Move an email to trash by ID (requires OAuth2 config)
AI agents call delete_email to permanently remove resources in Gmail MCP Server — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
Although technically moved to trash rather than permanently purged, trashing an email removes it from normal access and represents an irreversible action that cannot be undone by the tool itself. The user would need to manually recover from trash if desired.
From the tool's definition Tool description explicitly states it 'Move[s] an email to trash by ID' — this moves emails to trash, which is irreversible deletion from the user's inbox and effectively removes access to email content.
Attacks that exploit this kind of access
Move an email to trash by ID (requires OAuth2 config). It is categorised as a Destructive tool in the Gmail MCP Server MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Gmail 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 Gmail 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 Gmail MCP Server MCP server (nasirhuss86/gmail-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 →