Connect your AI agent and run outreach in plain language

Connect any AI agent — Claude, ChatGPT, Cursor, Codex, OpenClaw, or Hermes Agent — to WarmySender and run your outreach just by describing what you want. You brief your agent in everyday English, it sets things up in your own WarmySender workspace, and WarmySender runs it on autopilot, 24/7, inside safe sending limits. It all works through the Model Context Protocol (MCP) — the open standard for connecting AI agents to tools.

WarmySender is a complete outreach platform: cold email, email warmup, LinkedIn outreach, Instagram outreach, multichannel sequences, and real-time email verification — all in one place. Once your agent is connected, most of that is one sentence away.

What your agent can do

With WarmySender connected, your agent can run your whole outreach — in plain language, on your behalf:

• Build and launch cold email campaigns — create a multi-step sequence, set the sending window and daily limits, and start it. Your agent handles the whole thing, start to finish.
• Build and launch LinkedIn and Instagram campaigns — create the campaign, choose the accounts and steps, and launch it. Same as cold email: your agent does it end to end, then enrolls prospects, pauses, and resumes on request.
• Publish and manage LinkedIn posts — draft a post, schedule it for later, or publish it to your profile or a company page, and list what you've posted with its engagement.
• Run LinkedIn recruiter jobs — create, publish, and close job postings, and read the applicants who apply (requires a LinkedIn Recruiter seat).
• Add and enroll prospects — create prospects or import a batch, then enroll them into a campaign or a list.
• Verify email addresses — check a single address or hand your agent a whole list; it returns which addresses are safe to send to.
• Tune warmup — turn warmup on for a mailbox, set its ramp strategy and target volume, and see how its reputation is building.
• Check inbox health and stats — ask which mailboxes have low inbox placement this week, how a campaign is performing, or which prospects have replied.

Your agent does it all — the scheduler keeps it safe

Your agent handles everything: building and launching campaigns on every channel, enrolling prospects, verifying emails, and tuning warmup. You don't have to author the sensitive parts yourself first — the safety doesn't come from making you do the work, it comes from WarmySender's scheduler, which paces every send inside safe limits no matter who pressed go.

There's exactly one thing that stays in the app: connecting and disconnecting your accounts. That's a deliberate security choice — your mailbox and social logins never pass through an agent. Everything else, your agent can do. It's not a limitation on what your agent can build; it's the one lock that keeps account access in your hands.

The safety line that never moves

Your agent never sends messages directly, and it can never raise a limit. WarmySender's scheduler paces every email and every LinkedIn or Instagram action within safe daily caps and a gradual ramp — the very same protections the app uses behind the scenes. Even if you ask your agent to enroll a huge list all at once, WarmySender still sends it out gently over time rather than in a burst. Account safety always comes first.

Two ways to connect

There are two ways to link your agent to WarmySender — pick whichever suits your setup:

• Sign in with your WarmySender account (simplest). Agents that support a one-click connect — like Claude — just ask you to point them at https://warmysender.com/mcp. An approval screen from WarmySender opens; you sign in with your account and approve, and you're connected. No key to copy or paste. Tip: sign in to warmysender.com in the same browser first so the approval finishes in a couple of clicks. For a step-by-step of this path in Claude, see Connect WarmySender to Claude.
• Use an API key (works with every agent). Create a key once and give it to your agent. This is the universal path — it works with any agent, including shared or headless setups where there's no one to click an approval screen. Steps below.

Both paths give your agent the exact same access to your own workspace, and both stay inside WarmySender's safe sending limits. You can switch between them or revoke access any time in Settings → API Keys.

Connect with an API key in 3 steps

1. Get an API key

In WarmySender, go to Settings → API Keys and create a key (it starts with ws_). Choose the permissions you want your agent to have — for full control, grant everything; for read-only monitoring, grant only the read permissions. The key is shown once, so copy it somewhere safe. This single key is what links your agent to your workspace. (Prefer not to use a key? Use the sign-in path above instead.)

2. Add WarmySender to your agent

Each agent has its own quick, one-time setup — a short config you paste in, or a single command you run. Two things stay the same across all of them: the WarmySender address is always https://warmysender.com/mcp, and you authenticate with the ws_ key from step 1. The connect an AI agent page has one-paste snippets for every supported agent — Claude, ChatGPT, Cursor, Codex, OpenClaw, and Hermes Agent — so you can pick yours and be live in a minute.

3. Ask your agent in plain English

That's the whole setup. From here, talk to your agent the way you'd brief a teammate, and it does the clicking for you.

Example prompts to try

Here are real things you can say once your agent is connected:

• Launch a cold email campaign: "Create a 3-step cold email campaign called 'Q3 SaaS founders', enroll these 40 leads, and launch it."
• Launch a LinkedIn campaign: "Build a LinkedIn campaign called 'Recruiter Outreach' on my main account, add a connect-then-message sequence, enroll these 25 profiles, and start it."
• Launch an Instagram campaign: "Create an Instagram DM campaign for these creators and launch it."
• Publish a LinkedIn post: "Publish a LinkedIn post announcing our new launch, and show me the engagement in a couple of days."
• Open a recruiter role: "Create and publish a LinkedIn job posting for a Senior Account Executive, then list the applicants as they come in."
• Verify a list: "Verify this list of 500 emails and tell me which ones are safe to send to."
• Check deliverability: "Which of my mailboxes have low inbox placement this week?"

WarmySender does the rest — building the sequence, enrolling the people, verifying the addresses, and pacing every send safely.

Which agents work

WarmySender works with Claude, ChatGPT, Cursor, Codex, OpenClaw, and Hermes Agent (Nous Research) — plus any agent that speaks MCP. The same ws_ key works across all of them, so you can drive WarmySender from whichever agent you already use, or switch between them freely.

Good to know

• It's included. Connecting an AI agent is included with any active WarmySender plan — there's no separate charge. See the pricing page for current plans.
• You stay in control. You can revoke a key any time in Settings → API Keys, and your agent's access stops right away.
• It's scoped to you. Your agent only ever works inside your own workspace. It can't see or touch anyone else's data, and it never sees your mailbox passwords or billing details.

Frequently asked questions

Which AI agents can I connect to WarmySender?

Claude, ChatGPT, Cursor, Codex, OpenClaw, and Hermes Agent (Nous Research), plus any agent that speaks the Model Context Protocol (MCP). One WarmySender API key works with all of them, so you can run your outreach from whichever agent you prefer.

What can my agent actually do?

Run your whole outreach. It can build, launch, and manage campaigns on every channel — cold email, LinkedIn, and Instagram (create, launch, pause, resume, enroll) — publish and manage LinkedIn posts, run LinkedIn recruiter jobs (create, publish, close, and read applicants), add and enroll prospects, verify email addresses, tune warmup, and check inbox health and stats, all in plain language. The only thing that stays in the app is connecting and disconnecting your accounts, for security.

Is it safe to let an AI agent run my outreach?

Yes. Your agent never sends messages directly and can never raise a limit. WarmySender's scheduler paces every email and every LinkedIn or Instagram action within safe daily caps and a gradual ramp — the same protections the app uses. Ask it to enroll a large list and WarmySender still sends everything out gently over time. Account safety always wins, and you can revoke access any time.

How do I connect my agent?

There are two ways. The simplest, with agents that support it (like Claude), is to point your agent at https://warmysender.com/mcp and then sign in with your WarmySender account on the approval screen that opens — no key needed. The universal way, which works with every agent, is to create an API key in Settings → API Keys (it starts with ws_), add WarmySender to your agent using the same address and that key, then ask in plain English. The "connect an assistant" page has one-paste setup for every supported agent.

Do I need an API key, or can I just sign in?

Either works. Agents that support a one-click connect — like Claude — let you point them at https://warmysender.com/mcp and simply sign in with your WarmySender account to approve, so there's no key to copy. Every agent also supports the API-key path: create a key in Settings → API Keys and give it to your agent, which is the way to go for shared or headless setups. Both give your agent the same access to your workspace and both stay inside your safe sending limits.

Does connecting an agent cost extra?

No. It's included with any active WarmySender plan — there's no separate add-on to buy. You can see current plans on the pricing page.

Can my agent build and launch a LinkedIn or Instagram campaign?

Yes — end to end. Your agent can create the campaign, set its steps and accounts, launch it, and then enroll prospects, pause, and resume. Launching a campaign only hands it to WarmySender's scheduler, which paces every invite and DM inside safe daily, weekly, and hourly limits and a gradual ramp. Nothing goes out in a burst, and your agent can never raise those limits.

Can my agent verify emails?

Yes. Ask it to check a single address or hand it a whole list, and it returns which addresses are safe to send to. Verification shares the same daily and monthly allowance and the same safe pacing as verifying in the app — your agent can't burn through it any faster.

What still stays in the app?

Just one thing: connecting and disconnecting your accounts. Your mailbox and social logins never pass through an agent — that's a deliberate security choice. Everything else about running your outreach, your agent can do.

Related reading

• Connect an AI agent — one-paste setup for Claude, ChatGPT, Cursor, Codex, OpenClaw, Hermes Agent, and more, and where to create your API key
• Connect WarmySender to Claude — the calm, step-by-step Claude connector walkthrough
• Integrations and API — the deeper technical reference for builders
• Plans and pricing — connecting an agent is included with every paid plan
• Full documentation — Cold Emailing, Email Warmup, LinkedIn Outreach, Instagram, and Multichannel guides