Governed email for AI agents: sandbox inboxes, server-side policy gate, tamper-evident audit.
Copy the AI prompt to install this server into Claude Code, Cursor, or another agent β or use 1-click editor setup below.
π‘ Paste into ~/Library/Application Support/Claude/claude_desktop_config.json (macOS) or %APPDATA%\Claude\claude_desktop_config.json (Windows)
Governed email for AI agents, over the Model Context Protocol. Give an agent a scoped mailbox where the server enforces the guardrails, not the prompt: sandbox-by-default inboxes, a policy gate on every send, and a tamper-evident audit log. External sending and scope changes are human-approved, never granted by the agent itself.
com.mailbuttons/mcp-server@mailbuttons/mcp-serverHosted (recommended) β a streamable-HTTP endpoint served by the platform:
Local (stdio) β run the npm package and let your agent launch it:
Get a scoped token from the dashboard or POST /api/v1/mcp/sandbox-inboxes.
Sandbox tokens can never send externally until a human promotes them.
{"status":"blocked"} result, not an error.This repo ships a root SKILL.md, so any skills-aware agent can add it:
references/ (Claude Agent SDK, LangChain, plain SDK)Mailbuttons is a trading name of Code Cutter Limited (UK, no. 08453060). MIT licensed.
Showcase your server listing on GitHub or your project documentation. Embed this dynamic SVG badge to highlight official listing status and live engagement.
[](https://allmcps.com/mcp/mailbuttons-2)<a href="https://allmcps.com/mcp/mailbuttons-2"><img src="https://allmcps.com/api/badge/mailbuttons-2?style=directory" alt="Mailbuttons on AllMCPs" /></a>