What are the runtime requirements?
Node.js 16 or later and a Chrome/Chromium browser installed on the system.
@priyankark
Basic information
Allows AI assistants such as Amp/Cline/Cursor/Claude Code/Codex/GitHub Copilot to use Google's lighthouse tool to measure perf metrics for your webpage. You can then run an agentic loop and get the assistants to optimize those metrics!
Add this server to your MCP-compatible client using the configuration below.
{
"mcpServers": {
"lighthouse": {
"command": "npx",
"args": [
"lighthouse-mcp"
],
"disabled": false,
"autoApprove": []
}
}
}Run a Lighthouse audit on a URL
Get just the performance score for a URL
Lighthouse Mcp is an MCP server that wraps Google’s Lighthouse tool to measure performance, accessibility, SEO, and other web page metrics. It is designed for developers and site owners who want automated audits through MCP‑compatible clients like Claude.
Install via the MCP Registry, npx lighthouse-mcp, npm install -g lighthouse-mcp, or local clone and build. Then add a lighthouse entry to your MCP settings file with the appropriate command and args. Once configured, ask Claude or another MCP client to audit a URL.
Node.js 16 or later and a Chrome/Chromium browser installed on the system.
You can install via the MCP Registry, run directly with `npx lighthouse-mcp`, install globally with `npm install -g lighthouse-mcp`, or clone the repo and build locally.
It requires a `url`, and optionally accepts `categories` (array from "performance", "accessibility", "best-practices", "seo", "pwa"), `device` ("mobile" or "desktop", default "mobile"), and `throttling` (boolean, default true).
Yes, the `get_performance_score` tool returns just the performance score for a URL, with an optional `device` parameter.
Yes, it is designed for use with MCP clients including Claude Desktop; example usage shows asking Claude for a performance score.

The tools your AI needs to make your games. Turn prompts into production-ready game assets — animated characters with their weapons attached, seamless textures, terrain, VFX, HUDs — and playable game kits Unity, Godot, U

AI SEO tools for MCP clients — audit whether AI crawlers can read a website, validate JSON-LD and robots.txt, and generate llms.txt, AI-crawler-aware robots.txt, and JSON-LD schema without leaving the conversation.
Console, Backend and CLI to manage Capgo Instant update and Native build for Capacitor apps Build and upload to app store your mobile app
Set up and manage the Eddyter AI rich text editor by talking to your AI agent — for Claude, Cursor, Codex and other MCP tools. A Model Context Protocol server that lets AI tools add Eddyter to a React, Next.js, Vite or R

Catch intent conflicts before code conflicts. The open-source coordination protocol for coding agents, built above Git.
Comments