AI agents call browser_get_performance to retrieve information from Byob without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool only queries and returns performance data about a webpage. It does not modify, delete, execute code, or trigger external operations. It is a pure read operation that observes browser state without altering it. The low severity reflects that performance metrics are non-sensitive data and misuse poses minimal risk.
From the tool's definition Tool retrieves performance metrics (Core Web Vitals: LCP/CLS/INP/FCP/TTFB) from a page. The verb 'Get' and the nature of metrics collection indicates data retrieval with no side effects.
Attacks that exploit this kind of access
Get page performance metrics — Core Web Vitals (LCP/CLS/INP/FCP/TTFB) and. It is categorised as a Read tool in the Byob MCP Server, which means it retrieves data without modifying state.
Register the Byob MCP server in PolicyLayer and add a rule for browser_get_performance: 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 Byob. Nothing to install.
browser_get_performance 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 browser_get_performance 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 browser_get_performance. 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.
browser_get_performance is provided by the Byob MCP server (wxtsky/byob). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.