83trust / 100

Machine Inbox

by machineinbox.com in Email & messaging

MCP serverPassing, checked 6 h ago

Task-scoped email inboxes for AI agents: read mail, extract verification codes, and reply.

https://machineinbox.com/mcp

Last 30 days

All checks passedSome failedAll failedNot checked
Uptime
100%
Response time
285 ms typical, 285 ms slowest 5%
Last check
6 h ago
Next check
any minute now

How to call it

Add it to any MCP client that supports remote servers.

{
  "mcpServers": {
    "machine-inbox": {
      "type": "http",
      "url": "https://machineinbox.com/mcp"
    }
  }
}

11 tools

  • get_service_info

    Read the Machine Inbox service instructions: pricing, payment rails, endpoints, and limits.

  • create_inbox

    Request a new paid inbox. Buying requires an out-of-band payment (Stripe MPP or x402 USDC on Base); this tool returns the live HTTP 402 payment challenge plus exact instructions to complete the purchase. Standard inbox: $2.00.

  • get_inbox

    Read an inbox: address, status, expiry, limits, and usage.

  • list_messages

    List messages in an inbox, newest first. Pass after=<newest createdAt seen> to poll for only new mail.

  • get_message

    Fetch one message with parsed text, HTML, and attachment download URLs.

  • get_verification_code

    Extract the newest one-time verification code or confirmation link from inbound mail. Ideal for signup and login flows.

  • reply_to_message

    Send an included plain-text reply to the authenticated sender of an inbound message.

  • set_webhook

    Register or replace the inbox webhook: an HMAC-signed POST fires on every inbound message with metadata, extracted verification codes, and injection risk (never the body). Returns the signing secret.

  • get_webhook

    Read the inbox webhook state: URL, delivery counters, and whether it is disabled. The secret is only returned by set_webhook.

  • delete_webhook

    Remove the inbox webhook.

  • delete_inbox

    Delete an inbox: revokes the token and erases stored mail.

Security scan

  • No findings. We scan names, descriptions and tool definitions for hidden instructions and other prompt-injection patterns.

Recent checks

WhenResultHTTPTime
6 h agoPassed200285 ms
15 h agoPassed200471 ms