webtool_lighthouse · Webtools MCP Server MCP: Risk & Policy

WHAT IT DOES

What webtool_lighthouse does on Webtools MCP Server

AI agents invoke webtool_lighthouse to trigger actions in Webtools MCP Server. 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 webtool_lighthouse needs a policy

This tool triggers external code execution (Lighthouse audit engine) that inspects and analyzes a web resource. While it produces only informational output (no data modification), the execution itself depends entirely on the URL argument provided, making it an Execute tool. An AI agent could misuse this to enumerate internal infrastructure details, discover resource paths, or perform reconnaissance on systems.

From the tool's definition "Run a Lighthouse audit on a webpage" - executes an external tool (Lighthouse/Chrome DevTools) against a specified target.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

webtool_lighthouse Rate-limited

webtool_lighthouse 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": {
    "webtool_lighthouse": {
      "limits": [
        {
          "counter": "webtool_lighthouse_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 Webtools MCP Server, so you can run agents against it safely.

FAQ

Questions about webtool_lighthouse

What does the webtool_lighthouse tool do? +

Run a Lighthouse audit on a webpage to generate a comprehensive performance report with detailed resource analysis. The report includes specific file paths, resource sizes, and performance metrics similar to Chrome DevTools. Identifies exact files causing performance issues without offering improvement suggestions. It is categorised as a Execute tool in the Webtools MCP Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on webtool_lighthouse? +

Register the Webtools MCP Server MCP server in PolicyLayer and add a rule for webtool_lighthouse: 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 Webtools MCP Server. Nothing to install.

What risk level is webtool_lighthouse? +

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

Can I rate-limit webtool_lighthouse? +

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

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

webtool_lighthouse is provided by the Webtools MCP Server MCP server (misterboe/webtools-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.