Move a file to trash
AI agents call gdrive_file_delete to permanently remove resources in GDrive MCP Server — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
Although technically recoverable from trash for a limited period, this action irreversibly deletes files from the user's active workspace and cannot be undone immediately. Misuse by an AI agent could destroy important documents, spreadsheets, or folders. This is a destructive operation that warrants the highest severity category.
From the tool's definition Tool name is 'gdrive_file_delete' and description states 'Move a file to trash', which permanently removes user data from accessible storage.
Attacks that exploit this kind of access
Move a file to trash. It is categorised as a Destructive tool in the GDrive MCP Server MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the GDrive MCP Server MCP server in PolicyLayer and add a rule for gdrive_file_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 GDrive MCP Server. Nothing to install.
gdrive_file_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 gdrive_file_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 gdrive_file_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.
gdrive_file_delete is provided by the GDrive MCP Server MCP server (shaikh3/gdrive-mcp-server). 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 →