Run a performance audit on the current page
AI agents call runPerformanceAudit to retrieve information from BrowserTools MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
A performance audit passively measures and reports on page performance characteristics (load times, resource usage, rendering metrics, etc.). It is a read/analysis operation with no side effects on data or system state. The worst case misuse is consuming browser resources during the audit, which is negligible.
From the tool's definition "Run a performance audit on the current page" - this reads and analyzes the current page's performance metrics without modifying any data
Attacks that exploit this kind of access
Run a performance audit on the current page. It is categorised as a Read tool in the BrowserTools MCP MCP Server, which means it retrieves data without modifying state.
Register the BrowserTools MCP server in PolicyLayer and add a rule for runPerformanceAudit: 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 BrowserTools MCP. Nothing to install.
runPerformanceAudit 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 runPerformanceAudit 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 runPerformanceAudit. 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.
runPerformanceAudit is provided by the BrowserTools MCP server (oenius/browser-tools-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 →