browser_perf_start_profile · Browser MCP: Risk & Policy

WHAT IT DOES

What browser_perf_start_profile does on Browser

AI agents invoke browser_perf_start_profile to trigger actions in Browser. 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_perf_start_profile needs a policy

CPU profiling is an execution action that triggers runtime instrumentation and data collection within a browser context. While it doesn't directly modify or delete data, it executes a diagnostic operation whose effects depend on the execution environment and how the profiling data is subsequently used.

From the tool's definition Tool name contains 'start_profile' and description states 'Start CPU profiling to track JavaScript execution' — this initiates a profiling operation that captures runtime behavior.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

browser_perf_start_profile Rate-limited

browser_perf_start_profile 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_perf_start_profile": {
      "limits": [
        {
          "counter": "browser_perf_start_profile_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 Browser, so you can run agents against it safely.

FAQ

Questions about browser_perf_start_profile

What does the browser_perf_start_profile tool do? +

Start CPU profiling to track JavaScript execution (see browser_docs). It is categorised as a Execute tool in the Browser 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_perf_start_profile? +

Register the Browser MCP server in PolicyLayer and add a rule for browser_perf_start_profile: 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 Browser. Nothing to install.

What risk level is browser_perf_start_profile? +

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

Can I rate-limit browser_perf_start_profile? +

Yes. Add a rate_limit block to the browser_perf_start_profile 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_perf_start_profile completely? +

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

browser_perf_start_profile is provided by the Browser MCP server (ricardodeazambuja/browser-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.