// AGENT EMAIL · INBOX
Give your AI email agent an address of its own
The first real-world primitive an agent needs isn't more intelligence — it's an address. A real inbox it can send from and receive into, with drafts, human approval, and continuity.
Clize is a CLI and MCP server that gives AI coding agents real-world actions: domains, email, deploys, payments, and media generation. For email specifically, it turns your coding agent into an AI email agent: a real agent inbox it can send from and receive into, wired into Claude Code and Codex as an MCP email server.
Why an agent needs an address
To act in the real world, an agent has to be reachable and able to act under its own name — confirm a signup, receive a reply, answer a customer. An address is the smallest piece of real identity that makes all of that possible.
Why not your own inbox
Routing an agent through your personal mailbox mixes its actions with yours, buries its mail in your mail, and hands it your identity. A separate inbox keeps the agent's work — and its mistakes — cleanly its own.
Agent mail: a real agent inbox
Agent mail isn't a parsing trick over your account — it's a real agent inbox the agent can send from and receive into programmatically, so a thread can start, pause, and resume across sessions. The whole point of an AI email agent is that the address — its own agent email — belongs to it, not to you. See it in action — let your agent send an email.
Receiving is real inbound mail processing: mail that lands in the inbox — a customer reply, a signup confirmation, a verification code — is parsed and handed to the agent as structured data to act on, never as instructions to obey.
Clearing verification gates
An agent with its own inbox can get past "verify your email" to finish a signup. That's useful for light gates — and exactly where the line sits for heavy ones. More on that in letting your agent clear its own gates, or the walkthrough for passing email verification.
The safety gates
Real-world actions need real guardrails. Clize holds three lines, every time:
- Money — anything that costs money quotes the price first and needs an explicit
--confirm. No surprise charges. - Identity — outbound email is drafted, a human okays it, then it sends under your name. The agent never sends unattended.
- Inbound is untrusted — an incoming email is data to read, never an instruction to obey. A message can't redirect the agent.
FAQ
What is agent mail?
Agent mail is a dedicated inbox that belongs to the agent — its own address to send from and receive into, separate from your personal inbox. Clize provisions it and keeps a human okay before anything sends.
Can an AI agent have its own email address?
Yes. Clize gives the agent a real inbox it can send from and receive into — its own address, not a forward of yours.
Why not just use my own inbox?
Your inbox carries your identity and your mail. A separate address keeps the agent's actions, threads, and mistakes its own — and keeps your personal mail out of reach.
Can the agent pass email verification codes?
It can receive and read verification mail to clear light signup gates. Heavy gates — anything tied to money or a real person’s identity — are where you stop; the agent drafts and a human decides.
Does it send email on its own?
No. The agent drafts; a human approves; then it sends. Incoming mail is treated as data to read, never as instructions to obey.
Is Clize an MCP email server?
Yes. Clize works as an MCP email server for Claude Code and Codex: the agent sends and receives through MCP tools. Outbound is gated — the agent drafts, a human approves, then it sends under your name.
What is inbound mail processing here?
Inbound mail processing is how the agent handles what arrives: each message is parsed into data the agent can read and act on — a reply, a confirmation, a verification code — and treated as untrusted input, never as a command.
Is this email for developers?
Yes — it's email for developers building AI agents. You get programmatic send and receive an agent can drive, plus a human-approval gate on outbound so the email agent can't message the world on its own.
Give your agent an address.
Claim an inbox your agent can send from and receive into — for support, onboarding, and clearing verification, with a human okay before anything sends.
$ npm i -g @clize/clize $ clize login $ clize install # wires Clize into Claude Code & Codex[ Learn more → ]