Mailbuttons MCP server

MCP serverCommunication

Your AI can send and receive email under your rules. It works from its own sandbox inbox, every message passes a policy check before it goes out, and all email activity is recorded in an audit log. The email tools come from Mailbuttons (mbag.ai).

Available today. Use it from your connected AI after setup.

After adding it, set up a sandbox inbox and decide which email rules your AI must follow. Use the audit log to review its email activity.

Then ask your AI: use Mailbuttons MCP server

What your AI can do with it

  • Send and receive email from a dedicated sandbox inbox
  • Keep AI email separate from your own accounts
  • Check outgoing messages against your policies before they are sent
  • Review a full audit log of every email your AI sends or receives

From the project's README

As published by mailbuttons/mcp-server in README.md.

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.

Use it

Hosted (recommended) — a streamable-HTTP endpoint served by the platform:

https://mailbuttons.com/api/v1/mcp/rpc
Authorization: Bearer <your Mailbuttons MCP token>   # mb_sandbox_... (or mb_prod_...)

Local (stdio) — run the npm package and let your agent launch it:

{
  "mcpServers": {
    "mailbuttons": {
      "command": "npx",
      "args": ["-y", "@mailbuttons/mcp-server"],
      "env": { "MAILBUTTONS_API_KEY": "mb_sandbox_..." }
    }
  }
}

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.

What the server enforces

  • Inbound — a per-mailbox sender policy, fail-closed: mail from strangers bounces by default, so nobody can prompt-inject your agent just by emailing it.
  • Outbound — a recipient blocklist the agent can read but not change; a blocked send returns a normal {"status":"blocked"} result, not an error.
  • Caps + audit — per-account send caps and a hash-chained audit log that records refusals too.
  • Escalation — sending externally or widening scope is propose-only; a named human approves. The agent cannot approve its own request.

Install as an agent skill

This repo ships a root SKILL.md, so any skills-aware agent can add it:

npx skills add mailbuttons/mcp-server

Docs

Mailbuttons is a trading name of Code Cutter Limited (UK, no. 08453060). MIT licensed.

Signals

GitHub stars
1
Last commit
Jul 2026
Advanced
Delivery
mcp-server MCP server → your ahel gateway (mcp.ahel.ai) → every connected AI client.
Catalog kind
mcp-server
Gateway key
com-mailbuttons-mcp-server
Source
github.com/mailbuttons/mcp-server
Hosted endpoint
https://mailbuttons.com/api/v1/mcp/rpc