performance_stop_trace
Stops the active performance trace recording on the selected page.
This record as markdown: /tools/anirbandz-chrome-mcp-devtool/performance-stop-trace.md
What performance_stop_trace does on Chrome DevTools MCP
AI agents invoke performance_stop_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.
Why performance_stop_trace is rated High
This tool executes a command that affects browser state and monitoring infrastructure. While not destructive (the trace data itself persists), it irreversibly changes the recording state and could interfere with performance diagnostics if misused by an AI agent. It fits Execute rather than Write because it triggers an external operation (trace termination) whose effects are system-level rather than data-creation.
From the tool's definition Stops an active performance trace recording; this is an operational action that modifies the state of the Chrome DevTools tracing system, triggering external effects (terminating an ongoing recording session).
Attacks that exploit this kind of access
The rule that runs performance_stop_trace safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Chrome DevTools MCP, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For performance_stop_trace, this is the rule to start with:
performance_stop_trace stays usable, but rate-capped: a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.
The button opens the PolicyLayer dashboard: create your workspace, connect Chrome DevTools MCP, apply this rule, and every performance_stop_trace call is checked against it from then on.
Questions about performance_stop_trace
Stops the active performance trace recording on the selected 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_stop_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_stop_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_stop_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_stop_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_stop_trace is provided by the Chrome DevTools MCP server (anirbandz/chrome_mcp_devtool). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Chrome DevTools, and thousands of servers like it.
Across the catalogue