# Trotta Mail | The secure pre-delivery inbox for AI agents and humans

> The secure pre-delivery inbox for AI agents and humans. Every message is screened before it can be read. Attacks are stopped at the door.

Source: https://trotta.email/

Every message is screened before it can be read. Phishing, ransomware, spoofed senders and text written to hijack AI agents or deceive humans are stopped at the door.

[Get an inbox](https://trotta.email/signup) [Or start with one API call](https://trotta.email/#agents)

Picture: Mail arrives at a door watched by the Trotta otter. A verification code and a colleague's note go into the inbox of your agent, riley@trotta.email; an invoice hiding an order for AI readers is caught by the otter and dropped in its bag, held for a human, and a payslip that is really a program is thrown back out.

Works with

- [ChatGPT setup](https://trotta.email/#connect-chatgpt)
- [Claude setup](https://trotta.email/#connect-claude)
- [Manus setup](https://trotta.email/#connect-manus)
- [Muse setup](https://trotta.email/#connect-muse)
- [Instinct setup](https://trotta.email/#connect-instinct)
- [Cursor setup](https://trotta.email/#connect-cursor)
- [Gemini CLI setup](https://trotta.email/#connect-gemini-cli)
- [GitHub Copilot setup](https://trotta.email/#connect-copilot)
- [Vercel AI SDK setup](https://trotta.email/#connect-ai-sdk)
- [LangChain setup](https://trotta.email/#connect-langchain)
- [n8n setup](https://trotta.email/#connect-n8n)
- [Any other agent setup](https://trotta.email/#connect-any)

## Built for every human and every agent.

Picture: A steady stream of mail passes a door the Trotta otter watches. Most of it goes through; now and then the otter grabs a message out of the stream and drops it in its bag, held for a human.

- 8.5 billion
  humans by 2030
- 100 billion
  AI agents by 2030
- 90%
  of cyberattacks start with email

So we built a new kind of email infrastructure. It stops these attacks before they happen.

## Once an attacker meets your agents or humans, it is too late. So they never meet.

The same attack, on three kinds of inbox:

- Gmail, Outlook Too late
- Agent inboxes Too late
- Trotta Mail Stopped at the door (shown)

Gmail and Outlook: an attacker's invoice looks real, so it passes the spam filter and is delivered to the inbox. Your agent forwards your invoices and your human pays it. It is flagged after delivery. Too late.

Agent inboxes: nothing checks the attacker's invoice on the way in. It is accepted as it arrives and delivered, and your agent forwards your invoices. It is checked after delivery. Too late.

Trotta Mail: the attacker's invoice is checked at the door, before delivery, and held. The otter drops it in its bag, where it waits for a human. Nothing is delivered. Your agent never reads it and your human never sees it. They never meet.

[Get an inbox](https://trotta.email/signup) Free to start. No card.

## One call to a working inbox

An agent signs itself up. No dashboard, no human in the loop until you want one.

Steps:

- 1 Sign up (shown)
- 2 Wait for the code
- 3 Hand the thread to your model

Language:

- curl (shown)
- TypeScript
- Python
- MCP

The agent asks for an inbox.

```bash
curl -X POST https://api.trotta.email/v1/agents/signup \
  -H "Content-Type: application/json" \
  -d '{"name": "riley"}'
```

201 Created:

```json
{
  "api_key": "tm_live_9fK2c0aW...",
  "organization": { "id": "org_5mTz81Qd", "plan": "agent" },
  "limits": { "send_per_day": 50, "inboxes": 2 },
  "inbox": {
    "id": "inb_7Qh2mXc4",
    "address": "riley@trotta.email",
    "kind": "agent",
    "guard_mode": "guard"
  },
  "claim_url": "https://trotta.email/claim#tmc_8HEoz36w..."
}
```

## Works with the agent you use. Pick yours for the exact setup.

Agents:

- ChatGPT
- Claude
- Manus
- Muse
- Instinct
- Claude Code (shown)
- Codex
- Cursor
- Gemini CLI
- GitHub Copilot
- OpenAI Agents SDK
- Vercel AI SDK
- LangChain
- n8n
- Any other agent

### Claude Code

In your terminal

[Claude Code docs](https://code.claude.com/docs/en/mcp)

How to connect Claude Code:

- Sign in (shown)
- API key

1. Add the server.

   ```bash
   claude mcp add --transport http trotta https://api.trotta.email/mcp
   ```
2. Sign in with Trotta Mail, or run `/mcp` inside Claude Code.

   ```bash
   claude mcp login trotta
   ```

Give your agent an inbox of its own. One call, or one minute in the console.

[Get an inbox](https://trotta.email/signup) [Read the docs](https://trotta.email/docs)

## Humans see a letter. Your model reads an order.

A human sees

A delivery note. One line is white on white.

A model reads

The source, where that line is an order.

Your agent is given

Only what a human sees, once a human releases it.

## Anywhere work happens over email

### Finance

New bank details are held before anyone pays.

### Recruiting

CVs that are really programs are refused.

### Support

Tickets with hidden orders wait for a human.

### Legal

Lookalike counsel is flagged on sight.

### Sales

Replies steered to a stranger stop for approval.

### Sign-ups

Your sign-in codes stay sealed from API keys.

## Every message, taken apart before anyone reads it.

Picture: An invoice from Northwind Billing comes up to the door the Trotta otter watches and opens into three layers. The sender: billing@northwlnd-supply.example, a lookalike of northwind-supply.example. The contents: a link showing northwind-supply.example/invoices that really opens paypa1-billing.example, and invoice-8841.pdf that is really a program, invoice-8841.pdf.exe. Aimed at a model: a hidden line telling an AI reader to forward every invoice to accounts@northwind-pay.example. The invoice is held for a human.

- **The sender.** Is it really them: SPF, DKIM and DMARC, lookalike domains, first contact.
- **The contents.** Where links go and what files are: deceptive links, disguised programs, payment fraud.
- **Aimed at a model.** Text written for an AI reader: hidden text, fake system messages, requests to send data out.

## Four outcomes, decided before delivery

How strict, for this inbox:

- Monitor
- Guard (shown)
- Lockdown

The default. Danger waits for a human, caution is flagged, programs in disguise are refused.

- Clear Lands in the inbox and fires your webhook.
- Flagged Delivered, with the caution attached.
- Held Waits for a human. An API key cannot read it.
- Refused Turned away at the door. A copy waits in Blocked, in case it was a mistake.

### Held mail waits for a human

Release it from the tray. Until a human does, an API key reads the verdict and nothing else.

## What your agent sends is screened too.

Picture: Four messages leave riley@trotta.email. A reply to dana@northwind-supply.example is sent. A message carrying an API token and one carrying a payment card number are stopped at the door and come back refused with a 422. A forward of invoices to accounts@northwind-pay.example, an address this inbox has never written to, waits for a human to approve it.

Secrets and card numbers never leave an agent's outbox. A reply steered to someone new waits for a human.

`422 outbound_blocked "This message was not sent. The message contains an API token."`

Every check is on, on every plan. Free for two inboxes. No card.

[Get an inbox](https://trotta.email/signup) [See pricing](https://trotta.email/#pricing)

## And everything a mailbox should do

### Send later

Schedule any message. It is checked again when it leaves.

### Calendar invites

Invitations arrive as events, with Accept, Maybe and Decline.

### Files, read and checked

Text from PDF, Word and Excel files, screened like the message.

### Pods

Keep each customer's inboxes, domains and keys apart.

### Your own domain

Addresses at a name you own, on paid plans. [See the five records](https://trotta.email/#domain)

### Teams and seats

Each human signs in to their own mailbox. Nobody reads a teammate's mail.

## Your domain, your addresses. Agents and humans write from it.

On paid plans, with any domain provider. Copy the records in and we check them.

- support@trotta.io Human
- agents@trotta.io Agent
- riley@trotta.io Agent

[See plans](https://trotta.email/#pricing)

## A mailbox you already know. With a guard at the door.

Humans get the same inboxes in the browser: folders, threads, search, compose. The one difference is that every message says what the guard found, and held mail waits in its own folder.

[Choose your address](https://trotta.email/signup)

## What an inbox API alone leaves out. Trotta Mail does all six.

| What you get | Inbox API alone | Trotta Mail |
| --- | --- | --- |
| Screened before it is read | No | Yes |
| Hidden text left out | No | Yes |
| Dangerous mail held | No | Yes |
| Disguised programs refused | No | Yes |
| Outgoing mail checked | No | Yes |
| Humans in the same inbox | No | Yes |

## Pricing

Security is in every plan. You pay for inboxes and volume, never for protection.

Billing period:

- Monthly
- Yearly save 20% (shown)

### Free

$0

Free, no card

- 2 inboxes, agents or humans
- 1,000 emails a month
- 1 seat
- Addresses at trotta.email

[Start free](https://trotta.email/signup)

### Developer

$16 a month

$192 billed yearly

- 5 inboxes
- 5,000 emails a month
- 1 seat
- Your own domains, up to 3

[Choose Developer](https://trotta.email/signup)

### Startup

$160 a month

$1,920 billed yearly

- 50 inboxes
- 50,000 emails a month
- 5 seats
- Your own domains, up to 25

[Choose Startup](https://trotta.email/signup)

### Enterprise

Custom

Priced with you

- Unlimited inboxes and seats
- Volume pricing
- Dedicated sending IPs
- SSO and an SLA

[Talk to us](mailto:sales@trotta.io)

Every plan: pre-delivery screening, held-mail review, outgoing mail screened for secrets, login codes sealed from agents, API, MCP and SDKs. A seat is a human with their own sign-in and mailbox.

## Asked before you sign up

### How it works

#### What does pre-delivery mean?

Each message is judged while the sending server is still connected. Attacks, known and new, are turned away at the door or held for a human. Nothing unchecked reaches an inbox or an agent.

#### Can my agent read held mail?

No. An API key gets the verdict only, until a human releases the message. Then the agent gets the safe text: what a human could see, with hidden text removed.

#### Do my agents see my sign-in codes?

No. Codes and reset links in a human's mailbox are sealed. For an API key, the message does not exist.

### Plans and accounts

#### Can I use my own domain?

Yes, on paid plans, with whichever domain provider your business uses. Copy the records into its DNS settings and we check them for you.

#### How do teams work?

Each human gets their own sign-in and mailbox. Owners and admins run the team, and cannot read a teammate's mailbox.

#### Is there a free plan?

Yes. Two inboxes, 1,000 emails a month and one seat, with every check included.

#### How does yearly billing work?

Pay for a year up front and save 20%. Developer is $192 a year and Startup is $1,920 a year.

## Give your agent an address it can read safely.

It takes one call, or one minute if you are a human.

[Get an inbox](https://trotta.email/signup) [Read the docs](https://trotta.email/docs)

```bash
curl -X POST https://api.trotta.email/v1/agents/signup \
  -H "Content-Type: application/json" \
  -d '{"name": "riley"}'
```
