The OnPage Lighthouse API is based on Google’s open-source Lighthouse project for measuring the quality of web pages and web apps.
AI agents call on_page_lighthouse to retrieve information from Dataforseo without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
| Parameter | Type | Required | Description |
|---|---|---|---|
url | string | Yes | URL of the page to parse |
full_data | boolean | — | Return the complete API response instead of a reduced version |
accept_language | string | — | Accept-Language header value |
custom_user_agent | string | — | Custom User-Agent header |
enable_javascript | boolean | — | Enable JavaScript rendering |
Parameters from the server's own tool schema.
This tool queries an external API to fetch Lighthouse audit results and metrics about web pages. It retrieves data about page quality, performance, and accessibility without creating, modifying, executing code, deleting, or moving money. The blast radius of misuse is minimal—an attacker could only gather unwanted SEO/performance intelligence about websites, not compromise them.
From the tool's definition Tool measures and retrieves web page quality metrics from Google's Lighthouse; performs audits and returns performance/quality data with no modification or execution capabilities on target sites.
Risk signalsAccepts URL/endpoint input (url)
Attacks that exploit this kind of access
The OnPage Lighthouse API is based on Google’s open-source Lighthouse project for measuring the quality of web pages and web apps. It is categorised as a Read tool in the Dataforseo MCP Server, which means it retrieves data without modifying state.
on_page_lighthouse accepts 5 parameters: url, full_data, accept_language, custom_user_agent, enable_javascript. Required: url. The full parameter table on this page comes from the server's own tool schema.
Register the Dataforseo MCP server in PolicyLayer and add a rule for on_page_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 Dataforseo. Nothing to install.
on_page_lighthouse 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 on_page_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 on_page_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.
on_page_lighthouse is provided by the Dataforseo MCP server (dataforseo-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.