Delete a reply from a comment.
AI agents call delete_reply 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.
The tool permanently removes a reply, which cannot be undone without external backup or version history. This is a destructive operation on user-generated content. Severity is high because while the scope is narrowly scoped (a single reply rather than entire documents), deletion of collaborative content can disrupt workflows and is irreversible at the API level.
From the tool's definition Tool name includes 'delete' and description states 'Delete a reply from a comment' — this irreversibly removes data.
Attacks that exploit this kind of access
Delete a reply from a comment. 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_reply: 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_reply 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_reply 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_reply. 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_reply 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 →