Envelope runs on your own machine — the client starts it, so there is no endpoint to ping. Last commit 15 Oct 2026.
Your own IMAP/SMTP mailboxes as agent tools, with per-agent policy and human-approved sends.
We read the source, 2 d ago · rules 995398eba69f
What this server is able to do. For an MCP server this is often the job itself — a terminal server runs commands because that is what it is for. Listed so you know what you are plugging in, not as an accusation.
<p class="block-note">In the Trash view, Delete becomes a permanent, count + account-scope confirmed hard-delete:</p>
<script defer src="https://umami.tmrtn.com/script.js" data-website-id="536e835e-4ffc-422e-82f3-6d80a3df44eb"></script>
Is this your server and something here is wrong? Tell us — corrections are free and do not require a plan.
We found places where it runs commands, builds paths or queries from values it is given. None of that is a flaw by itself — it becomes one when the code changes, and code changes quietly between releases. We re-read it on every one.
Your real mailbox and calendar for your agent (M365/IMAP); a human approves every send.
Gmail, Outlook, iCloud, Fastmail and any IMAP mailbox for your agent. Scoped OAuth, approved sends.
Your agent posts, schedules, queues and threads posts on X, with a human approval queue.
Your agent sends real postcards and letters. You approve; we print and mail.
namailu.cz gives your AI agent its own email inbox: read and send mail over MCP, with OAuth.
Set up human approval for your AI agents' tool calls.
Local MCP tools for server-readable agent inboxes and sending to owner-approved recipients.
One MCP endpoint for your company's tools, with per-person sign-in, policy and audit.
Answers built from our own checks of this server.