Starts a performance trace recording on the selected page. This can be used to look for performance problems and insights to improve the performance of the page. It will also report Core Web Vital (CWV) scores for the page.
AI agents invoke performance_start_trace to trigger actions in Chrome DevTools MCP. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.
This tool triggers an active measurement operation on a live browser—it executes a performance profiling command on the target page, analogous to launching a debugger or profiler. While it is non-destructive and read-only in intent (it observes behavior rather than modifying page state), it actively executes an external operation whose scope and timing are argument-dependent. This makes it Execute rather than Read.
From the tool's definition Tool 'performance_start_trace' initiates a performance trace recording on a live Chrome browser page, which triggers external measurement and profiling operations whose effects depend on which page is selected and when tracing occurs.
Attacks that exploit this kind of access
Starts a performance trace recording on the selected page. This can be used to look for performance problems and insights to improve the performance of the page. It will also report Core Web Vital (CWV) scores for the page. It is categorised as a Execute tool in the Chrome DevTools MCP MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Chrome DevTools MCP server in PolicyLayer and add a rule for performance_start_trace: 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 Chrome DevTools MCP. Nothing to install.
performance_start_trace is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the performance_start_trace 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 performance_start_trace. 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.
performance_start_trace is provided by the Chrome DevTools MCP server (shay5555-gif/chrome-devtools-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 →