Permanently delete emails by IDs. Irreversible. Call pollEmails first.
AI agents call deleteEmailsById to permanently remove resources in MCP Email Server — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
This tool irreversibly removes data (emails) and cannot be undone. Destructive is the appropriate category per the rules hierarchy. Severity is high because an AI agent misusing this could permanently erase a user's email archive, causing significant data loss. The confidence is very high given the explicit language in the description.
From the tool's definition Tool description explicitly states 'Permanently delete emails by IDs' and 'Irreversible.'
Attacks that exploit this kind of access
Permanently delete emails by IDs. Irreversible. Call pollEmails first. It is categorised as a Destructive tool in the MCP Email Server MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the MCP Email Server MCP server in PolicyLayer and add a rule for deleteEmailsById: 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 Email Server. Nothing to install.
deleteEmailsById 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 deleteEmailsById 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 deleteEmailsById. 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.
deleteEmailsById is provided by the MCP Email Server MCP server (ptbsare/email-mcp-server). 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 →