Run a Lighthouse performance audit on a URL. Returns: - Performance, Accessibility, Best Practices, and SEO scores - Core Web Vitals (LCP, CLS, TBT/INP proxy, FCP, TTFB) - Optimization opportunities with estimated savings - Diagnostics (long tasks, layout shifts, etc.) - SEO audit results (crawla...
AI agents invoke run_lighthouse to trigger actions in SEO Audit 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.
This tool executes an external command-line program (Lighthouse CLI) against a specified URL. It is not merely reading stored data; it actively launches a subprocess that performs browser-based auditing. The blast radius is medium: it could be misused to probe arbitrary URLs or consume significant resources, but it does not modify or delete data.
From the tool's definition 'Run a Lighthouse performance audit on a URL' and 'Requires Lighthouse CLI to be installed (npm install -g lighthouse)' — triggers an external CLI process (lighthouse) against a target URL
Attacks that exploit this kind of access
Run a Lighthouse performance audit on a URL. Returns: - Performance, Accessibility, Best Practices, and SEO scores - Core Web Vitals (LCP, CLS, TBT/INP proxy, FCP, TTFB) - Optimization opportunities with estimated savings - Diagnostics (long tasks, layout shifts, etc.) - SEO audit results (crawlability, meta tags, etc.) Use this for performance analysis. Run separately for mobile and desktop if both matter. Note: Requires Lighthouse CLI to be installed (npm install -g lighthouse). It is categorised as a Execute tool in the SEO Audit MCP Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the SEO Audit MCP Server MCP server in PolicyLayer and add a rule for run_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 SEO Audit MCP Server. Nothing to install.
run_lighthouse is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the run_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.
Set action: deny in the PolicyLayer policy for run_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.
run_lighthouse is provided by the SEO Audit MCP Server MCP server (richarddillman/seo-audit-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 →