Delete a folder (move to trash or permanently delete).
AI agents call gdrive_delete_folder to permanently remove resources in Mcp Google Gdrive — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
This tool irreversibly removes data from Google Drive. Even when moving to trash (rather than permanent deletion), the action is destructive to the user's file organization and data accessibility. The capability for permanent deletion makes this critically destructive.
From the tool's definition 'Delete a folder (move to trash or permanently delete)' — the tool explicitly performs deletion operations, including permanent deletion which cannot be undone.
Attacks that exploit this kind of access
Delete a folder (move to trash or permanently delete). It is categorised as a Destructive tool in the Mcp Google Gdrive MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Mcp Google Gdrive MCP server in PolicyLayer and add a rule for gdrive_delete_folder: 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 Mcp Google Gdrive. Nothing to install.
gdrive_delete_folder 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_delete_folder 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_delete_folder. 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_delete_folder is provided by the Mcp Google Gdrive MCP server (sleepytimeshon/mcp-google-gdrive). 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 →