compare_lighthouse · MCP Frontend Analyzer MCP

WHAT IT DOES

What compare_lighthouse does on MCP Frontend Analyzer

AI agents call compare_lighthouse to retrieve information from MCP Frontend Analyzer without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.

WHY IT NEEDS A POLICY

Why compare_lighthouse needs a policy

The tool compares Lighthouse audit results between two URLs. Lighthouse is a read-only auditing tool that analyzes web pages and returns metrics without modifying any data, code, or systems. The 'compare' operation is a data retrieval and analysis function. The incomplete description ('İki URL') does not suggest any write, execute, destructive, or financial capabilities.

From the tool's definition Tool name 'compare_lighthouse' and server description indicating it performs 'Google Lighthouse audits' and 'code quality checks' - these are analysis and querying operations with no side effects.

Attacks that exploit this kind of access

Questions about compare_lighthouse

What does the compare_lighthouse tool do? +

İki URL. It is categorised as a Read tool in the MCP Frontend Analyzer MCP Server, which means it retrieves data without modifying state.

How do I enforce a policy on compare_lighthouse? +

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

What risk level is compare_lighthouse? +

compare_lighthouse is a Read tool with low risk. Read-only tools are generally safe to allow by default.

Can I rate-limit compare_lighthouse? +

Yes. Add a rate_limit block to the compare_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 compare_lighthouse completely? +

Set action: deny in the PolicyLayer policy for compare_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 compare_lighthouse? +

compare_lighthouse 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.