lighthouse_audit
Get Lighthouse score and reports for accessibility, SEO, best practices, and agentic browsing. This excludes performance. For performance audits, run ${startTrace.name}
This record as markdown: /tools/async23-chrome-devtools-mcp/lighthouse-audit.md
What lighthouse_audit does on Chrome Devtools
AI agents invoke lighthouse_audit to trigger actions in Chrome Devtools. 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 lighthouse_audit is rated High
Lighthouse audits execute code/tools within the browser context to measure accessibility, SEO, and best practices. While the audit itself is read-oriented (generates reports without modifying page state), the mechanism of 'running' an audit via DevTools constitutes triggering an external operation.
From the tool's definition Tool runs Lighthouse audit which executes external performance analysis operations on the browser; description explicitly references running performance traces via startTrace. Audits are operations that trigger external analysis tools.
Attacks that exploit this kind of access
The rule that runs lighthouse_audit safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Chrome Devtools, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For lighthouse_audit, this is the rule to start with:
lighthouse_audit 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.
The button opens the PolicyLayer dashboard: create your workspace, connect Chrome Devtools, apply this rule, and every lighthouse_audit call is checked against it from then on.
Questions about lighthouse_audit
Get Lighthouse score and reports for accessibility, SEO, best practices, and agentic browsing. This excludes performance. For performance audits, run ${startTrace.name}. It is categorised as a Execute tool in the Chrome Devtools MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Chrome Devtools MCP server in PolicyLayer and add a rule for lighthouse_audit: 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 Chrome Devtools. Nothing to install.
lighthouse_audit 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 lighthouse_audit 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 lighthouse_audit. 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.
lighthouse_audit is provided by the Chrome Devtools MCP server (@async23/chrome-devtools-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Chrome Devtools, and thousands of servers like it.
Across the catalogue