Jev in production › Moderation and content filtering

Agents Mail

Optional Jev labels inbound email as spam, phishing or marketing and flags likely prompt injection in this self-hosted agent mailbox.

Open on GitHub ↗

The source publishes no measured number.
Use
Moderation and content filtering
Industry
Security
Form
Open-source tool
Stage
In production
Listed
2026-10-01
Found via
github
Repository
nikuscs/agents-mail
Stars
5
Forks
0
Last push
2026-09-30
Language
TypeScript
License
MIT
Agents Mail screenshot
assets/agents-mail.jpg in the nikuscs/agents-mail README, MIT; shown from GitHub.

The README opens with

A mailbox for AI agents on Cloudflare. Receive, search, read and send email over MCP or REST, behind one token.

- 📥 Catch-all inbox: every address on your domain lands here, with attachments. Optionally accept only the addresses you list, and cap mail per day. - 📤 Send, reply and forward from your domain, with names, cc, bcc, reply-to, attachments and threads. - ⏳ Wait for mail: blocks until a matching email or a reply in a thread arrives, and pulls out its verification code and link. - 🔎 Search by sender, recipient, thread, date, unread, category or text, HTML-only mail included. - 🤖 MCP server at /mcp: eight tools, stateless, works with Claude Code and any MCP client. - 🛡️ Optional JEV: labels each email (spam, phishing, marketing…) and...

Badge

For the project's own README, linking back here:

Listed in Jev in production

Also used for moderation and content filtering