PluginBench
MCP Server
Maintained
MIT

io.github.priyankark/lighthouse-mcp MCP Server

io.github.priyankark/lighthouse-mcp

Run Google Lighthouse audits on any URL to measure web performance, accessibility, and SEO metrics.

What is the io.github.priyankark/lighthouse-mcp MCP server?

The Lighthouse MCP server wraps Google's Lighthouse tool to measure web page performance metrics. It allows you to run comprehensive audits on any URL, configure device emulation and network throttling, and retrieve performance scores and detailed audit results.

This server integrates Google Lighthouse into your MCP workflow, enabling automated web performance analysis. Use it to audit websites for performance, accessibility, best practices, SEO, and PWA compliance—with options to emulate mobile/desktop devices and control network conditions.

How to install io.github.priyankark/lighthouse-mcp

Copy-paste configuration for popular MCP clients.

transport: stdio
Config generated by PluginBench — verify against the source before use.
~/Library/Application Support/Claude/claude_desktop_config.json
{
  "mcpServers": {
    "lighthouse-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "lighthouse-mcp"
      ]
    }
  }
}

Tools & capabilities

Tools this server exposes to the agent.

  • run_audit — Run a comprehensive Lighthouse audit on a URL with configurable categories (performance, accessibility, best-practices, seo, pwa), device emulation (mobile/desktop), and network throttling options.
  • get_performance_score — Get the performance score for a URL with optional device emulation (mobile/desktop).

Use cases

  • Measure web performance scores and identify bottlenecks on any website
  • Audit accessibility compliance and best practices for web pages
  • Compare mobile vs. desktop performance with device emulation
  • Monitor SEO and PWA readiness across multiple URLs
  • Analyze performance under simulated network throttling conditions

io.github.priyankark/lighthouse-mcp MCP server FAQ

What is the Lighthouse MCP server?

It's an MCP server that wraps Google's Lighthouse tool, allowing you to run web performance audits on any URL and retrieve metrics for performance, accessibility, best practices, SEO, and PWA compliance.

Is it free to use?

Yes, the server is free and open-source. It requires Node.js 16+ and Chrome/Chromium to run Lighthouse audits.

How do I install it in Claude Desktop?

Add the server to your MCP settings configuration file using either `npx lighthouse-mcp` or a local development path, then restart Claude Desktop.

What device types can I emulate?

You can emulate mobile or desktop devices. Mobile is the default for audits.

Can I audit specific categories only?

Yes, you can specify which categories to audit: performance, accessibility, best-practices, seo, or pwa. If not specified, all categories are audited.

What does network throttling do?

When enabled (default), it simulates network conditions to provide more realistic performance measurements. You can disable it for testing on fast connections.

README (reference)

Source of truth, from the repository.

Lighthouse MCP Server

An MCP server that wraps around Google's Lighthouse tool to help measure various performance metrics for web pages.

Features

  • Run comprehensive Lighthouse audits on any URL
  • Get performance scores and metrics
  • Configure device emulation (mobile/desktop)
  • Control network throttling
  • Select specific audit categories

Installation

Option 1: From MCP Registry (Recommended)

This server is available in the Model Context Protocol Registry. Install it using your MCP client or Claude Desktop.

Option 2: Using npx

You can run the tool directly using npx without installation:

npx lighthouse-mcp

Option 3: Global Installation

Install the package globally from npm:

npm install -g lighthouse-mcp

Then run it:

lighthouse-mcp

Option 4: Local Development

  1. Clone this repository
  2. Install dependencies:
    npm install
    
  3. Build the project:
    npm run build
    
  4. Run the server:
    npm start
    

MCP Configuration

When installed via npm (global or npx)

Add the following to your MCP settings configuration file:

{
  "mcpServers": {
    "lighthouse": {
      "command": "npx",
      "args": ["lighthouse-mcp"],
      "disabled": false,
      "autoApprove": []
    }
  }
}

When using local development version

Add the following to your MCP settings configuration file:

{
  "mcpServers": {
    "lighthouse": {
      "command": "node",
      "args": ["/absolute/path/to/lighthouse-mcp/build/index.js"],
      "disabled": false,
      "autoApprove": []
    }
  }
}

Replace /absolute/path/to/lighthouse-mcp with the actual path to this project.

Available Tools

run_audit

Run a comprehensive Lighthouse audit on a URL.

Parameters:

  • url (required): The URL to audit
  • categories (optional): Array of categories to audit (defaults to all)
    • Options: "performance", "accessibility", "best-practices", "seo", "pwa"
  • device (optional): Device to emulate (defaults to "mobile")
    • Options: "mobile", "desktop"
  • throttling (optional): Whether to apply network throttling (defaults to true)

Example:

{
  "url": "https://example.com",
  "categories": ["performance", "accessibility"],
  "device": "desktop",
  "throttling": false
}

get_performance_score

Get just the performance score for a URL.

Parameters:

  • url (required): The URL to audit
  • device (optional): Device to emulate (defaults to "mobile")
    • Options: "mobile", "desktop"

Example:

{
  "url": "https://example.com",
  "device": "mobile"
}

Example Usage

Once the MCP server is configured, you can use it with Claude:

What's the performance score for example.com?

Claude will use the get_performance_score tool to analyze the website and return the results.

Requirements

  • Node.js 16+
  • Chrome/Chromium browser (for Lighthouse)

Endorsements

<a href="https://glama.ai/mcp/servers/@priyankark/lighthouse-mcp"> <img width="380" height="200" src="https://glama.ai/mcp/servers/@priyankark/lighthouse-mcp/badge" /> </a>

Related MCP servers

Interface observations and explicit GOMS/KLM, Fitts, Hick–Hyman and cognitive walkthrough models.

View repository →

Read local AI agent sessions (Claude Code, Codex, OpenCode, Antigravity, Pi): intents, plans, tools

3
Python
MIT
View repository →

Unofficial local MCP server for Livespace CRM with read tools and guarded writes.

0
TypeScript
MIT
View repository →

Connect AI agents to Process Street workflows, tasks, runs, data sets, and operational records.

View repository →
PRprodlint logo

prodlint

Active

Static analysis for AI-generated code: 52 checks for security, reliability, performance, and AI quality issues.

15
TypeScript
MIT
View repository →
ASASOHawk logo

ASOHawk

Active

App Store optimization analytics and metadata management for iOS developers, powered by AI agents.

11
View repository →