AI agents use add_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.
This tool creates and modifies document structure within an OpenPencil file by adding pages and potentially reorganizing existing content. It is reversible (pages can be deleted), so it falls under Write rather than Destructive. The severity is medium because misuse could corrupt document organization, but the effect is not irreversible and not as critical as code execution or data deletion.
From the tool's definition Tool description states 'Add a new page to an .op file' and mentions automatic migration of children, indicating creation of new document structure and modification of existing document state.
Attacks that exploit this kind of access
Add a new page to an .op file. If the document has no pages yet, the existing children are migrated to the first page automatically. 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 add_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.
add_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 add_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 add_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.
add_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 →