Delete a tab from a Google Doc.
AI agents call delete_doc_tab 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 a tab (and its contents) from a Google Doc, which cannot be undone by the tool itself. Deletion of document structure/content is irreversible and falls squarely into the Destructive category. The severity is high because an AI agent could easily delete critical tabs from shared documents, affecting multiple users and causing data loss.
From the tool's definition Tool name is 'delete_doc_tab' and description states 'Delete a tab from a Google Doc.' The word 'delete' indicates irreversible removal of data.
Attacks that exploit this kind of access
Delete a tab from a Google Doc. 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_doc_tab: 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_doc_tab 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_doc_tab 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_doc_tab. 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_doc_tab 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 →