
Security News
Deno Goes the Way of the Dinosaur
Cloudflare is acquiring Deno’s team, which will provide another year of bug fixes and security updates before ending support for the runtime.
mailcycle-mcp
Advanced tools
An email address for your AI agent. MCP server for Mailcycle: read, wait for and reply to mail, open attachments and send files, decrypted on your machine.
An email address for your AI agent. This MCP server lets an agent read, wait for and reply to mail at its own Mailcycle addresses. Mail is decrypted on the machine running the agent. Mailcycle stores it sealed and can't read it.
Needs a Mailcycle account on Scale or above, and Node 20 or later.
On the machine the agent runs on:
npx -y mailcycle-mcp pair --name "Support agent"
It prints a line starting with MC1:. In the Mailcycle app, open AI agents, paste the line, and give the agent an email address. The line carries the key that the agent's address keys are sealed with, so keep it private. It goes from your terminal to the app and never through Mailcycle.
Then add the server to your MCP client:
claude mcp add mailcycle -- npx -y mailcycle-mcp
Or in a client's JSON config:
{ "mcpServers": { "mailcycle": { "command": "npx", "args": ["-y", "mailcycle-mcp"] } } }
Added the server before pairing? It still starts, and every tool answers with how to pair. Pair while it runs and the next tool call picks it up, with no restart.
| Tool | What it does |
|---|---|
list_addresses | The agent's addresses, and what it may send. |
list_messages | The newest messages, with a preview of each. |
read_message | One message in full, with its attachments numbered. |
read_attachment | Opens an attachment: text as text, images as images, anything else written to a save_to folder. |
wait_for_message | Waits for new mail, optionally from a sender or with a subject. Good for sign-up codes and verification links. |
reply | Replies to the sender of a message, threaded. Works in reply-only mode. Can attach files by path. |
send_message | Sends a new message. Needs the agent set to send to anyone. Can attach files by path. |
Each agent has a send mode, set in the app:
Mail an agent reads can contain instructions written by whoever sent it. Reply only limits what those can make it do. Message bodies are passed to the model marked as the sender's words.
Agents send only from the addresses you assign them, within your plan's daily sending limit.
To send with a name, like "Support at Acme", set Sender name on the address in the app, or on the agent's page for every address it holds. An address's own name wins. The agent picks it up on its next send.
~/.config/mailcycle/agent.json, readable only by your user. Anyone with that file can read the agent's mail. Remove the agent in the app to cut it off; the next time it runs, it deletes that file itself.mailcycle-mcp status shows the agent's addresses and send mode.MAILCYCLE_AGENT_FILE sets where the key is kept, for running more than one agent on a machine.Proprietary. Copyright (c) 2026 Northlab Studios Ltd. All rights reserved. You may run this package, unmodified, to connect AI agents to a Mailcycle account you're authorised to use. You may not copy, modify, redistribute or reverse engineer it. See the LICENSE file included with it and the Terms of Service.
FAQs
An email address for your AI agent. MCP server for Mailcycle: read, wait for and reply to mail, open attachments and send files, decrypted on your machine.
We found that mailcycle-mcp demonstrated a healthy version release cadence and project activity because the last version was released less than a year ago. It has 1 open source maintainer collaborating on the project.

Security News
Cloudflare is acquiring Deno’s team, which will provide another year of bug fixes and security updates before ending support for the runtime.

Security News
Anthropic’s free OSS Scanner uses Mythos and other Claude models to find open source vulnerabilities and send maintainers reports with proposed fixes.

Security News
On Front Lines’ Early Adopters: CISO podcast, Andrew Becherer shares lessons from Datadog, weighs the long-term costs of AI-built tools, and explains how founders can actually gain a CISO’s trust.