mailbridge

An email client that lets AI agents work with mailboxes from services such as Gmail, iCloud, Outlook.com, Exchange, QQ, and other IMAP servers. IMAP is a standard way for email software to access messages stored on a mail server.

In plain words
What is it for?
Use it to find messages, prepare or send email, organise mail, and export mailbox data from personal, work, or school accounts.
Why use it?
It gives an agent one way to search, read, draft, send, organise, and export email across different providers. Login details remain on the agent’s own computer.

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.

Claude Code
/plugin marketplace add henry200803/mailbridge
agentmods
npx agentmods add plugins/henry200803/mailbridge/mailbridge
Clone the repo
git clone --depth 1 https://github.com/henry200803/mailbridge

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

mailbridge 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/plugin.json · 12 lines

What it actually says

{
  "name": "mailbridge",
  "version": "1.2.0",
  "description": "A full email client for AI agents — Claude, Codex, Cursor or any MCP client: search, read, draft, send, organise and export mail across iCloud, Outlook.com, work/school Exchange, Gmail, QQ and any IMAP mailbox. Credentials stay on your own machine.",
  "author": {
    "name": "Sibo Huang"
  },
  "keywords": ["email", "imap", "outlook", "icloud", "gmail", "mail", "smtp", "graph", "mcp"],
  "license": "MIT",
  "homepage": "https://github.com/henry200803/mailbridge"
}
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 · 12 lines scan A 5cd7a06a08f1

Subscribe to this mod's changes

mailbridge is a plugin published in the GitHub repository henry200803/mailbridge (7 stars, last pushed 21d ago), licensed MIT. 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 2026-08-31.