// AGENT · CLI

An AI agent CLI your coding agent can actually call

Coding agents are already fluent in one interface: the command line. Clize is an AI agent CLI built for them to call — stable commands that claim handles, buy domains, send email, and deploy.

Why a CLI for AI agents

An agent doesn't need a dashboard — it needs a surface it can call reliably and read back. A CLI is exactly that: deterministic commands, predictable output, no clicking. The same property that makes a CLI good for scripts makes it good for an agent CLI.

CLI, Skill, and MCP — three ways in

  • CLI — the stable operation layer. Plain commands an agent (or you) can run and a script can pin.
  • Skill — the trigger layer for Claude Code, reached for when a task needs the real world.
  • MCP — the structured tool layer; the same actions as typed tools the agent discovers. See the MCP server.

What the agent CLI can do

  • Domains — check availability, buy a handle, point DNS.
  • Email — a real inbox the agent can send from and receive into.
  • Deploy — ship a static site to a live URL over HTTPS.
  • Status & context — inspect what's claimed, deployed, and pending.
  • Billing & pay links — quote costs and collect payment, gated.

The safety gates

A command line that can spend money needs guardrails built in. 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.

It pairs naturally with Codex and Claude Code.

FAQ

What is an AI agent CLI?

An AI agent CLI is a command-line tool built to be called by a coding agent rather than typed by a person. Commands are stable, scriptable, and predictable, so an agent can run them deterministically. Clize is one — for real-world actions like domains, email, and deploy.

How is an agent CLI different from an MCP server?

Same capabilities, different surface. The MCP server exposes typed tools the agent discovers automatically; the CLI is the stable command layer underneath. A step can fall back to a plain command when you want determinism or a script. Clize ships both.

Which agents can use it?

Any agent that can run a shell command. Clize wires into Claude Code and Codex directly via clize install, and the same commands work from any script or coding agent.

clize init — ready

The CLI your coding agent reaches for.

Install once and your agent gets stable commands for domains, email, deploy, and support — as a CLI, a Skill, and an MCP server.

$ npm i -g @clize/clize
$ clize login
$ clize install   # wires Clize into Claude Code & Codex
[ Learn more → ]