performance_start_trace · Opera DevTools MCP: Risk & Policy

WHAT IT DOES

What performance_start_trace does on Opera DevTools MCP

AI agents invoke performance_start_trace to trigger actions in Opera DevTools 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 performance_start_trace needs a policy

This is an Execute tool because it runs a profiling operation on a live webpage that modifies instrumentation state and collects runtime data. While non-destructive and non-financial, it actively triggers browser-level operations whose side effects (performance overhead, data collection) depend on the target page.

From the tool's definition The tool "Start a performance trace on the selected webpage" triggers an external operation (performance profiling) whose effects depend on which page is selected and how the trace data is used.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

performance_start_trace Rate-limited

performance_start_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": {
    "performance_start_trace": {
      "limits": [
        {
          "counter": "performance_start_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 Opera DevTools MCP, so you can run agents against it safely.

FAQ

Questions about performance_start_trace

What does the performance_start_trace tool do? +

Start a performance trace on the selected webpage. Use to find frontend performance issues, Core Web Vitals (LCP, INP, CLS), and improve page load speed. It is categorised as a Execute tool in the Opera DevTools 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 performance_start_trace? +

Register the Opera DevTools MCP server in PolicyLayer and add a rule for performance_start_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 Opera DevTools MCP. Nothing to install.

What risk level is performance_start_trace? +

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

Can I rate-limit performance_start_trace? +

Yes. Add a rate_limit block to the performance_start_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 performance_start_trace completely? +

Set action: deny in the PolicyLayer policy for performance_start_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 performance_start_trace? +

performance_start_trace is provided by the Opera DevTools MCP server (operasoftware/opera-devtools-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.