browser_start_tracing · Playwright MCP: Risk & Policy

WHAT IT DOES

What browser_start_tracing does on Playwright MCP

AI agents invoke browser_start_tracing to trigger actions in Playwright 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 IT NEEDS A POLICY

Why browser_start_tracing needs a policy

This tool triggers browser tracing, which is a browser operation whose effects depend on what occurs during the traced session. While tracing itself is non-destructive, it executes external browser operations and can capture sensitive session data. It falls under Execute (triggers external operations) rather than Read (passive data retrieval) because it initiates active browser instrumentation.

From the tool's definition Tool name 'browser_start_tracing' combined with server description indicating 'browser automation and web page interaction using Playwright'. Tracing in Playwright captures network, DOM mutations, and console logs during browser sessions.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

browser_start_tracing Rate-limited

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.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "browser_start_tracing": {
      "limits": [
        {
          "counter": "browser_start_tracing_rate",
          "window": "minute",
          "max": 10,
          "scope": "grant"
        }
      ]
    }
  }
}

RATE-LIMIT THIS TOOL →

Instant setup, no code required.

PolicyLayer is an MCP gateway: every tool call is checked against your rule before it reaches Playwright MCP, so you can run agents against it safely.

FAQ

Questions about browser_start_tracing

What does the browser_start_tracing tool do? +

browser_start_tracing. It is categorised as a Execute tool in the Playwright MCP MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on browser_start_tracing? +

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 MCP. Nothing to install.

What risk level is browser_start_tracing? +

browser_start_tracing is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.

Can I rate-limit browser_start_tracing? +

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.

How do I block browser_start_tracing completely? +

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.

What MCP server provides browser_start_tracing? +

browser_start_tracing is provided by the Playwright MCP server (lysander72/playwright-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.