browser_trace · Wmux MCP: Risk & Policy

WHAT IT DOES

What browser_trace does on Wmux

AI agents invoke browser_trace to trigger actions in Wmux. 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_trace needs a policy

This tool executes browser automation instrumentation commands via Playwright. While tracing itself is non-destructive, it represents execution of an external system (Playwright browser automation) whose effects persist in recorded trace files and depend on agent-supplied parameters.

From the tool's definition Tool name 'browser_trace' and description 'Start or stop Playwright tracing' indicates it triggers Playwright automation library actions.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

browser_trace Rate-limited

browser_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.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "browser_trace": {
      "limits": [
        {
          "counter": "browser_trace_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 Wmux, so you can run agents against it safely.

FAQ

Questions about browser_trace

What does the browser_trace tool do? +

Start or stop Playwright tracing. Use. It is categorised as a Execute tool in the Wmux 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_trace? +

Register the Wmux MCP server in PolicyLayer and add a rule for browser_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 Wmux. Nothing to install.

What risk level is browser_trace? +

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

Can I rate-limit browser_trace? +

Yes. Add a rate_limit block to the browser_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.

How do I block browser_trace completely? +

Set action: deny in the PolicyLayer policy for browser_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.

What MCP server provides browser_trace? +

browser_trace is provided by the Wmux MCP server (openwong2kim/wmux). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

// THE FULL RECORD

browser_trace is one line of Wmux's registry record.

The record carries the whole server: verified identity, auth posture, risk grade, every tool classified, recommended policy — re-checked continuously.

Teams ship this data inside their own products. See what a licence covers →