lighthouse_analyze · MCP Frontend Analyzer MCP

WHAT IT DOES

What lighthouse_analyze does on MCP Frontend Analyzer

AI agents invoke lighthouse_analyze to trigger actions in MCP Frontend Analyzer. 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 lighthouse_analyze needs a policy

This tool executes a Google Lighthouse audit against a given URL, which involves launching a browser instance and running an active scan. It is not a simple read/query of existing data — it triggers an external operation whose behavior depends on the URL argument. No data is written or deleted, but it actively executes an analysis process, placing it in the Execute category.

From the tool's definition 'Google Lighthouse analizi çalıştırır' (runs Google Lighthouse analysis) — triggers an external audit process against a specified URL

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

lighthouse_analyze Rate-limited

lighthouse_analyze 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": {
    "lighthouse_analyze": {
      "limits": [
        {
          "counter": "lighthouse_analyze_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 Frontend Analyzer, so you can run agents against it safely.

FAQ

Questions about lighthouse_analyze

What does the lighthouse_analyze tool do? +

Belirtilen URL üzerinde Google Lighthouse analizi çalıştırır. Performans, SEO, erişilebilirlik ve best-practices puanlarını döner. Analiz birkaç saniye sürebilir. It is categorised as a Execute tool in the MCP Frontend Analyzer MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on lighthouse_analyze? +

Register the MCP Frontend Analyzer MCP server in PolicyLayer and add a rule for lighthouse_analyze: 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 Frontend Analyzer. Nothing to install.

What risk level is lighthouse_analyze? +

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

Can I rate-limit lighthouse_analyze? +

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

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

lighthouse_analyze is provided by the MCP Frontend Analyzer MCP server (samet-berkay-taskin/mcp-frontend-analyzer). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.