Delete emails permanently
AI agents call delete_emails to permanently remove resources in MCP Mail Organizer — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
This tool permanently removes email data, which cannot be undone. While email is typically recoverable from backups in production systems, the tool itself provides no undo mechanism or reversibility. The blast radius is high: an agent misconfiguration could delete large volumes of user emails, causing data loss.
From the tool's definition The tool is named 'delete_emails' with description 'Delete emails permanently'. The word 'Delete' and 'permanently' explicitly indicate irreversible removal of data.
Attacks that exploit this kind of access
Delete emails permanently. It is categorised as a Destructive tool in the MCP Mail Organizer MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the MCP Mail Organizer MCP server in PolicyLayer and add a rule for delete_emails: 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 Mail Organizer. Nothing to install.
delete_emails 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_emails 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_emails. 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_emails is provided by the MCP Mail Organizer MCP server (neomody77/mcp-mail-organizer). 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 →