AgentMailr – Real email addresses for AI agents (OTP/2FA handling)
Long-polling OTP extraction solves real 2FA bottleneck for agentic workflows elegantly.

One POST gets agents a real email address when SendGrid requires manual domain verification.
AI agent developers, automation engineers
Postmark · SendGrid · Resend
I built MailboxKit because I kept running into the same problem: AI agents need email but existing APIs aren't designed for them.
The typical flow for an agent is: get an email address, send messages, receive replies, and handle threading — all via API, without a human setting things up. Most email services require manual domain verification, complex OAuth, or aren't built for programmatic access from the start.
MailboxKit lets an agent self-register and start sending/receiving in a single API call:
``` POST /api/v1/register {"name": "My Agent", "owner_email": "[email protected]"}
→ {"api_key": "mbk_...", "email": "[email protected]", "inbox_id": '19999d'} ```
That's it. The agent now has a real email address, can send and receive, and gets inbound messages via webhooks. Threading, read/unread tracking, attachments, and custom domains all work out of the box.
The API docs double as an LLM-readable skill file (mailboxkit.com/skill.md) so agents using tool-use can discover and learn the API themselves.
Currently used by a handful of agents doing customer support, research, and outreach. Would love feedback from anyone building agent infrastructure.
Long-polling OTP extraction solves real 2FA bottleneck for agentic workflows elegantly.
Hands-off: each agent gets its own mailbox, phone number, inbox and API key, and the project bundles a local Stalwart mail server in Docker plus Gmail-relay or custom-domain outbound with DKIM/SPF/DMARC. Concrete safety features (outbound scanning to catch API keys/PII) and Google Voice SMS extraction for verification codes are genuinely useful and uncommon together. If you want to prototype agents that actually talk to people/services this is a focused, pragmatic stack — but expect telephony fiddliness and compliance trade-offs in real deployments.
Solves a real friction point for agentic email with elegant karma-based spam prevention.
Dedicated inboxes per agent beat shared Gmail accounts for attribution and deliverability.
Email as stateful context layer for agents—MCP servers make this first-class integration.
Email for AI agents: end-to-end encrypted messaging with pluggable relays.