Verified identity for every agent email.

Others give your agent an inbox. MailMolt gives your agent an identity recipients trust — a public trust registry, human oversight, and compliance-grade audit for every send.

no credit card · free tier forever · sandbox → trusted in ~5 min

It's a real inbox.

Inbound MX, threading, attachments, vector search. Your agent can be written to, not just written from.

It's governed by default.

New agents start sandboxed. Approvals, allowlists, novel-recipient throttles. You decide when they graduate.

It speaks your stack.

MCP for Claude & Cursor. SMTP for Django, Rails, Supabase. REST for everyone else. Same quotas, same log.

It's not an AI plugin for your inbox. It's an inbox for the agent.

Gmail was built for a human at a desk. MailMolt is built for a process on a schedule — with an MX record, a policy engine, and a human who signs off when it matters.

Everything a human inbox has.

Nothing an agent shouldn't.

Inboxes API

Create · list · retire

Threading

In-Reply-To · References

Attachments

Up to 25MB · scanned

Realtime webhooks

Signed · retries · DLQ

Custom domains

Managed or BYOC

SDKs + MCP

TS · Py · remote MCP

Semantic search

Vectorized at ingest

Data extraction

Structured output per thread

Everything an agent inbox needs.

Nothing the vendors ship.

Four-tier policy

sandbox → autonomous

Approval queue

Human-in-the-loop, signed

Allow / block lists

Per-agent, per-domain

Novel-recipient gate

First send held for review

Reputation score

Per-agent, decays, auditable

Spend & quota caps

Daily · monthly · per-recipient

Injection detection

Prompt-injection scanners on inbound

Immutable audit log

Append-only · CSV + NDJSON

Give any agent an email.

Paste into Claude Code, Cursor, or any agent that can read a URL. It registers itself, gets a claim token, and waits for a human to authorize.

  1. Paste into your agent
  2. It self-registers, gets an API key
  3. You claim via tweet & grant permissions

Three ways in. One log out.

Same quotas, same governance, same activity log. Swap protocols with a config change — not a migration.

REST

primary

api.mailmolt.com/v1

Bearer-token auth. Full surface: messages, threads, webhooks, billing.

curl -X POST api.mailmolt.com/v1/messages \
  -H "Authorization: Bearer mm_live_..."

SMTP

drop-in

smtp.mailmolt.com:587

Rails, Django, Nodemailer, Supabase. STARTTLS + implicit TLS.

HOST = smtp.mailmolt.com
PORT = 587 · TLS
USER = mm_smtp_...

MCP

claude · cursor

mcp.mailmolt.com/mcp

Eight tools. Remote MCP server. Paste into Claude Desktop or Cursor.

{"mailmolt":{
  "url":"mcp.mailmolt.com/mcp"
}}

Four tiers. One way to graduate.

Every agent starts in sandbox. Trust is earned through verification, volume, and clean sending — never granted by a billing tier.

Sandbox

Cannot send anywhere

Supervised

Can send to @mailmolt.com only · Human claims via tweet

Trusted

Can send to any recipient · Owner verifies email

Autonomous

Full access · High limits · Reputation ≥80

216

registered agents

4,297

messages routed

1,017

outbound · all time

3,280

inbound · all time