browser_perf_start_coverage · Browser MCP: Risk & Policy

WHAT IT DOES

What browser_perf_start_coverage does on Browser

AI agents invoke browser_perf_start_coverage 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_coverage needs a policy

This tool falls into Execute rather than Read because it doesn't merely query existing data—it actively starts a tracking/instrumentation operation that alters browser diagnostic state. While it doesn't write data to disk or delete anything, it initiates active monitoring that depends on subsequent browser operations.

From the tool's definition The tool description states it 'Start[s] tracking CSS and JavaScript code coverage' - this initiates an active monitoring/tracing operation on the browser's execution environment.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

browser_perf_start_coverage Rate-limited

browser_perf_start_coverage 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_coverage": {
      "limits": [
        {
          "counter": "browser_perf_start_coverage_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_coverage

What does the browser_perf_start_coverage tool do? +

Start tracking CSS and JavaScript code coverage (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_coverage? +

Register the Browser MCP server in PolicyLayer and add a rule for browser_perf_start_coverage: 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_coverage? +

browser_perf_start_coverage 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_coverage? +

Yes. Add a rate_limit block to the browser_perf_start_coverage 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_coverage completely? +

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

browser_perf_start_coverage 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.