l1_collect · Lighthouse MCP: Risk & Policy

WHAT IT DOES

What l1_collect does on Lighthouse MCP

AI agents invoke l1_collect to trigger actions in Lighthouse 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 l1_collect needs a policy

This tool executes an external Lighthouse performance audit against a given URL, which involves running a headless browser, making network requests to the target site, and collecting telemetry data. It is not a simple read of stored data but an active execution of an analysis pipeline against an external resource. No data is modified or deleted, so Execute is the appropriate category.

From the tool's definition "Collect raw Lighthouse data for a URL" — this triggers an external Lighthouse audit process that actively fetches and analyzes a remote URL

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

l1_collect Rate-limited

l1_collect 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": {
    "l1_collect": {
      "limits": [
        {
          "counter": "l1_collect_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 Lighthouse MCP, so you can run agents against it safely.

FAQ

Questions about l1_collect

What does the l1_collect tool do? +

Collect raw Lighthouse data for a URL (Layer 1). It is categorised as a Execute tool in the Lighthouse 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 l1_collect? +

Register the Lighthouse MCP server in PolicyLayer and add a rule for l1_collect: 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 Lighthouse MCP. Nothing to install.

What risk level is l1_collect? +

l1_collect is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.

Can I rate-limit l1_collect? +

Yes. Add a rate_limit block to the l1_collect 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 l1_collect completely? +

Set action: deny in the PolicyLayer policy for l1_collect. 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 l1_collect? +

l1_collect is provided by the Lighthouse MCP server (mizchi/lighthouse-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.