Analyze issues prioritized by Lighthouse audit weights (Layer 2)
AI agents call l2_weighted_issues to retrieve information from Lighthouse MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This is a read-only analytical tool that retrieves and prioritizes existing Lighthouse audit findings. It queries and presents performance metrics and issues without making any changes to systems, executing arbitrary code, or causing side effects. The 'analyze' and 'prioritize' operations are purely informational transformations of audit data, consistent with Read category tools like 'get' or 'fetch'.
From the tool's definition Tool name 'l2_weighted_issues' with description 'Analyze issues prioritized by Lighthouse audit weights' indicates data retrieval and analysis of existing audit results.
Attacks that exploit this kind of access
Analyze issues prioritized by Lighthouse audit weights (Layer 2). It is categorised as a Read tool in the Lighthouse MCP MCP Server, which means it retrieves data without modifying state.
Register the Lighthouse MCP server in PolicyLayer and add a rule for l2_weighted_issues: 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.
l2_weighted_issues is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the l2_weighted_issues 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.
Set action: deny in the PolicyLayer policy for l2_weighted_issues. 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.
l2_weighted_issues 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.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →