AI agents call get_design_prompt to retrieve information from Pen without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves or queries design prompt information from the Pen document manager. It has no destructive side effects, does not execute arbitrary code or commands, and does not modify data. It falls squarely into the Read category with low severity since it only accesses information without affecting system state or creating blast radius for misuse.
From the tool's definition Tool name 'get_design_prompt' and description 'Get design knowledge prompt' indicate retrieval of existing prompt data without modification, creation, deletion, or side effects. The verb 'Get' is characteristic of Read operations.
Attacks that exploit this kind of access
Get design knowledge prompt. Use. It is categorised as a Read tool in the Pen MCP Server, which means it retrieves data without modifying state.
Register the Pen MCP server in PolicyLayer and add a rule for get_design_prompt: 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.
get_design_prompt is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the get_design_prompt 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 get_design_prompt. 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.
get_design_prompt 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 →