mail_delete_mailbox
AI agents call mail_delete_mailbox to permanently remove resources in Pyfastmail — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
Deleting a mailbox is irreversible and cannot be undone — it destroys all email data within that mailbox. This is the most severe category (Destructive > Execute > Write > Read) because the action cannot be reversed and has maximum blast radius if invoked by an AI agent with incorrect arguments or malicious intent. Critical severity is warranted given the total data loss risk.
From the tool's definition Tool name is 'mail_delete_mailbox' — the verb 'delete' combined with 'mailbox' indicates irreversible deletion of an entire mailbox and its contents. Description is empty but the name alone provides clear signal.
Attacks that exploit this kind of access
mail_delete_mailbox. It is categorised as a Destructive tool in the Pyfastmail MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Pyfastmail MCP server in PolicyLayer and add a rule for mail_delete_mailbox: 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 Pyfastmail. Nothing to install.
mail_delete_mailbox 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_mailbox 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_mailbox. 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_mailbox is provided by the Pyfastmail MCP server (pjosols/pyfastmail-mcp). 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 →