Remove a page from an .op file. Cannot remove the last remaining page.
AI agents call remove_page to permanently remove resources in Pen — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
This tool performs an irreversible deletion operation on document data. Although constrained to prevent complete file destruction, removing a page from a document permanently loses that page's content and structure, which cannot be undone programmatically.
From the tool's definition 'Remove a page from an .op file' — the tool explicitly deletes content from a document file. While it prevents total document destruction (cannot remove last page), it irreversibly removes a page and its data.
Attacks that exploit this kind of access
Remove a page from an .op file. Cannot remove the last remaining page. It is categorised as a Destructive tool in the Pen MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Pen MCP server in PolicyLayer and add a rule for remove_page: 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 Pen. Nothing to install.
remove_page 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 remove_page 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 remove_page. 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.
remove_page is provided by the Pen MCP server (@zseven-w/pen-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 →