Enables email agents to send emails with granular trust levels per contact, ensuring human approval for high-risk or unknown recipients while allowing automatic sending for trusted ones.
An email operating system for AI agents that provides safe triage, drafting, and searching of emails with unbypassable hard-stops on money, banking changes, first-contact senders, and prompt injection.
Enables AI agents to run real email operations across multiple IMAP/SMTP and provider OAuth accounts — syncing, searching, reading, drafting, attaching, and sending mail — while requiring explicit human approval for sending, deleting, or forwarding and recording an inspectable audit trail.
Mailforce is an MCP server that provides a policy layer for AI agents to safely interact with email, controlling which accounts, recipients, and actions are allowed, with optional human approval for sends.