Delete an email by message ID
AI agents call delete_email to permanently remove resources in Email MCP Server — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
Email deletion is irreversible—once an email is deleted by message ID, it cannot be undone (barring manual recovery from backups outside the tool's control). This matches the Destructive category definition: 'irreversibly deletes or overwrites data, or actions that cannot be undone.' The severity is high because an AI agent misusing this tool could delete sensitive business communications, legal records, or personal…
From the tool's definition delete_email: Delete an email by message ID. The tool name and description explicitly indicate permanent removal of email messages, which are data that cannot be recovered once deleted.
Attacks that exploit this kind of access
Delete an email by message ID. It is categorised as a Destructive tool in the Email MCP Server MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Email MCP Server MCP server in PolicyLayer and add a rule for delete_email: 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 Email MCP Server. Nothing to install.
delete_email 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_email 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_email. 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_email is provided by the Email MCP Server MCP server (tianpeijun/email-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 →