Stars
Forks
Watchers
Developer links
E2A
E2A is an open-source email API that lets any application send transactional email and gives AI agents real two-way inboxes of their own, so an assistant can hold a conversation over email without borrowing a person's mailbox. Register an agent and it gets a working address on a shared domain in seconds, or verify your own domain for branded addresses, then connect through the hosted MCP server, a coding-agent plugin with browser OAuth, signed webhooks, a WebSocket stream, REST polling, or the TypeScript and Python SDKs. A local agent behind a firewall needs no public URL at all: it listens over WebSocket and replies in-thread with conversation identifiers keeping multi-turn exchanges coherent across humans and other agents. Every inbound message arrives with structured SPF, DKIM, and DMARC evidence, with the DMARC alignment verdict included, so your agent can judge how far to trust a sender instead of trusting the From header. Flip on the human-in-the-loop gate per agent and outbound messages pause for a person to approve, edit, or reject from the dashboard, the SDK, MCP tools, or magic links in their own inbox, with expiry rules and recipient allowlists narrowing which sends get held. Inbound content screening flags prompt-injection payloads before the agent ever sees them. Support bots triage intake, scheduling agents coordinate meetings, and commerce agents answer order questions from one persistent address. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. Apache-2.0 licensed.
Benefits
- Real Two-Way Agent Inboxes
- Each agent owns a dedicated email address for sending, receiving, and replying in-thread with stable conversation identifiers, reachable through MCP tools, signed webhooks, WebSocket streams, REST polling, or TypeScript and Python SDKs.
- Human Approval Before Sending
- An opt-in per-agent gate holds outbound messages until a reviewer approves, edits, or rejects them from the dashboard, SDK, MCP tools, or magic links, with configurable expiry and allowlists for routine recipients.
- Authentication Evidence Built In
- Every inbound message carries normalized SPF verdicts, each DKIM signature result, and a DMARC alignment verdict as structured evidence, so agents can weigh sender trust programmatically, no raw header parsing required.
- Works Where Agents Run
- Local agents need no public HTTPS endpoint: mail arrives over an at-least-once WebSocket stream; cloud agents use webhooks, and a CLI streams or forwards events to local handlers for notebooks and laptops.
Features
- Transactional Sending API
- Send receipts, verification messages, alerts, and notifications over plain HTTP or the TypeScript and Python SDKs, and convert the same sender into a two-way inbox when replies matter.
- MCP Server and Plugins
- The hosted MCP server and coding-agent plugins register send, receive, reply, and hold-for-review tools directly inside Claude Code, Codex, Cursor, Zed, Goose, and other MCP clients with browser OAuth.
- Agent Management Dashboard
- Manage registered agents with domain choices between shared and branded addresses, pending review queues, domains, API keys, settings, and per-agent human-in-the-loop controls from one web console.
- Inbound Injection Screening
- Opt-in content screening inspects mail before the agent acts, flagging hidden HTML, Unicode-tag smuggling, and encoded instruction payloads into the same review queue people already check.