Delete an IMAP folder.
AI agents call delete_folder to permanently remove resources in Mail — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
Deleting a folder is a destructive action that cannot be undone—it removes data permanently. While it doesn't directly involve financial transactions or code execution, the permanent loss of email data (which may contain important business communications, legal records, or personal information) represents a high-severity risk.
From the tool's definition The tool name is 'delete_folder' and the description states it will 'Delete an IMAP folder.' This is an irreversible operation that permanently removes a folder and its contents from an email account.
Attacks that exploit this kind of access
Delete an IMAP folder. It is categorised as a Destructive tool in the Mail MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Mail MCP server in PolicyLayer and add a rule for delete_folder: 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 Mail. Nothing to install.
delete_folder 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 delete_folder 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 delete_folder. 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.
delete_folder is provided by the Mail MCP server (kpihx/mail-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 →