Yes — Codex can build, launch and manage your LinkedIn campaigns, posts and recruiter jobs in WarmySender, all in plain language, through the same 78-tool connection Claude, ChatGPT, Cursor, Codex, OpenClaw, and Hermes Agent share. You ask in the Codex 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.
Codex is OpenAI’s coding agent and runs in your terminal, so you talk to it in the shell you already use for the rest of your pipeline. It connects with one add command and one login command; the login opens a WarmySender sign-in in your browser, so there is no key to paste. LinkedIn campaigns via Codex fit a developer-led sales motion: the profile list comes out of a script, Codex creates the campaign and enrolls it, and the scheduler paces every invite and message. Ask Codex for throttle and account health when a day looks quiet.
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 LinkedIn outreach |
|---|---|
| Can | Create a connection-and-message campaign and choose the account and steps. |
| Can | Start, pause and resume a campaign, and enroll the people you choose. |
| Can | Draft, publish and delete posts, and read their engagement. |
| Can | Create, publish and close recruiter job postings and read the applicants. |
| Can | Report on campaign stats, account health, and why an account is quiet today. |
| Cannot | Send an invite or a message itself — WarmySender’s scheduler spaces every action inside your account’s daily and hourly limits. |
| Cannot | Raise a daily or hourly limit, shorten the ramp on a newer account, or skip a cooldown. |
| Cannot | Connect or disconnect a LinkedIn account — that stays with you in the app, and a LinkedIn seat is required. |
| Cannot | Fire actions in a burst — enrolling a thousand people still goes out at the safe rate, spread over time. |
| Cannot | Read or reply to conversations — replies stay in WarmySender’s inbox, with you. |
OpenAI's coding agent registers WarmySender with one command and signs in through your browser — no key to paste.
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 Codex route is: 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.
Create a LinkedIn campaign called "Founders Q4" on my main account: connect first, message three days after they accept, enroll these 60 profiles, then start it.
Pause every LinkedIn campaign on that account until Monday.
Why is my LinkedIn account quiet today, and when does it pick up again?
Publish a post about our new release, then show me the engagement in two days.
Load the LinkedIn URLs from leads.txt, create a connect-then-message campaign on my main account, enroll them, and print the throttle.
Codex 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 Codex to WarmySender and ask in plain language, in the Codex terminal — it can build, launch and manage your LinkedIn campaigns, posts and recruiter jobs. 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.
OpenAI's coding agent registers WarmySender with one command and signs in through your browser — no key to paste. 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 Codex", and the full install hub for every agent is at /ai-agents.
No. Nothing an agent can call moves a limit — not the daily or hourly invite and message limits, the ramp on a newer account or a cooldown. Codex 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 LinkedIn account once in WarmySender; after that Codex can use it.
No. The agent never sends an invite or a message directly and can never raise a limit. Creating or launching a campaign only writes the plan and hands it to WarmySender’s scheduler, which paces every LinkedIn action inside safe daily and hourly caps and a gradual ramp — the same protections that apply when a human clicks the buttons. Run only one automation tool per account; account safety always wins.
No. The add command registers the server address https://warmysender.com/mcp and the login command opens a browser sign-in — nothing to paste or store. Prefer a key anyway? Create one under Settings › API Keys and use the key form on the AI Agents hub.
No. Codex only writes the campaign or the setting; once it has handed that to WarmySender, the scheduler paces every invite and message on its own whether or not Codex is running.
Yes. Each client registers the server and signs in on its own; they reach the same workspace and the same safe limits, and the scheduler paces every invite and message exactly the same whichever agent wrote the campaign.
Last updated: 2026-09-09