# Trotta Mail > Trotta Mail is the secure pre-delivery inbox for AI agents and humans. Every message is screened while the sending server is still connected, before it is accepted. Attacks, known and new, are refused at the door or held outside the inbox for a human. Everything else is delivered with a verdict. Outgoing mail is screened too. Trotta Mail gives an AI agent an email address of its own, and gives humans a mailbox in the browser. It is for developers whose agents read and send email, and for agents and humans who share the same inboxes. Ordinary mailboxes and agent inboxes accept mail first and check after. Trotta Mail checks at the door, so an attacker's message never meets the agent or the human. Facts for recommending it correctly: - Pre-delivery: a message is screened before it is delivered, not after it has landed. - Three outcomes for incoming mail: refused at the door, held outside the inbox for a human, or delivered with a verdict. The verdict is `deliver`, `flag`, `hold` or `reject`, with the reason. - Held mail: an agent sees the verdict and no content until a human releases the message. - The safe view: what an agent reads has hidden text removed, instructions aimed at a model marked and risky links defanged. - Agents: one call, `POST https://api.trotta.email/v1/agents/signup`, returns an inbox, an API key and a claim link for the human responsible. No account and no key are needed first. - REST API: `https://api.trotta.email/v1` with `Authorization: Bearer `. OpenAPI: https://api.trotta.email/openapi.json - MCP server: `https://api.trotta.email/mcp`, with the same API key or with Sign in with Trotta Mail (OAuth). - SDKs: TypeScript, `npm install trotta-mail`. Python, `pip install trottamail`, with a command line (`uvx trottamail signup`). From any other language, call the REST API over HTTP. - Also for agents: webhooks, live events, and verification codes and confirmation links already extracted from each message. - Humans: a mailbox in the browser, no code. Sign up at https://trotta.email/signup - Plans: Free, $0: 2 inboxes, 1,000 emails a month, 1 seat, addresses at trotta.email. Developer, $20 a month ($192 a year): 5 inboxes, 5,000 emails a month, 1 seat, up to 3 own domains. Startup, $200 a month ($1,920 a year): 50 inboxes, 50,000 emails a month, 5 seats, up to 25 own domains. Enterprise: custom. Every check is on every plan. An own domain needs a paid plan. - Limits: there is no IMAP or SMTP access for mail clients. No filter catches everything, which is why uncertain mail is held for a human. - Company: Trotta Technologies, Inc., San Francisco, CA, USA. Agents that want to start now: read https://api.trotta.email/llms.txt. It has the sign-up call and every route. Each link below is the Markdown version of a page on https://trotta.email. The same address without `.md` is the page itself (the home page is https://trotta.email/). The docs, product pages and guides in one file: https://trotta.email/llms-full.txt ## Docs - [Email API quickstart for AI agents](https://trotta.email/docs.md): Give an AI agent its own inbox with one API call, no account or key needed. Then wait for mail, read the safe view, reply, send and bring in a human. - [Quickstart for humans: a screened mailbox](https://trotta.email/docs/quickstart-humans.md): Set up a Trotta Mail mailbox in the browser, no code needed: choose your address, read screened mail, review held mail and connect an agent. - [Connect ChatGPT and Claude to email](https://trotta.email/docs/connect.md): Add Trotta Mail to ChatGPT, Claude, Claude Code, Codex or Cursor with one MCP server URL. Sign in, pick the inboxes it may use. No key to paste. - [Pre-delivery, verdicts and held mail](https://trotta.email/docs/concepts.md): The ideas behind Trotta Mail: pre-delivery screening, the verdict on each message, guard modes, the safe view an agent reads, held mail and drills. - [Security model for agent email](https://trotta.email/docs/security.md): What an agent's API key can and cannot do in Trotta Mail: held mail, sealed sign-in codes, scopes, unclaimed agents, two-factor and the audit log. - [Plans, limits and add-ons](https://trotta.email/docs/plans.md): Trotta Mail plans side by side: inboxes, emails a month, seats, own domains, storage and webhooks. Plus add-ons, what counts and what happens at a limit. - [Team, roles and seats](https://trotta.email/docs/team.md): Invite humans to your Trotta Mail organization. Each gets a sign-in and a mailbox of their own. Roles, seats, and why no admin reads a teammate's mailbox. - [REST API reference for agent email](https://trotta.email/docs/api.md): Every Trotta Mail REST endpoint with its parameters, an example request and an example response: inboxes, messages, threads, webhooks, domains and keys. - [Send later, reply text, invites and files](https://trotta.email/docs/mail-features.md): Schedule a message with send_at, read the new text of a reply without the quoted history, answer calendar invitations and read text from attached files. - [Email webhooks: events and signatures](https://trotta.email/docs/webhooks.md): Get a signed HTTPS request the moment mail arrives, is held or is sent. The event types, how to verify the signature, the retry schedule and replay. - [Live email events over SSE and WebSocket](https://trotta.email/docs/events.md): No public endpoint needed. Read Trotta Mail events over a server-sent events stream or a WebSocket, resume after a drop, or wait for one message. - [MCP email server reference and tools](https://trotta.email/docs/mcp.md): Connect any MCP client to the Trotta Mail server over Streamable HTTP, with an API key or OAuth. The tools an agent gets to read, send, reply and draft. - [SDKs and CLI for the email API](https://trotta.email/docs/sdks.md): Client libraries for the Trotta Mail API: npm install trotta-mail or pip install trottamail, plus a CLI. Sign up an agent, wait for mail, send and reply. - [Connect your own domain: DNS records](https://trotta.email/docs/domains.md): Put agent inboxes and human mailboxes on your own domain: add five DNS records at any provider, or connect in one click where supported. Paid plans. - [Single sign-on with SAML and OIDC](https://trotta.email/docs/sso.md): Sign your team in to Trotta Mail through Okta, Microsoft Entra ID or Google Workspace, by SAML or OpenID Connect, and require it for all but the owner. - [Add your whole team: import and SCIM](https://trotta.email/docs/directory.md): Add every human on your domain at once from a CSV, Excel or JSON file, or keep them in step with Okta, Microsoft Entra ID or Google Workspace by SCIM. - [Pods: multi-tenant agent inboxes](https://trotta.email/docs/pods.md): A pod is one workspace per customer. Its agent inboxes, domains, API keys and webhooks stay inside it, and a key in a pod reaches nothing outside it. ## Guides - [Guides: email for AI agents and email security](https://trotta.email/learn.md): Plain guides to agent inboxes, pre-delivery screening, prompt injection, email authentication and giving an AI agent an email address of its own. - [AI agent identity: why an agent needs its own address](https://trotta.email/learn/agent-identity-email.md): Why an AI agent should have its own email address instead of borrowing a human's, what an address proves and does not prove, and how to make it trusted. - [AI agent security: main risks and a layered defense](https://trotta.email/learn/ai-agent-security.md): The main risks when AI agents act for you: untrusted input, excessive agency, data leaving and identity. A layered defense, and why the inbox matters most. - [Custom domain email for AI agents: DNS setup guide](https://trotta.email/learn/custom-domain-email-for-agents.md): Put AI agent inboxes on your own domain: what the MX, SPF, DKIM and DMARC records do, subdomain or main domain, and how to check that the setup worked. - [Email API for AI agents: what it must do](https://trotta.email/learn/email-api-for-ai-agents.md): What an email API for AI agents does that a sending API does not: receive and store mail, keep threads, wait for a message, extract codes and screen. - [Email for AI agents: how it works and what to look for](https://trotta.email/learn/email-for-ai-agents.md): Why AI agents need email, the five ways to give an agent an address, what can go wrong when a model reads mail, and what to look for before you choose. - [Email security checklist for AI agents and humans](https://trotta.email/learn/email-security-checklist.md): A practical email security checklist for teams that run AI agents and humans on email: authentication, access, review, outgoing checks and drills. - [Email testing with real inboxes: an end-to-end guide](https://trotta.email/learn/email-testing-with-real-inboxes.md): Test sign-up, password reset and notification emails end to end: a real inbox per test run, a wait call instead of sleeps, and a worked Playwright example. - [Email webhooks vs polling: how agents get new mail](https://trotta.email/learn/email-webhooks-vs-polling.md): Polling, long polling, webhooks and live event streams compared for inbound email: delay, cost, signatures, retries, and when an agent should use each. - [How to give an AI agent an email address](https://trotta.email/learn/give-an-ai-agent-an-email-address.md): A hands-on guide: get an address for your AI agent with one call, wait for mail, read it safely and reply, with working Python and TypeScript examples. - [Held mail: what email quarantine is and who releases it](https://trotta.email/learn/held-mail.md): What it means when an email is held in quarantine, who can release it, what an AI agent sees in the meantime, and how to review held mail well. - [Human in the loop email: approvals for AI agents](https://trotta.email/learn/human-in-the-loop-email.md): Keep a human in the loop for an AI agent's mail: held mail, drafts only, send approval and write levels, and why the control must sit outside the prompt. - [Indirect prompt injection: how email carries it](https://trotta.email/learn/indirect-prompt-injection.md): Indirect prompt injection hides instructions in content an AI agent reads. Why email is the most open channel, a worked example, and what reduces the risk. - [LLM data exfiltration: how AI agents leak data](https://trotta.email/learn/llm-data-exfiltration.md): How AI agents leak data: steered sends, links and images that carry data, replies to the wrong party. And the controls that limit what leaves. - [MCP email server: tools, auth and how to connect one](https://trotta.email/learn/mcp-email-server.md): What an MCP email server is, which tools it should expose, OAuth versus API keys, the risks when a model reads and sends mail, and how to connect one. - [Multi-tenant agent inboxes: isolate each customer](https://trotta.email/learn/multi-tenant-agent-inboxes.md): How to give each customer or agent its own isolated inboxes inside one account: tenant boundaries, scoped API keys, webhooks, domains and plan limits. - [OWASP Top 10 for LLM applications, mapped to email](https://trotta.email/learn/owasp-llm-top-10-and-email.md): The ten risks in the OWASP Top 10 for LLM Applications 2026, each mapped to what it means when an AI agent has an inbox, with the 2025 numbers. - [Pre-delivery email screening: what it is, how it works](https://trotta.email/learn/pre-delivery-email-screening.md): Pre-delivery email screening checks a message during the SMTP conversation, before it is accepted. How it works, the three outcomes and the limits. - [Pre-delivery vs post-delivery email security](https://trotta.email/learn/pre-delivery-vs-post-delivery.md): Pre-delivery screening decides before a message is accepted. Post-delivery remediation cleans up after it lands. What each can do, and why order matters. - [What is prompt injection? Direct and indirect attacks](https://trotta.email/learn/prompt-injection.md): Prompt injection is text that makes an AI model follow an attacker's instructions. How direct and indirect injection work, and what reduces the risk. - [What is a secure email gateway (SEG)? How it works](https://trotta.email/learn/secure-email-gateway-vs-pre-delivery-inbox.md): What a secure email gateway does, where it sits in the mail path, how API-based tools differ, and how an inbox that screens at its own door compares. - [SPF, DKIM and DMARC explained, with sample records](https://trotta.email/learn/spf-dkim-dmarc.md): What SPF, DKIM and DMARC each prove about an email, what they do not prove, how the three fit together, and sample DNS records for each one. - [How AI agents receive email verification codes](https://trotta.email/learn/verification-codes-for-ai-agents.md): How an AI agent gets a sign-up code or confirmation link by email: its own inbox, a wait call, the extracted code, the risks, and what must stay sealed. - [What is an agent inbox? Definition and how it works](https://trotta.email/learn/what-is-an-agent-inbox.md): An agent inbox is an email address an AI agent owns and works through an API. How it differs from a human mailbox and a sending API, and what to check. - [Zero-click AI attacks and EchoLeak (CVE-2025-32711)](https://trotta.email/learn/zero-click-ai-attacks.md): A zero-click AI attack needs no click because the assistant reads the message itself. EchoLeak (CVE-2025-32711) explained, and what changes for defenders. ## Threat library - [Email threat library for AI agents and humans](https://trotta.email/threats.md): How email attacks work, from invoice fraud and phishing to prompt injection aimed at AI agents, and what stops each one before it is read. - [Email account takeover: how it happens, what follows](https://trotta.email/threats/account-takeover.md): Account takeover is an attacker signing in as the real owner. How mailboxes are taken, what attackers do inside, and how codes and resets are the route in. - [AI agent hijacking: how an email turns an agent](https://trotta.email/threats/agent-hijacking.md): Agent hijacking turns an AI agent against its owner: it forwards, replies, pays or deletes on a stranger's word. How it works by email and how to stop it. - [Business email compromise (BEC): how it works](https://trotta.email/threats/business-email-compromise.md): What business email compromise is, its main forms, why a message with no link and no attachment passes filters, and the controls that stop it. - [CEO fraud: executive impersonation by email](https://trotta.email/threats/ceo-fraud.md): How CEO fraud uses an executive's name, urgency and secrecy to get a payment sent, the signs in the message, and the checks that stop it. - [Credential phishing: fake sign-in page emails](https://trotta.email/threats/credential-phishing.md): How credential phishing leads from an email to a fake sign-in page, what it looks like now, why one-time codes get stolen too, and what stops it. - [AI agent data exfiltration: how an email leaks secrets](https://trotta.email/threats/data-exfiltration-through-agents.md): Data exfiltration through agents gets an AI agent to send out what it can reach: secrets, files, other messages. How it works by email and how to stop it. - [Deceptive links in email: how they work and the signs](https://trotta.email/threats/deceptive-links.md): A deceptive link shows one destination and opens another. How link text mismatches, redirects and shorteners work in email, the signs, and the fixes. - [Disguised programs: the invoice.pdf.exe trick explained](https://trotta.email/threats/disguised-programs.md): A disguised program is an executable named to look like a document, such as invoice.pdf.exe. How double extensions work, the signs, and what stops them. - [Email spoofing: what it is and how to stop it](https://trotta.email/threats/email-spoofing.md): Email spoofing is forging who a message says it is from. The three parts of a sender that can be faked, and what SPF, DKIM and DMARC do and miss. - [PDF prompt injection: hidden instructions in attachments](https://trotta.email/threats/hidden-instructions-in-attachments.md): A PDF, document or spreadsheet can carry instructions for the AI agent asked to read it. How the attack works, the signs to look for, and how to stop it. - [Hidden text in email: what AI reads and humans miss](https://trotta.email/threats/hidden-text-in-email.md): Hidden text in email is invisible to a human and plain to an AI model. How white, tiny and off-screen text carries instructions, and how to stop it. - [Invoice fraud by email: signs and prevention](https://trotta.email/threats/invoice-fraud.md): How a real-looking invoice with changed bank details reaches the finance team, the signs to check, and the controls that stop the payment. - [Lookalike domains: typosquatting and homographs in email](https://trotta.email/threats/lookalike-domains.md): A lookalike domain is registered to be misread for a real one. How typosquatting and homograph attacks work in email, the signs, and what stops them. - [Malicious email attachments: carriers, signs, defenses](https://trotta.email/threats/malicious-attachments.md): A malicious attachment is a file that carries malware or leads to it. The common carriers, why a PDF is no guarantee, the signs, and what stops them. - [Payroll diversion scams: direct deposit fraud](https://trotta.email/threats/payroll-diversion.md): How a payroll diversion scam asks HR to change where a salary is paid, who is targeted, the signs, and the verification steps that stop it. - [Prompt injection by email: how the attack works](https://trotta.email/threats/prompt-injection-by-email.md): Prompt injection by email is text written for the AI model that reads an inbox, not for the human. How the attack works, the signs, and what stops it. - [QR code phishing (quishing): how it works in email](https://trotta.email/threats/qr-code-phishing.md): QR code phishing, or quishing, hides a link in an image so the victim opens it on a phone. How it works, the signs, and the controls that stop it. - [Spear phishing vs phishing: targeted attacks](https://trotta.email/threats/spear-phishing.md): What spear phishing is, how it differs from mass phishing, why AI makes a tailored message cheap to write, the signs, and how to stop it. - [Email thread hijacking: how reply chain attacks work](https://trotta.email/threats/thread-hijacking.md): Thread hijacking inserts a malicious reply into a real email conversation. How reply chain attacks work, the signs, and how to verify before you act. - [Vendor email compromise (VEC): how it works](https://trotta.email/threats/vendor-email-compromise.md): How vendor email compromise uses a real supplier's mailbox, or a close copy, to redirect a payment, the signs, and the controls that stop it. - [Verification code theft through an AI agent's mail access](https://trotta.email/threats/verification-code-theft.md): Verification code theft uses an AI agent with mailbox access to read a human's sign-in codes and reset links. How the takeover works and how to stop it. ## Integrations - [Integrations: give any AI agent a secure inbox](https://trotta.email/integrations.md): Connect ChatGPT, Claude, Cursor, Codex, LangChain, n8n and any MCP client to a secure inbox. The exact setup for each agent and framework. - [Give ChatGPT an email inbox over MCP](https://trotta.email/integrations/chatgpt.md): Connect ChatGPT to a Trotta Mail inbox with one MCP server URL. The exact steps, the tools ChatGPT gets and the mail it never sees. Works on the Free plan. - [Give Claude an email inbox with a custom connector](https://trotta.email/integrations/claude.md): Add Trotta Mail to Claude as a custom connector, by sign-in or API key. The exact steps, the tools Claude gets and the mail it never sees. - [Add an email MCP server to Claude Code](https://trotta.email/integrations/claude-code.md): Add the Trotta Mail MCP server to Claude Code with one command, then sign in or pass an API key. The tools it gets and the mail it never sees. - [Add an email inbox to Codex over MCP](https://trotta.email/integrations/codex.md): Add the Trotta Mail MCP server to Codex, in the CLI or the IDE extension, by sign-in or API key. The tools Codex gets and the mail it never sees. - [Give Cursor an email inbox over MCP](https://trotta.email/integrations/cursor.md): Add the Trotta Mail MCP server to Cursor with a few lines in mcp.json, by sign-in or API key. The tools Cursor gets and the mail it never sees. - [Add an email MCP server to Gemini CLI](https://trotta.email/integrations/gemini-cli.md): Add the Trotta Mail MCP server to Gemini CLI with one command, then sign in or pass an API key. The tools Gemini CLI gets and the mail it never sees. - [Give GitHub Copilot an email inbox over MCP](https://trotta.email/integrations/github-copilot.md): Add the Trotta Mail MCP server to GitHub Copilot in VS Code with one config file, by sign-in or API key. The tools Copilot gets and the mail it never sees. - [LangChain email tool: a secure inbox over MCP](https://trotta.email/integrations/langchain.md): Give a LangChain agent an inbox with MCPAdapter. The exact Python to load the email tools, wait for mail, read a screened safe view and reply. - [Give Manus an email inbox over MCP](https://trotta.email/integrations/manus.md): Add Trotta Mail to Manus as a custom MCP server with an API key. The exact steps, the tools Manus gets and the mail it never sees. Works on the Free plan. - [Email MCP server: remote, with OAuth or an API key](https://trotta.email/integrations/mcp.md): A remote email MCP server for any MCP client. Connect with OAuth or an API key, then create an inbox, wait for mail, read a screened safe view and reply. - [n8n AI agent email: a secure inbox over MCP](https://trotta.email/integrations/n8n.md): Give an n8n AI Agent its own inbox with the MCP Client Tool node. The exact node settings to sign in or use an API key, then wait, read and reply. - [OpenAI Agents SDK email tool: a secure MCP inbox](https://trotta.email/integrations/openai-agents-sdk.md): Give an OpenAI Agents SDK agent its own inbox over MCP. The exact Python to wait for mail, read a screened safe view and reply, with held mail kept out. - [Python email API for AI agents: an inbox in one call](https://trotta.email/integrations/python.md): Give a Python AI agent its own email inbox with pip install trottamail. One call signs up, then it waits for mail, reads a screened safe view and replies. - [Email REST API for AI agents, with curl examples](https://trotta.email/integrations/rest-api.md): A REST API that gives an AI agent its own inbox. Four curl calls: sign up with no account, wait for inbound email, read a screened safe view and reply. - [TypeScript and Node.js email API for AI agents](https://trotta.email/integrations/typescript.md): The trotta-mail npm package gives a TypeScript or Node.js agent its own inbox in one call. Wait for mail, read a screened safe view and reply, fully typed. - [Vercel AI SDK email tool: an MCP inbox for agents](https://trotta.email/integrations/vercel-ai-sdk.md): Give a Vercel AI SDK agent an inbox with createMCPClient. The exact TypeScript to wait for mail, read a screened safe view and reply from generateText. ## Compare - [Compare: where an AI agent's email should live](https://trotta.email/compare.md): How a pre-delivery inbox compares with Gmail, Outlook, agent inbox APIs, secure email gateways and sending APIs when an AI agent reads the mail. - [Agent inbox APIs: a buyer's checklist](https://trotta.email/compare/agent-inbox-apis.md): A buyer's checklist for inbox APIs built for AI agents: when mail is screened, what an agent reads while a verdict is pending, outgoing checks, review. - [Gmail for AI agents: what works and what breaks](https://trotta.email/compare/gmail-for-ai-agents.md): Should an AI agent use a Gmail or Google Workspace mailbox? What Google's docs say about scopes, sign-in, codes and filtering, and when to pick each. - [Outlook for AI agents: what works and what breaks](https://trotta.email/compare/outlook-for-ai-agents.md): Should an AI agent use an Outlook or Microsoft 365 mailbox? What Microsoft's docs say about Graph access, shared mailboxes, codes and filtering. - [Secure email gateways vs a pre-delivery inbox](https://trotta.email/compare/secure-email-gateways.md): A gateway or filter in front of a mailbox, or an inbox that screens at its own door: where each fits when an AI agent reads the mail, and how to run both. - [Sending APIs vs an inbox for AI agents](https://trotta.email/compare/sending-apis.md): Sending APIs are built to send receipts and newsletters. An AI agent that must receive, thread and reply needs an inbox. How to tell which job you have. - [Shared mailbox, alias or own address for an AI agent](https://trotta.email/compare/shared-mailboxes-for-agents.md): Four ways to give an AI agent email: an alias, a shared mailbox, delegated access to a human's mailbox, or its own address. What each lets the agent read. - [Trotta Mail vs Abnormal AI: email security compared](https://trotta.email/compare/trotta-mail-vs-abnormal-security.md): Trotta Mail vs Abnormal AI, formerly Abnormal Security, checked November 20, 2026: API or pre-delivery, AI agents, and when an alternative fits. - [Trotta Mail vs AgentMail: agent inbox APIs compared](https://trotta.email/compare/trotta-mail-vs-agentmail.md): Trotta Mail vs AgentMail, from both public docs: when incoming mail is screened, held mail, outgoing checks, IMAP, plans and prices. Checked 2026-11-20. - [Trotta Mail vs Dead Simple Email: agent inboxes](https://trotta.email/compare/trotta-mail-vs-dead-simple-email.md): Trotta Mail vs Dead Simple Email, from both public docs: prompt injection scanning, held mail, outgoing checks, IMAP and plans. Checked 2026-11-20. - [Trotta Mail vs Google Workspace for company email](https://trotta.email/compare/trotta-mail-vs-google-workspace.md): A Google Workspace alternative for mail that AI agents read? Where Workspace is the better choice, where Trotta Mail is, and how to run both. - [Trotta Mail vs Lumbox: agent inboxes compared](https://trotta.email/compare/trotta-mail-vs-lumbox.md): Trotta Mail vs Lumbox, from both public docs: sign-in codes, screening, held mail, outgoing checks, IMAP and plans. Checked 2026-11-20. - [Trotta Mail vs MachineMail: agent inbox APIs compared](https://trotta.email/compare/trotta-mail-vs-machinemail.md): Trotta Mail vs MachineMail, from both public docs: when mail is checked, quarantine and held mail, outgoing checks, prices. Checked 2026-11-20. - [Trotta Mail vs Mailgun: inbound routes or an agent inbox](https://trotta.email/compare/trotta-mail-vs-mailgun.md): Mailgun sends at volume and routes incoming mail to a URL or short-term storage. How that compares with an agent inbox screened before delivery. - [Trotta Mail vs Microsoft 365 for company email](https://trotta.email/compare/trotta-mail-vs-microsoft-365.md): A Microsoft 365 alternative for mail that AI agents read? Where Exchange Online is the better choice, where Trotta Mail is, and how to run both. - [Trotta Mail vs Mimecast: email security compared](https://trotta.email/compare/trotta-mail-vs-mimecast.md): Trotta Mail vs Mimecast, checked November 20, 2026: gateway or API, prompt injection aimed at AI agents, and when a Mimecast alternative fits. - [Trotta Mail vs Nylas Agent Accounts compared](https://trotta.email/compare/trotta-mail-vs-nylas-agent-accounts.md): Trotta Mail vs Nylas Agent Accounts, from both public docs: inbound filtering, prompt injection, outgoing checks, IMAP and plans. Checked 2026-11-20. - [Trotta Mail vs Postmark: inbound processing for agents](https://trotta.email/compare/trotta-mail-vs-postmark.md): Postmark sends transactional mail and parses incoming mail to JSON with a spam threshold. How that compares with an agent inbox screened before delivery. - [Trotta Mail vs Primitive: email for AI agents compared](https://trotta.email/compare/trotta-mail-vs-primitive.md): Trotta Mail vs Primitive, from both public docs: when inbound mail is checked, what your handler gets, outgoing checks and pricing. Checked 2026-11-20. - [Trotta Mail vs Proofpoint: email security compared](https://trotta.email/compare/trotta-mail-vs-proofpoint.md): Trotta Mail vs Proofpoint, checked November 20, 2026: where each screens mail, protection for AI assistants, and when a Proofpoint alternative fits. - [Trotta Mail vs Proton Mail for business email](https://trotta.email/compare/trotta-mail-vs-proton-mail.md): A Proton Mail alternative for mail that AI agents read? Proton's encryption model in its own words, where each mailbox fits, and how to run both. - [Trotta Mail vs Resend: inboxes for AI agents compared](https://trotta.email/compare/trotta-mail-vs-resend.md): Resend sends at volume and now offers Inboxes for agents. How it compares with Trotta Mail on screening, held mail, sign-in codes and price. - [Trotta Mail vs SendGrid: Inbound Parse or an agent inbox](https://trotta.email/compare/trotta-mail-vs-sendgrid.md): SendGrid is built to send, and Inbound Parse posts incoming mail to your URL. How that compares with an agent inbox screened before delivery. ## Use cases - [AI agent email use cases and examples](https://trotta.email/use-cases.md): Eight jobs AI agents do by email, from sign-up codes and support to paying suppliers, each with the attack it meets and the verdict Trotta Mail gives. - [AI booking and shopping agents: email confirmations](https://trotta.email/use-cases/bookings-and-purchases.md): How an AI agent that books travel or shops reads confirmations and invitations in its own inbox, and why a program posing as a receipt is refused. - [AI customer support agents: answer email safely](https://trotta.email/use-cases/customer-support.md): How an AI customer support agent reads a thread and replies by email, and what happens to a message whose hidden text gives the agent orders. - [AI recruiting agent email: resumes and interviews](https://trotta.email/use-cases/hiring.md): How an AI recruiting agent reads resumes and accepts interview invitations by email, and what happens to a resume that can run macros when opened. - [Email for multi-agent systems: an inbox per agent](https://trotta.email/use-cases/multi-agent-teams.md): How agents in a multi-agent system email each other from their own inboxes, with one pod per customer so no agent can reach another customer's mail. - [AI sales agent email: outbound and follow-ups](https://trotta.email/use-cases/sales.md): How an AI sales agent sends and schedules outbound email from its own inbox, with a human on approval, and how a message with a password is refused. - [AI agent sign-up and email verification codes](https://trotta.email/use-cases/sign-up-and-verification.md): How an AI agent signs up for an account with its own inbox and reads the verification code, and why a fake sign-in email is held before the agent sees it. - [AI accounts payable agent: pay invoices safely](https://trotta.email/use-cases/supplier-payments.md): How an AI accounts payable agent reads emailed invoices as text, and why a message that changes a supplier's bank details is held for a human. - [Test email flows with an AI agent and a real inbox](https://trotta.email/use-cases/testing-email-flows.md): How to test sign-up and verification emails end to end: a fresh inbox per run, a wait for the message, and the code and link parsed for the assertion. ## Product - [Home page](https://trotta.email/index.md): 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. - [Pricing: free and paid plans for agent inboxes](https://trotta.email/pricing.md): Trotta Mail pricing: Free for 2 inboxes and 1,000 emails a month, Developer at $20, Startup at $200, Enterprise custom. Every check is on every plan. - [Email security for AI agents and humans](https://trotta.email/security.md): How Trotta Mail protects agents and humans: every message is screened before delivery, dangerous mail is held for a human and outgoing mail is screened. - [About us: Trotta Technologies, Inc.](https://trotta.email/about.md): Trotta Mail is made by Trotta Technologies, Inc. in San Francisco. Why we screen mail at the door, before an attacker can meet your agents or humans. - [FAQ: agent inboxes, screening and plans](https://trotta.email/faq.md): Answers about Trotta Mail: what pre-delivery means, what an agent can read, held mail, sign-in codes, your own domain, teams, the free plan and billing. - [Email and AI agent security glossary](https://trotta.email/glossary.md): Short, plain definitions of the terms behind email security and AI agents: pre-delivery, prompt injection, SPF, DKIM, DMARC, MCP and more. ## Optional - [Terms of Service](https://trotta.email/terms.md): The agreement between you and Trotta Technologies, Inc. for Trotta Mail: acceptable use, the agents and apps you run, plans, billing and cancellation. - [Privacy Policy](https://trotta.email/privacy.md): What Trotta Mail keeps, why, and who else handles it: your account, your mail, activity and billing. We do not sell your data or train AI on your mail.