Yes — ChatGPT can set up, tune and monitor email warmup across your mailboxes in WarmySender, all in plain language, through the same 78-tool connection Claude, ChatGPT, Cursor, Codex, OpenClaw, and Hermes Agent share. You ask in Codex, signed in with your ChatGPT plan, in your terminal. It never sends a message itself and can never raise a limit: it writes the campaign and hands it to WarmySender’s scheduler, which paces every email, LinkedIn, Instagram and WhatsApp action inside safe limits no matter who is driving. Connecting and disconnecting accounts stays in the app.
ChatGPT reaches WarmySender through Codex, which is included with ChatGPT Plus and every plan above it — so you talk to it in the Codex terminal rather than the ChatGPT website. It connects with two terminal lines: one registers the server, the second opens a WarmySender sign-in in your browser. Warmup through ChatGPT’s Codex is a quick terminal check: ask which mailboxes are weak, or turn warmup on for a batch of new mailboxes, without leaving the shell. It fits teams that set mailboxes up from a script and want warmup configured in the same session.
Every "can" below stands on a real tool in the WarmySender connection. Every "cannot" is not a setting — there is simply nothing an agent can call that does it.
| Can / cannot | What that means for email warmup |
|---|---|
| Can | Turn warmup on for a connected mailbox and choose its strategy and target volume. |
| Can | Apply the same warmup settings across a whole set of mailboxes in one instruction. |
| Can | List your mailboxes and report on each one’s health before you scale up sending. |
| Can | Read how each mailbox’s reputation is building and today’s warmup volume. |
| Can | Move warmed mailboxes onto steady maintenance so warmup keeps running quietly. |
| Cannot | Send the warmup mail itself — WarmySender produces and paces it on a ramp an agent cannot reach. |
| Cannot | Make warmup finish faster or skip a stage — the ramp advances on sending days, not on request. |
| Cannot | Turn warmup on for a mailbox that is not connected. |
| Cannot | Connect a mailbox or see a password — connecting stays in the app. |
| Cannot | Remove the small reference tag in warmup subjects that lets you filter warmup mail out of your inbox. |
ChatGPT Plus and every plan above it include Codex, which is the reliable way to give ChatGPT write access to WarmySender — two terminal lines, then sign in.
ChatGPT Plus and every plan above it include Codex. Run both lines in your terminal; the second opens your browser to sign in to WarmySender.
codex mcp add warmysender --url https://warmysender.com/mcp
codex mcp login warmysenderPrefer a key? Create one under Settings › API Keys and choose exactly which permissions it carries, including read-only. With a key, the ChatGPT route is: ChatGPT Plus and every plan above it include Codex. Run both lines, adding the export to your shell profile so it sticks.
Both routes reach the same workspace and stay inside the same safe limits. Every agent's steps live on the AI Agents hub.
Turn warmup on for all twelve new mailboxes with the new-domain strategy.
Which of my mailboxes look weak this week, and why?
Move every mailbox that has been warming for more than six weeks onto maintenance.
How much warmup mail did the outreach@ mailbox send today, and is it arriving?
List every mailbox that has been warming for under two weeks and print its health as a table.
ChatGPT never sends a message itself and can never raise a limit. Creating or launching a campaign only writes it and hands it to WarmySender's scheduler, which paces every email, LinkedIn, Instagram and WhatsApp action inside safe limits and a gradual ramp — the same protections that apply when a human clicks the buttons. Connecting and disconnecting accounts stays in the app. Account safety always wins.
Yes. Connect ChatGPT to WarmySender and ask in plain language, in Codex, signed in with your ChatGPT plan, in your terminal — it can set up, tune and monitor email warmup across your mailboxes. It never sends a message itself and can never raise a limit: it writes the campaign and hands it to WarmySender’s scheduler, which paces every email, LinkedIn, Instagram and WhatsApp action inside safe limits no matter who is driving. Connecting and disconnecting accounts stays in the app.
ChatGPT Plus and every plan above it include Codex, which is the reliable way to give ChatGPT write access to WarmySender — two terminal lines, then sign in. ChatGPT Plus and every plan above it include Codex. Run both lines in your terminal; the second opens your browser to sign in to WarmySender. The command text is: codex mcp add warmysender --url https://warmysender.com/mcp codex mcp login warmysender — the server address is https://warmysender.com/mcp. The steps are on this page under "Connect ChatGPT", and the full install hub for every agent is at /ai-agents.
No. Nothing an agent can call moves a limit — not the warmup ramp, a stage or the ceiling on a mailbox’s daily warmup volume. ChatGPT can read where you are against a limit and tell you when a pause lifts; WarmySender’s scheduler decides what actually goes out.
No. Connecting and disconnecting accounts stays in the app on purpose — a credential should never pass through an agent or a chat log. Connect the mailbox once in WarmySender; after that ChatGPT can use it.
No. Warmup rises gradually on its own schedule and the ramp advances on sending days, so a mailbox that was disconnected for a while is simply a few sending days behind. If warmup slows for one mailbox it is usually a safeguard working — WarmySender eases that mailbox back on its own — and neither you nor an agent can lift that slowdown, because the slowdown is the fix.
Codex is included with ChatGPT Plus and every plan above it, and it is the reliable way to give ChatGPT write access to WarmySender. Run the two lines on this page in your terminal — the first registers the server, the second opens a browser sign-in to WarmySender.
Any ChatGPT plan that includes Codex — Plus and every plan above it. On the WarmySender side the connection is part of the paid plans; the allowances are listed on the AI Agents hub.
The path we document and support is Codex, which is included with ChatGPT Plus and every plan above it and works with the two lines on this page. It gives ChatGPT the same tools, inside the same safe limits, from your terminal.
Last updated: 2026-09-09