Delete a Drive file. Requires user to have used an explicit 'delete' verb.
AI agents call drive_delete to permanently remove resources in Hermes Google — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
This tool permanently removes data from Google Drive without possibility of recovery (unless relying on Google's trash/recovery features, which are temporary). File deletion is an irreversible destructive action. The requirement for explicit 'delete' verb does not reduce the severity—it is a safety guard, not a reduction in impact.
From the tool's definition Tool is explicitly named 'drive_delete' and description states 'Delete a Drive file.' Deletion of files is irreversible.
Attacks that exploit this kind of access
Delete a Drive file. Requires user to have used an explicit 'delete' verb. It is categorised as a Destructive tool in the Hermes Google MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Hermes Google MCP server in PolicyLayer and add a rule for drive_delete: 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 Hermes Google. Nothing to install.
drive_delete 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 drive_delete 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 drive_delete. 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.
drive_delete is provided by the Hermes Google MCP server (jimmy-larsson/hermes-google). 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 →