e2a

An email connection for applications and AI agents. It supports sending product emails, giving agents two-way inboxes, requesting human approval, recording email-authentication evidence, and checking an event log.

In plain words
What is it for?
It helps applications send transactional email, lets agents receive and answer messages, routes sensitive actions for human approval, and records email activity. SPF, DKIM, and DMARC are standards used to verify that email is allowed to come from a domain.
Why use it?
It removes the need to build and maintain separate email-sending, inbox, approval, and delivery-tracking systems.

Plugin for Claude Code

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add plugins/tokencanopy/e2a/marketplace
Claude Code
/plugin marketplace add tokencanopy/e2a
Clone the repo
git clone --depth 1 https://github.com/tokencanopy/e2a

Made for: Claude Code.

Per session not measured What this adds to a session before it is invoked.
When invoked not measured Not applicable: nothing here is loaded into a session.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Security

Grade A, and why

e2a scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

.claude-plugin/marketplace.json · 29 lines

What it actually says

{
  "name": "e2a",
  "owner": {
    "name": "TokenCanopy",
    "email": "[email protected]",
    "url": "https://e2a.dev"
  },
  "metadata": {
    "description": "e2a plugins for Claude Code — open-source email API for applications and AI agents",
    "version": "0.9.5"
  },
  "plugins": [
    {
      "name": "e2a",
      "description": "Open-source email API for applications and AI agents — transactional sending from any product, per-agent two-way inboxes, HITL approval, structured SPF/DKIM/DMARC evidence, and a queryable event log. 78 MCP tools over hosted streamable HTTP with OAuth.",
      "category": "productivity",
      "source": "./plugins/e2a",
      "homepage": "https://e2a.dev"
    },
    {
      "name": "e2a-labs",
      "description": "Experimental Agentify, Autopilot, and Tether workflows for e2a. Requires the core e2a plugin for MCP tools and authentication.",
      "category": "productivity",
      "source": "./plugins/e2a-labs",
      "homepage": "https://e2a.dev"
    }
  ]
}
Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. yesterday First seen · 29 lines scan A c3c06db2142a

Subscribe to this mod's changes

e2a is a plugin published in the GitHub repository tokencanopy/e2a (184 stars, last pushed yesterday), licensed Apache-2.0. Its token cost is not measured: this kind of file is read by the harness, not the model. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.