AI agents call delete_label 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.
Deleting a label removes a user's organizational structure and any email categorization associated with it. This is an irreversible destructive action that affects email organization and cannot be reversed. Severity is high because it could disrupt a user's email management system, though it does not directly impact email content or financial/operational systems as severely as mass email deletion would.
From the tool's definition Tool name 'delete_label' and description 'Delete a single label from gmail' indicate irreversible deletion of a Gmail label, which cannot be undone.
Documented attack patterns abuse exactly the kind of access delete_label 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 delete_label:
{
"version": "1",
"default": "deny",
"hide": [
"delete_label"
]
}delete_label 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.
Delete a single label from gmail. 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 delete_label: 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.
delete_label 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_label 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_label. 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_label 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.