AI agents use design_skeleton 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 new design elements (frames and sections) in a document, which constitutes data modification. It is reversible (frames can be deleted), so it does not qualify as Destructive. The blast radius is medium—an agent could create unwanted layout structures, but the damage is correctable and scoped to design layout only, not system-wide or critical operations.
From the tool's definition Tool performs 'Create a layout skeleton with root frame + section frames', which explicitly creates new design structures. While reversible, this modifies the document state by adding new frames/sections.
Risk signalsAdmin/system-level operation
Attacks that exploit this kind of access
Create a layout skeleton with root frame + section frames. Part of the layered design workflow. 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 design_skeleton: 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.
design_skeleton 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 design_skeleton 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 design_skeleton. 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.
design_skeleton 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 →