AI agents call trash_email to permanently remove resources in Gmail — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
Trashing an email is a destructive operation. While technically recoverable within a window (Gmail trash is emptied after 30 days), the action is considered destructive in intent and effect. An AI agent misusing this tool could trash important emails at scale, causing significant data loss. Severity is high due to potential bulk misuse across a mailbox.
From the tool's definition 'Thrash an email' — moving email to trash is a destructive, potentially irreversible action that removes the email from the inbox and could result in permanent deletion after the trash retention period.
Documented attack patterns abuse exactly the kind of access trash_email gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Gmail, and nothing reaches the server without passing your rules. This is the rule we recommend for trash_email:
{
"version": "1",
"default": "deny",
"hide": [
"trash_email"
]
}trash_email disappears from the agent's tool list entirely, and any attempt to call it is denied. The rest of the server keeps working.
Free to start. No card required.
Thrash an email. It is categorised as a Destructive tool in the Gmail MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Gmail MCP server in PolicyLayer and add a rule for trash_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. Nothing to install.
trash_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 trash_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 trash_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.
trash_email is provided by the Gmail MCP server (ivanlhz/gmail-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Gmail, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
12 Gmail tools catalogued and risk-classified — across an index of 43,000+ MCP servers.