AI agents call get_style_guide 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 is a read-only operation that fetches or retrieves a style guide resource. It performs a query based on input parameters (tags or name) and returns information without modifying any state or triggering external operations. The passive verb 'Returns' and absence of any action verbs suggest no side effects. Low severity because compromised access merely exposes design information, with minimal blast radius.
From the tool's definition Tool description states 'Returns a style guide' — purely retrieves/queries data with no side effects. No modification, deletion, execution, or financial operation indicated.
Attacks that exploit this kind of access
Returns a style guide for design inspiration based on tags or name. 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_style_guide: 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_style_guide 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_style_guide 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_style_guide. 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_style_guide 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 →