tracing_start · MCP Playwright Server MCP: Risk & Policy

WHAT IT DOES

What tracing_start does on MCP Playwright Server

AI agents invoke tracing_start to trigger actions in MCP Playwright Server. 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 tracing_start needs a policy

While tracing_start does not directly execute code or shell commands, it initiates an external operation (trace recording) whose side effects depend on subsequent browser interactions captured within that trace session. This falls under Execute rather than Read, as it modifies the browser's runtime behavior and state recording.

From the tool's definition Tool 'tracing_start' initiates recording of browser state including screenshots, DOM snapshots, and action logs. This is an operational control that triggers recording state in the browser runtime, similar to starting a debugger or profiler.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

tracing_start Rate-limited

tracing_start 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": {
    "tracing_start": {
      "limits": [
        {
          "counter": "tracing_start_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 MCP Playwright Server, so you can run agents against it safely.

FAQ

Questions about tracing_start

What does the tracing_start tool do? +

Start recording a trace for debugging. Captures screenshots, DOM snapshots, and action logs. View traces at trace.playwright.dev. It is categorised as a Execute tool in the MCP Playwright Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on tracing_start? +

Register the MCP Playwright Server MCP server in PolicyLayer and add a rule for tracing_start: 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 MCP Playwright Server. Nothing to install.

What risk level is tracing_start? +

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

Can I rate-limit tracing_start? +

Yes. Add a rate_limit block to the tracing_start 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 tracing_start completely? +

Set action: deny in the PolicyLayer policy for tracing_start. 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 tracing_start? +

tracing_start is provided by the MCP Playwright Server MCP server (j0hanz/playwright-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.