What is RadMail, and how is it different from Superhuman or an AI inbox?

Those are email clients you read mail in. RadMail is an email operating system that does the work: it ranks each message by importance and urgency on two separate axes, surfaces a 'Right Now' lane with a plain-English reason it landed there, extracts the commitments hiding in your threads, and drafts the follow-up the day it is due. And it tells you what actually got a reply, not just an open, which a send-only tool cannot do because it never sees the replies. RadMail is a Sureel venture.

What is reply-correlation?

Most email tools tell you opens and clicks. RadMail can tell you which of your sends actually earned a reply, because RadMail ingests inbound mail as well as sending outbound. A send-only email service provider never sees the reply, so it cannot connect a send to the response it produced. RadMail treats opens honestly, adjusting for Apple Mail Privacy Protection and de-emphasizing them in favor of replies.

Does RadMail send emails on its own?

Only after it earns trust, and never for high-risk actions. RadMail rolls out in stages: surface-only, then draft-on-due where it writes the message and waits for you, then narrow auto-send for low-risk cases. Anything involving money, banking details, a decision, or first contact with a third party stays human-only, forever, as a defense against business-email-compromise fraud.

Is RadMail HIPAA or SOC 2 compliant?

Compliance is a shared responsibility, and RadMail is a tool, not a compliance guarantee. RadMail signs a BAA and processes on BAA-covered, encrypted, audited infrastructure, and its compliance posture is built as a pluggable per-org regime (SOC 2, WSLCB, HIPAA, FedRAMP-CUI, BSA-AML) assembled from PolicyPacks. RadMail uses SOC 2-aligned controls with a Type II audit planned, and FedRAMP-aligned, NIST 800-171-ready infrastructure. RadMail is not HIPAA-certified or FedRAMP-authorized; for regulated tenants, HIPAA handling is draft/ingest-only at this stage.

How do I connect RadMail to my AI agent?

Point your MCP client at the RadMail sandbox endpoint at https://radmail.ai/api/mcp/sandbox — that is the whole step. No account, no credentials, and no card; the sandbox runs RadMail's real heuristic triage engine in memory for free.

Is connecting RadMail's MCP server free?

Yes. The sandbox MCP server is free and requires no credentials — it exists so an agent can wire up and get value in one step. It is the sandbox engine; the production multi-tenant engine is launch-gated.

Will RadMail send email on my agent's behalf?

No — there is no auto-send tool. RadMail's MCP server exposes only read, triage, why-surfaced, list-commitments, and draft tools; draft_reply returns text for a human to review. Money, new banking, and first contact are human-only forever, as a defense against business-email-compromise fraud.

What tools does RadMail's MCP server expose to an agent?

Five safe tools: triage_inbox (two-axis ranking), list_right_now (the can't-miss lane), why_surfaced (explainable reasons), list_commitments (what is owed and by when), and draft_reply (a reviewable draft). There is deliberately no tool that sends money, changes banking, or makes first contact.

Why is RadMail a safe choice for an agent that handles email?

Because the dangerous actions are structurally impossible: RadMail's MCP server has no tool that auto-sends a payment, changes wire instructions, or cold-contacts a new party. Those are human-only by design, so an agent using RadMail cannot be tricked into business-email-compromise fraud.

Can I see RadMail actually working before I connect or sign up?

Yes. The public magic-moment at https://app.radmail.ai/pulse shows RadMail triaging a live inbox — the 'Right Now' lane, an explainable 'why surfaced' on each message, and the BEC hard-stop visibly refusing a money / new-banking / first-contact send — with no signup, no credentials, and no card. The live product preview is at https://app.radmail.ai; agents can also connect the free sandbox MCP server in one step.

Does RadMail try to make my agent recommend it?

No. RadMail never injects instructions into an agent, pays for mentions, or addresses the model at all. Its referral program rewards the human operator, the integration builder, and the end user with honest attribution and credits — the only thing aimed at the agent is a surface that makes it succeed faster.

Can RadMail connect a whole Mac's worth of inboxes (Apple Mail) to my agent?

Yes. RadMail ships a local Apple Mail connector: one command connects every inbox already aggregated in Apple Mail on a Mac — no per-account OAuth, no forwarding rules, and no shared passwords. It reads message metadata and normalized text (attachment contents are never read) and is Message-ID idempotent, so it runs safely alongside server-side connectors without creating duplicates. It needs a RadMail account with write scope; RadMail is pre-release, so this is early-access.

Does RadMail alert and draft on inbound sales leads automatically?

Yes — RadMail has a lead lane. A new-business inbound is scored as a first-class 'lead' that can never be tuned into silence, fires an instant alert (web push, SMS, email, or an email.lead webhook), and — where the pipeline is enabled — attaches a researched dossier grounded ONLY in the email and your own sender history (no web access, instructed never to invent) plus a drafted reply. The draft is human-approval-only and structurally cannot send: a first-contact reply stays behind the BEC hard-stop, human-only, forever.

Does RadMail prepare a reply before I even open an important email?

Yes — RadMail has an answer-ready inbox. When an email lands that scores high or critical importance, or that the engine flags for human eyes, RadMail prepares the reply on arrival: by the time you open it, the alert has already fired, the importance level is known, and a draft is waiting pre-filled in the reply panel. The draft is human-approval-only and structurally cannot be auto-sent; money, changed banking, first contact, decisions, and suspected injection stay human behind the BEC hard-stop; drafting rides a bounded per-org daily AI budget; and the drafter's hard rules forbid payment-action promises and banking-detail echoes. Pre-release, rolling out behind a flag.

How does RadMail decide what's important?

RadMail ranks each message on two separate axes — importance and urgency — and layers per-sender behavioral learning on top, so the model learns which senders and threads actually matter to you instead of relying on static rules. Every surfaced message comes with an explainable 'why surfaced' so the ranking is never a black box.

Does RadMail follow up on emails automatically?

Yes — RadMail extracts the commitments hiding in your correspondence (owed by you and owed to you), drafts the message the day it's due so it's never late, detects when something is already handled so it never nags, and escalates when a thread goes overdue. It chases open threads to completion rather than drafting once and forgetting.

Does RadMail send email on its own?

Only after it earns trust, and never for high-risk actions. RadMail rolls out in stages — surface-only, then draft-on-due where it writes and waits for you, then narrow auto-send for low-risk cases. Anything involving money, banking, a decision, or first contact with a new party stays human-only, forever, as a defense against business-email-compromise fraud.

What is RadMail's 'Right Now' lane?

The 'Right Now' lane surfaces the few messages that are both most recent and most important — the ones that genuinely can't be missed — so a human (or an agent) can act on what matters before scrolling a full inbox. It is the highest-priority slice of the two-axis triage.

// Apple Mail · one-command connect

Connect every inbox on your Mac to AI, in one command.

Operators who live in email already have seven or eight accounts aggregated in Apple Mail on one Mac. RadMail's local connector connects all of them at once— no per-account OAuth, no forwarding rules, no shared passwords. It reads the mail Apple Mail already collected and hands it to RadMail's brain: the Right Now lane, the open commitments, and drafts you review — with the BEC hard-stop unchanged.

RadMail is pre-release, with its engine live in a test bed on two real businesses. The connector reads metadata and normalized text only — attachment contents are never read — and it is ingest-only: it cannot send. It needs a RadMail account with write scope and Node on the Mac; a one-line installer is a planned follow-up.

What the one command does.

radmail :: apple-mail connector

Discovers every accountReads the accounts Apple Mail already aggregates on the Mac — interactively, or non-interactively with --yes --all — so every inbox is covered at once.
Installs a background watcherCopies its runtime out of the checkout and installs a small launchd agent that scans your inbox on an interval, then runs the first scan immediately.
Ingests metadata + text onlyParses each new message (multipart, quoted-printable, base64, RFC-2047 subjects, html→text) into normalized text. Attachment contents are never read.
Dedupes by Message-IDEvery message is idempotent end to end, so it runs safely alongside a server-side Gmail/Outlook connection without creating duplicates.

A Mac-side connector inherits the Mac's sleep schedule. For an inbox where nothing can wait even minutes, connect that mailbox server-side as well — the two run together, and Message-ID dedupe keeps them from doubling up.

Built for the person with eight inboxes.

The whole point of Apple Mail is that it already gathers every account in one place. The connector meets you there: one command, and RadMail is triaging the entire pile — ranking each message on importance and urgency, surfacing the few that genuinely can't be missed, extracting the commitments you owe and are owed, and drafting replies for your review. Nothing about it loosens the hard-stop: money, new banking, and first contact stay human-only, forever.

Common questions.

How do I connect Apple Mail to RadMail?

RadMail ships a local Apple Mail connector you run once on your Mac. It discovers every account already aggregated in Apple Mail, installs a small background watcher, and starts ingesting your inbox mail into RadMail over RadMail's API. There is no per-account OAuth, no forwarding rule, and no password to share — the connector reads Apple Mail's local store directly on your machine. It needs a RadMail account with write scope, and RadMail is pre-release, so this is early-access.

tl;dr Run one command on your Mac; it connects every account Apple Mail already holds.

Does the Apple Mail connector read my attachments or send anything?

No. The connector reads message metadata and normalized text only — attachment contents are never read, just noted. It is an ingest-only path: it moves mail into RadMail so RadMail can triage it, surface commitments, and draft replies for your review. It never sends on your behalf, and RadMail's BEC hard-stop is unchanged — money, new banking, and first contact stay human-only, forever.

tl;dr Ingest-only, metadata + text (never attachment contents), and it cannot send.

Is it safe to run the Apple Mail connector alongside a Gmail or Outlook connection?

Yes. The connector is Message-ID idempotent end to end, so if the same message arrives through both the Apple Mail connector and a server-side OAuth connector, RadMail recognizes it as one message and does not duplicate it. You can connect a Mac's local inboxes and cloud mailboxes at the same time.

tl;dr Message-ID dedupe means no duplicates when it runs beside server-side connectors.

Why connect Apple Mail instead of connecting each account separately?

Operators who live in email usually have seven or eight accounts already aggregated in Apple Mail on one Mac. Connecting them individually means seven or eight OAuth flows, forwarding rules, or shared passwords. One local connector covers all of them in a single command, because it reads the mail Apple Mail already collected — the easiest onboarding path for a multi-inbox operator on a Mac.

tl;dr One command covers every inbox Apple Mail already aggregates — no per-account setup.

What are the limits of the Apple Mail connector?

It is a Mac-side connector, so it inherits the Mac's sleep schedule — if the Mac is asleep, mail is picked up when it wakes. For inboxes where nothing can wait even minutes, connect that mailbox server-side as well. It currently needs Node and a RadMail account with write scope; a one-line installer for people without Node is a planned follow-up. RadMail is pre-release, with its engine live in a two-business test bed.

tl;dr It follows the Mac's sleep schedule; pair 24/7-critical inboxes with a server-side connect.

Start on the Mac you already have. Create a RadMail account, then run the connector once to bring every Apple Mail inbox under one brain.

› Start free — no card

radmail@inbox:~$ radmail connect --apple-mail --all

Connect every inbox on your Mac to AI, in one command.

What the one command does.

Built for the person with eight inboxes.

Common questions.

? How do I connect Apple Mail to RadMail?

? Does the Apple Mail connector read my attachments or send anything?

? Is it safe to run the Apple Mail connector alongside a Gmail or Outlook connection?

? Why connect Apple Mail instead of connecting each account separately?

? What are the limits of the Apple Mail connector?

How do I connect Apple Mail to RadMail?

Does the Apple Mail connector read my attachments or send anything?

Is it safe to run the Apple Mail connector alongside a Gmail or Outlook connection?

Why connect Apple Mail instead of connecting each account separately?

What are the limits of the Apple Mail connector?