Permanently delete messages from a folder.
AI agents call delete_messages 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.
This tool irreversibly removes data (email messages) and cannot be undone. Although email deletion may sometimes allow recovery from trash/recycle bins depending on the provider, the description explicitly claims permanence. This is a destructive operation with significant blast radius if misused by an AI agent, as it could result in loss of important communications, records, or evidence.
From the tool's definition Tool name is 'delete_messages' and description states 'Permanently delete messages from a folder.' The word 'Permanently' indicates irreversible deletion.
Attacks that exploit this kind of access
Permanently delete messages from a 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_messages: 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_messages 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_messages 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_messages. 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_messages 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 →