AI agents use design_content 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.
The tool creates or modifies content nodes in a design section, which is a reversible data modification operation. There is no indication of deletion, execution of arbitrary code, or financial impact. The 'medium' severity reflects that incorrect use could alter document structure, but changes are reversible. Confidence is 0.8 rather than higher because the description lacks detail about scope and undo mechanisms.
From the tool's definition Populate a section with content nodes—description explicitly indicates creation/modification of design content within a section.
Attacks that exploit this kind of access
Populate a section with content nodes. 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_content: 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_content 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_content 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_content. 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_content 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 →