Delete text from a specific range in the document
AI agents call delete_text to permanently remove resources in LLM2Docs (Unofficial) — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
This tool permanently removes data from a Google Docs document. Deletion is irreversible and cannot be undone by the tool itself (though Google Docs maintains undo history, the tool's action is destructive in nature). An AI agent misusing this could maliciously or accidentally wipe significant portions of user documents.
From the tool's definition Tool name 'delete_text' with description 'Delete text from a specific range in the document' explicitly performs irreversible deletion of document content.
Attacks that exploit this kind of access
Delete text from a specific range in the document. It is categorised as a Destructive tool in the LLM2Docs (Unofficial) MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the LLM2Docs (Unofficial) MCP server in PolicyLayer and add a rule for delete_text: 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 LLM2Docs (Unofficial). Nothing to install.
delete_text 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_text 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_text. 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_text is provided by the LLM2Docs (Unofficial) MCP server (nomannayeem/google-docs-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 →