AI agents call debug_screenshot 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.
A screenshot operation reads and renders the current state of the canvas into an image file without modifying, deleting, or executing any logic that would alter the underlying document or system. This is fundamentally a Read operation with minimal security risk even if invoked repeatedly or by an untrusted agent.
From the tool's definition Tool name and description both indicate image capture: 'Capture a PNG screenshot of the live canvas via the renderer.' This is a non-destructive retrieval operation that produces no side effects to data or system state.
Attacks that exploit this kind of access
Capture a PNG screenshot of the live canvas via the renderer. 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 debug_screenshot: 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.
debug_screenshot 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 debug_screenshot 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 debug_screenshot. 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.
debug_screenshot 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 →