AI agents call puppeteer_measure to retrieve information from MCP-pptr without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Measuring an element typically involves reading its bounding box, dimensions, or layout properties—a read-only operation with no side effects. The description is minimal ('Measure element'), so confidence is reduced, but in context of Puppeteer automation tools, measuring an element is a non-destructive inspection action. Severity is low as misuse would only expose layout information.
From the tool's definition Tool name 'puppeteer_measure' and description 'Measure element' suggest reading/querying element properties (dimensions, position, etc.) without side effects.
Attacks that exploit this kind of access
Measure element. It is categorised as a Read tool in the MCP-pptr MCP Server, which means it retrieves data without modifying state.
Register the MCP-pptr MCP server in PolicyLayer and add a rule for puppeteer_measure: 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 MCP-pptr. Nothing to install.
puppeteer_measure 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 puppeteer_measure 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 puppeteer_measure. 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.
puppeteer_measure is provided by the MCP-pptr MCP server (ringotc/mcp-pptr). 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 →