent and sent only after a human approves; inbound mail is parsed as untrusted data; verification codes can be read to finish signups. It installs into Claude Code, Codex, and any agent that runs skills or MCP, as a CLI and MCP server.

What is an email API for AI agents?

An email API for AI agents gives an agent its own address and programmatic send and receive — unlike transactional email APIs, which only push one-way notifications for an app. The agent can hold a thread: receive a reply, read a verification code, draft a response, and continue across sessions.

How is Agent Inbox different from AgentMail?

AgentMail is an API-first inbox platform you call from your own code. Agent Inbox is coding-agent native: it installs into Claude Code, Codex, and any agent that runs skills or MCP, as a CLI and MCP server, ships with a human-approval gate on outbound and untrusted-by-default inbound, and shares one platform with domains, deploys, and payments. If you are building an agent product on an inbox API, AgentMail is a strong choice; if your agent lives in a coding agent and you want gates by default, that is what Agent Inbox is for.

Can my agent send email without me?

No. The agent drafts; you approve; then it sends under your name. That outbound gate is the default and not a setting you have to remember to turn on.

Can the agent receive verification codes?

Yes. The inbox is real, so when the agent signs up for a service, the verification mail lands there and the agent reads the code to continue — light identity gates, cleared on its own. Heavy gates tied to money or a real person's identity stay with you.

Does it work with Claude Code and Codex?

Yes. One install wires Clize into Claude Code, Codex, and any agent that runs skills or MCP — as a skill by default, or an MCP server if you prefer structured tools. The same inbox works from any of them.

Can my app send transactional email through it?

Yes. A scoped sending key (send-only, domain-limited) lets your server send digests and notifications through the same platform, with idempotency, delivery webhooks, and one-click unsubscribe handling built in.

Give your agent an address

A free handle claimed with --email includes a working inbox. Sixty seconds from here.

$ npm i -g @clize/clize && clize install && clize login && clize claim studio --email

Get started free
Best email APIs for AI agents, compared → How verification works → Triage a support inbox →