AI agents use reorder_page to create or update resources in Pen — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Pen environment.
Reordering pages modifies document structure persistently but is a non-destructive write operation. It does not execute code, move money, or irreversibly delete data. The severity is medium because misuse could reorganize critical document sections in confusing ways, but the effect is fully reversible and does not cause permanent data loss. Confidence is high given the clear, specific description of the operation.
From the tool's definition Tool description states "Move a page to a new position (index) in an .op file" — this modifies the structure/order of document content without deleting data. The operation is reversible (can be moved again to restore original order).
Attacks that exploit this kind of access
Move a page to a new position (index) in an .op file. It is categorised as a Write tool in the Pen MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Pen MCP server in PolicyLayer and add a rule for reorder_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.
reorder_page is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the reorder_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 reorder_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.
reorder_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 →