lighthouse MCP Server

Use This MCP server To

Run automated Lighthouse audits on webpages via AI assistants Measure and report detailed web performance metrics Emulate mobile or desktop devices for performance testing Control network throttling to simulate different connection speeds Select specific Lighthouse audit categories for targeted analysis Enable AI agents to optimize webpage performance iteratively Integrate web performance data into developer workflows Generate performance reports for continuous monitoring

README

Lighthouse MCP Server

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

Lighthouse MCP Server Screenshot

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: Using npx (Recommended)

You can run the tool directly using npx without installation:

npx lighthouse-mcp

Option 2: Global Installation

Install the package globally:

npm install -g lighthouse-mcp

Then run it:

lighthouse-mcp

Option 3: Local Development

Clone this repository
Install dependencies:
```
npm install
```
Build the project:
```
npm run build
```
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

lighthouse-mcp FAQ

How do I install the Lighthouse MCP server?

You can install it globally via npm, run it directly with npx, or clone and build from source.

Can I configure device emulation with this MCP server?

Yes, you can emulate mobile or desktop devices to test performance under different conditions.

Is network throttling supported?

Yes, the server allows you to control network throttling to simulate various connection speeds.

How does this MCP server integrate with AI assistants?

It exposes Lighthouse audit data so AI assistants like Cursor, Cline, and GitHub Copilot can use it for performance optimization.

Can I select specific audit categories for Lighthouse reports?

Yes, you can configure which audit categories to include in the performance reports.

Does this server support real-time performance monitoring?

While primarily for on-demand audits, it can be integrated into workflows for continuous monitoring.

What platforms or environments does this MCP server support?

It runs in Node.js environments and can be used via CLI or integrated into MCP host applications.

Can I use this MCP server without installing it globally?

Yes, you can run it directly using npx without global installation.