Delete emails by their IDs
AI agents call mail_delete to permanently remove resources in MCP Apple Mail — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
Deleting emails is an irreversible operation that cannot be undone. Once deleted, email messages are permanently removed from the mailbox. This meets the definition of Destructive category (irreversibly deletes data). While not as critical as financial or system-wide data loss, the deletion of user emails represents a significant loss of potentially important personal or business communications.
From the tool's definition Tool name 'mail_delete' combined with description 'Delete emails by their IDs' indicates irreversible deletion of email messages. The verb 'delete' is explicitly destructive.
Attacks that exploit this kind of access
Delete emails by their IDs. It is categorised as a Destructive tool in the MCP Apple Mail MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the MCP Apple Mail MCP server in PolicyLayer and add a rule for mail_delete: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches MCP Apple Mail. Nothing to install.
mail_delete is a Destructive tool with critical risk. Critical-risk tools should be blocked by default and only enabled with explicit human approval.
Yes. Add a rate_limit block to the mail_delete rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for mail_delete. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
mail_delete is provided by the MCP Apple Mail MCP server (lionsr/mcp-apple). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →