AI agents invoke browser_start_tracing to trigger actions in Playwright. 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.
Tracing captures browser activity, network traffic, and performance data—an active operation that executes an external process (browser instrumentation) whose behavior depends on runtime state. This is Execute rather than Read because it modifies browser state (activates tracing mode). It is not Destructive (reversible via stop_tracing), not Write (doesn't persist user data), and not Financial.
From the tool's definition Tool name 'browser_start_tracing' combined with context that this is Playwright (a browser automation framework). Sibling tools like 'browser_click', 'browser_console_messages', 'browser_drag' confirm this server controls active browser operations.
Documented attack patterns abuse exactly the kind of access browser_start_tracing gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Playwright, and nothing reaches the server without passing your rules. This is the rule we recommend for browser_start_tracing:
{
"version": "1",
"default": "deny",
"tools": {
"browser_start_tracing": {
"limits": [
{
"counter": "browser_start_tracing_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}browser_start_tracing 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.
Free to start. No card required.
browser_start_tracing. It is categorised as a Execute tool in the Playwright MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Playwright MCP server in PolicyLayer and add a rule for browser_start_tracing: 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 Playwright. Nothing to install.
browser_start_tracing 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 browser_start_tracing 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_start_tracing. 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_start_tracing is provided by the Playwright MCP server (@playwright/mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Playwright, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
68 Playwright tools catalogued and risk-classified — across an index of 43,000+ MCP servers.