Delete a positioned object (e.g. floating image) from a Google Doc.
AI agents call delete_positioned_object 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 floating image or positioned object from a Google Doc without possibility of automated recovery by the user. While the blast radius is limited to a single object rather than entire documents, deletion is irreversible and meets the Destructive category definition.
From the tool's definition Tool name explicitly contains 'delete'; description states 'Delete a positioned object' from a Google Doc. This operation removes content irreversibly.
Attacks that exploit this kind of access
Delete a positioned object (e.g. floating image) 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_positioned_object: 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_positioned_object 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_positioned_object 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_positioned_object. 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_positioned_object 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 →