Remove a permission from a Google Drive file.
AI agents call delete_permission to permanently remove resources in Google — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
This tool permanently removes access controls. While the file itself is not deleted, the permission structure is irreversibly modified in a way that eliminates previously-granted access rights. This qualifies as destructive because it overwrites/removes authorization state that cannot be automatically recovered.
From the tool's definition delete_permission removes a permission from a Google Drive file, which irreversibly revokes access rights. The action cannot be undone without re-sharing the resource.
Attacks that exploit this kind of access
Remove a permission from a Google Drive file. It is categorised as a Destructive tool in the Google MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Google MCP server in PolicyLayer and add a rule for delete_permission: 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 Google. Nothing to install.
delete_permission 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_permission 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_permission. 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_permission is provided by the Google MCP server (ztgluis/google-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 →