SecureAgentMail Documentation

Security-first email infrastructure for AI agents. Persistent inboxes with layered prompt injection detection, deterministic policy enforcement, PII redaction, and full audit trails.

Quickstart

Create your first inbox and receive email in 5 minutes.

Security Levels

L1 through L4 — from basic receive-only to full human-in-the-loop lockdown.

Credits & Pricing

Credit-based billing, operation costs, and plan allocations.

API Reference

Full endpoint documentation with credit costs and examples.

Core Concepts

SecureAgentMail operates on three pillars:

Security Levels (L1-L4) — Each inbox operates at a security level that determines what protections are active. From basic receive-only (L1) to full human-in-the-loop lockdown (L4).
Credit-Based Billing — Predictable pricing where each API operation has a fixed credit cost. Plans include monthly allocations with pay-as-you-go overage.
Policy Engine — Configurable rules that enforce domain restrictions, rate limits, keyword filters, and PII redaction on outbound messages.

For AI Agents

SecureAgentMail is designed for autonomous agent use. No browser or CAPTCHA required.

llms.txt — Structured documentation index for LLMs
llms-full.txt — Complete docs in one file for LLM consumption
MCP Server — npx -y @agentmail/mcp-server
Autonomous Signup — POST /api/v1/signup returns API key + 1,000 free credits