Pagespeed Insights MCP Server

PageSpeed Insights MCP Server

18-tool MCP server for Google PageSpeed Insights & Chrome UX Report APIs. Analyze, compare, and optimize web performance directly through Claude, Cursor, or any MCP-compatible AI client.

🎬 View Interactive Demo → — See all 18 tools in action with animated examples Fallback URL: https://ruslanlap.github.io/pagespeed-insights-mcp/demo.html

📖 Table of Contents

• ⚡ Quick Start (Copy & Paste)
  • Claude Desktop
  • Codex / OpenAI
• 📚 Documentation
• 📝 Release Notes
• 🎯 Why You Need This
• ✨ Features
  • Core Features
  • Advanced Analysis Tools (New!)
• 🚀 Quick Installation
  • Option 1: Automatic Installation (Recommended)
  • Option 2: Via npm or GitHub Packages
    • From npm (Public Registry)
    • From GitHub Packages
  • 🔧 Configuration
  • 📝 MCP Configuration Examples
    • For Claude Desktop
    • For Codex
  • Claude Desktop Configuration
  • Google Antigravity
  • Option 3: Docker
• 🔑 Getting Google API Key
• ⚙️ Claude Desktop Configuration
  • Automatic Configuration
  • Manual Configuration
    • For npm / Global Installation
    • For GitHub Packages
    • For Docker
• 💻 Usage
  • 🔍 Full Page Analysis
  • 📱 Mobile Device Analysis
  • ⚡ Quick Performance Overview
  • 🖥️ Desktop Analysis
  • 🌐 Multi-Category Analysis
  • 🎯 Smart Performance Recommendations
  • 💾 Cache Management
  • 📸 Visual Analysis
  • 🎯 Element-Level Debugging
  • 🌐 Network Waterfall Analysis
  • ⚡ JavaScript Performance
  • 🖼️ Image Optimization Opportunities
  • 🚫 Render-Blocking Resources
  • 🔌 Third-Party Script Impact
  • 📊 Full Lighthouse Audit
• 🛠️ Available Tools
  • Core Analysis
  • CrUX & Comparison
  • Advanced Diagnostics
• 📊 Complete Ratings for example.com
• 💻 Development
• 🔧 Troubleshooting
• 📋 Requirements
• 🔒 Security
• 🙏 Acknowledgments
• 📄 License
• 💬 Support

---

⚡ Quick Start (Copy & Paste)

Claude Desktop

Add to your claude_desktop_config.json:

{
  "mcpServers": {
    "pagespeed-insights": {
      "command": "npx",
      "args": ["-y", "-p", "pino-pretty", "-p", "pagespeed-insights-mcp", "pagespeed-insights-mcp"],
      "env": {
        "GOOGLE_API_KEY": "your-google-api-key-here"
      }
    }
  }
}

Codex / OpenAI

Add to your configuration (TOML):

[mcp_servers.pagespeed-insights]
command = "npx"
args = [
  "-y",
  "-p",
  "pino-pretty",
  "-p",
  "pagespeed-insights-mcp",
  "pagespeed-insights-mcp"
]
env = { GOOGLE_API_KEY = "your-google-api-key-here" }

Note: The pino-pretty package is required for proper log formatting. The above configurations ensure it is installed automatically via npx.

For Grok Build (config.toml)

Add to ~/.grok/config.toml (global) or <repo>/.grok/config.toml (project-scoped, higher priority):

[mcp_servers.pagespeed-insights]
command = "npx"
args = ["-y", "-p", "pino-pretty", "-p", "pagespeed-insights-mcp", "pagespeed-insights-mcp"]
env = { GOOGLE_API_KEY = "${GOOGLE_API_KEY}" }
enabled = true

# Recommended companion professional MCPs (add once):
# [mcp_servers.github]      — PRs, issues, code search
# [mcp_servers.context7]    — fresh library docs (Upstash)
# [mcp_servers.serena]      — semantic code intelligence (uses your .serena/ if present)

Project-scoped example (put in this repo's .grok/config.toml for local dist/index.js + tighter Serena):

[mcp_servers.pagespeed-insights]
command = "node"
args = ["/home/ubuntuvm/Projects/pagespeed-insights-mcp/dist/index.js"]
env = { GOOGLE_API_KEY = "${GOOGLE_API_KEY}", NODE_ENV = "development" }

Verification inside Grok session:

• /mcps (or Ctrl+L → MCP tab) → ensure pagespeed-insights shows "running"
• Use tools: pagespeed-insights__analyze_page, pagespeed-insights__get_crux_data etc. (namespaced)

📚 Documentation

We have comprehensive documentation available online.

👉 View Full Documentation Site

• 🚀 Getting Started
• 🛠️ Tools Reference
• 🏗️ Architecture

You can also view the raw markdown files in the docs/ directory or run mkdocs serve locally.

📝 Release Notes

Current release: v1.5.1.

The badges at the top of this README update automatically on every release (npm version, GitHub package version, downloads). No manual edits needed.

For the complete release history, see CHANGELOG.md.

🎯 Why You Need This

Pain point 1 — "My page is slow but I don't know why." You open PageSpeed Insights, get a wall of data, and still can't tell what to fix first. This MCP gives your AI assistant 18 specialized tools that cut through the noise: it identifies the exact render-blocking resources, the specific images wasting 2 MB, the third-party scripts eating 1.5 s of main-thread time — and ranks them by impact. Ask "why is my site slow?" and get a prioritized fix list, not a 40-metric dashboard.

Pain point 2 — "I ship performance regressions to production." Your team moves fast, deploys daily, and nobody runs a full Lighthouse audit before each merge. By the time someone notices the Core Web Vitals dropped, the regression is already live. This MCP lets any developer paste a URL into Claude/Cursor and get a complete audit — lab data, field data from real Chrome users (CrUX), element-level CLS/LCP debugging — in seconds. It's the difference between catching a regression at your desk and discovering it in a Slack message from the SEO team three days later.

✨ Features

Core Features

• 🚀 Performance Analysis of web pages using Google PageSpeed Insights
• 📱 Multi-platform Support: mobile and desktop devices
• 🔍 Detailed Lighthouse Reports with comprehensive metrics
• 📊 Simplified Reports with key performance indicators
• 🎯 Smart Recommendations with priority scoring and actionable fixes
• 💾 Intelligent Caching to reduce API calls and improve performance
• 🌍 Localization - support for multiple languages
• ⚡ Quick Installation - one command setup
• 🐳 Docker Support for containerized deployment

Advanced Analysis Tools (New!)

• 📸 Visual Analysis - Screenshots, filmstrip, and full-page captures
• 🎯 Element-Level Debugging - Find specific DOM elements causing issues
• 🌐 Network Waterfall - Detailed request timing and resource loading
• ⚡ JavaScript Profiling - Execution breakdown and unused code detection
• 🖼️ Image Optimization - Specific image issues with exact savings
• 🚫 Render-Blocking Analysis - Critical request chains and dependencies
• 🔌 Third-Party Impact - Script impact grouped by provider
• 📊 Full Audits - Complete Lighthouse audits for all categories

🚀 Quick Installation

Option 1: Automatic Installation (Recommended)

# Set environment variable
export GOOGLE_API_KEY=your-google-api-key

curl -sSL https://raw.githubusercontent.com/ruslanlap/pagespeed-insights-mcp/master/scripts/install.sh | bash

The installer uses the public npm package (pagespeed-insights-mcp) by default. To install the scoped GitHub Packages build instead, configure GitHub Packages authentication first and run:

curl -sSL https://raw.githubusercontent.com/ruslanlap/pagespeed-insights-mcp/master/scripts/install.sh | \
  PAGESPEED_INSIGHTS_MCP_PACKAGE=@ruslanlap/pagespeed-insights-mcp bash

Option 2: Via npm or GitHub Packages

From npm (Public Registry)

# Global installation from npm
npm install -g pagespeed-insights-mcp

# Or use without installation
npx pagespeed-insights-mcp

From GitHub Packages

# First configure authentication (see GITHUB_PACKAGES.md for details)
# Then install globally
npm install -g @ruslanlap/pagespeed-insights-mcp

Note: This package is available on both npm and GitHub Packages.

• For npm: Use npm install pagespeed-insights-mcp
• For GitHub Packages: Use npm install @ruslanlap/pagespeed-insights-mcp (requires GitHub authentication)

For detailed instructions on installing from GitHub Packages, see GITHUB_PACKAGES.md or visit the GitHub Packages page

🔧 Configuration

The MCP server requires a Google API key to access the PageSpeed Insights API.

# Set environment variable
export GOOGLE_API_KEY=your-google-api-key

# Windows
$env:GOOGLE_API_KEY="your-google-api-key"

# Or pass directly when running
GOOGLE_API_KEY=your-google-api-key npx pagespeed-insights-mcp

📝 MCP Configuration Examples

For Claude Desktop (with pino-pretty logging):

"pagespeed-insights": {
  "command": "npx",
  "args": [
    "-y",
    "-p",
    "pino-pretty",
    "-p",
    "pagespeed-insights-mcp",
    "pagespeed-insights-mcp"
  ],
  "env": {
    "GOOGLE_API_KEY": "your-google-api-key-here"
  }
}

For Codex (with pino-pretty logging):

[mcp_servers.pagespeed-insights]
command = "npx"
args = [
  "-y",
  "-p",
  "pino-pretty",
  "-p",
  "pagespeed-insights-mcp",
  "pagespeed-insights-mcp"
]
env = { GOOGLE_API_KEY = "your-google-api-key-here" }

Note: These examples include pino-pretty for better log formatting. For production use without pretty logs, see the Logging section below.

Claude Desktop Configuration

To use this MCP server with Claude Desktop, add the following to your Claude Desktop configuration file:

{
  "mcpServers": {
    "pagespeed-insights": {
      "command": "npx",
      "args": ["-y", "-p", "pino-pretty", "-p", "pagespeed-insights-mcp", "pagespeed-insights-mcp"],
      "env": {
        "GOOGLE_API_KEY": "your-google-api-key-here"
      }
    }
  }
}

Google Antigravity

To use this MCP server with Google Antigravity, add the following configuration to your global settings file (~/.gemini/config/mcp_config.json):

{
  "mcpServers": {
    "pagespeed-insights": {
      "command": "npx",
      "args": ["-y", "-p", "pino-pretty", "-p", "pagespeed-insights-mcp", "pagespeed-insights-mcp"],
      "env": {
        "GOOGLE_API_KEY": "YOUR_GOOGLE_API_KEY"
      }
    }
  }
}

Example configuration files are available in the examples directory.

Option 3: Docker

docker build -t pagespeed-insights-mcp .
docker run -e GOOGLE_API_KEY=your-key pagespeed-insights-mcp

🔑 Getting Google API Key

To use this MCP server, you need a Google API key with the PageSpeed Insights API enabled.

[!TIP] ⚡ Quick Setup Link: You can go directly to the Google Cloud Credentials Setup Page to quickly create a key in your project.

Step-by-Step Guide

1. Go to the Google Cloud Console (or use the Quick Setup Link).
2. Create a new project or select an existing one.
3. Enable PageSpeed Insights API:
   • Navigate to APIs & Services → Library.
   • Search for "PageSpeed Insights API" and click Enable.
4. Create an API key:
   • Go to APIs & Services → Credentials.
   • Click Create Credentials → API Key.
   • Copy the generated key and set it as GOOGLE_API_KEY in your configuration.

⚙️ Claude Desktop Configuration

Automatic Configuration

If you used the scripts/install.sh script, the configuration was created automatically.

Manual Configuration

Add the configuration to your Claude Desktop file:

macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
Windows: %APPDATA%\Claude\claude_desktop_config.json
Linux: ~/.config/claude/claude_desktop_config.json

For npm installation and global installation

{
  "mcpServers": {
    "pagespeed-insights": {
      "command": "npx",
      "args": ["-y", "-p", "pino-pretty", "-p", "pagespeed-insights-mcp", "pagespeed-insights-mcp"],
      "env": {
        "GOOGLE_API_KEY": "your-google-api-key-here"
      }
    }
  }
}

For GitHub Packages installation

{
  "mcpServers": {
    "pagespeed-insights": {
      "command": "npx",
      "args": [
        "-y",
        "-p",
        "pino-pretty",
        "-p",
        "@ruslanlap/pagespeed-insights-mcp",
        "pagespeed-insights-mcp"
      ],
      "env": {
        "GOOGLE_API_KEY": "your-google-api-key-here"
      }
    }
  }
}

For Docker:

{
  "mcpServers": {
    "pagespeed-insights": {
      "command": "docker",
      "args": [
        "run",
        "--rm",
        "-i",
        "--env",
        "GOOGLE_API_KEY=your-google-api-key-here",
        "pagespeed-insights-mcp"
      ]
    }
  }
}

Restart Claude Desktop after configuration!

💻 Usage

After configuration, simply ask Claude any of these commands:

🔍 Full page analysis

Analyze the performance of https://example.com

📱 Mobile device analysis

Analyze https://example.com for mobile devices with all categories

⚡ Quick performance overview

Get a quick performance report for https://example.com

🖥️ Desktop analysis

Analyze https://example.com performance for desktop devices

🌐 Multi-category analysis

Perform a full audit of https://example.com including SEO, accessibility, and best practices

🎯 Smart performance recommendations

Get smart recommendations for improving https://example.com performance

💾 Cache management

Clear the cache to get fresh data for all subsequent requests

📸 Visual analysis

Get visual analysis for https://example.com showing screenshots and loading timeline

🎯 Element-level debugging

Show me which specific elements are causing performance issues on https://example.com

🌐 Network waterfall analysis

Analyze the network requests and resource loading for https://example.com

⚡ JavaScript performance

Get JavaScript execution breakdown for https://example.com

🖼️ Image optimization opportunities

Show me which images need optimization on https://example.com

🚫 Render-blocking resources

Find render-blocking resources on https://example.com

🔌 Third-party script impact

Analyze third-party script impact on https://example.com performance

📊 Full Lighthouse audit

Run a full audit including accessibility, SEO, and best practices for https://example.com

Available Tools

18 tools across three categories:

Core Analysis

CrUX & Comparison

Advanced Diagnostics

---

analyze_page_speed

Complete page analysis with all Lighthouse metrics.

Parameters:

• url (required): URL of the page to analyze
• strategy: "mobile" or "desktop" (default: "mobile")
• category: array of categories ["performance", "accessibility", "best-practices", "seo", "pwa"]
• locale: locale for results (default: "en")
• runs: 1–5 distinct analyses (default: 1). With runs > 1 the report shows the median with min-max spread for every score and metric, drops cached replays (identical fetchTime), and says how many it dropped. A single Lighthouse run is noise — TBT routinely swings 3× on an unchanged page, so treat differences inside the spread as no change. Note: Google re-analyses a URL about once a minute, so each extra run waits ~65 s to be genuinely distinct.
• strategy: also accepts "both" — runs mobile then desktop in one call and reports both.

get_performance_summary

Simplified report with key performance metrics.

get_recommendations

Generate smart performance recommendations with priority scoring and actionable fixes.

Parameters:

• url (required): URL of the page to analyze
• strategy: "mobile" or "desktop" (default: "mobile")
• category: array of categories to analyze (default: ["performance", "accessibility", "best-practices", "seo"])
• locale: locale for results (default: "en")

compare_baseline

Answer "did that change actually help" — with statistical honesty.

• First call on a URL+strategy records the baseline (median + spread of runs distinct analyses, saved to ~/.pagespeed-mcp/baselines.json) and compares nothing.
• Make your change, call again: a verdict is only given where the two min-max ranges do not overlap. On an unchanged page the performance score has been measured running 27–37 — comparing medians alone reports improvements that are just the instrument moving.
• Reports both the median difference and the smaller guaranteed figure the disjoint ranges actually give you. Quote the guaranteed one.
• Flags a Lighthouse version change between baseline and now, which moves scores without the page moving.

Parameters:

• url (required): URL to measure
• strategy: "mobile" or "desktop" (default: "mobile") — part of the baseline identity
• runs: 2–5 distinct analyses per side (default: 3, ~2 min)
• save_baseline: replace the baseline with this measurement (move the starting point; default: false)

clear_cache

Clear the internal cache to force fresh API requests for all subsequent analyses.

get_visual_analysis

Get screenshots and visual timeline showing how the page loads.

Parameters:

• url (required): URL of the page to analyze
• strategy: "mobile" or "desktop" (default: "mobile")

Returns:

• Final screenshot of the loaded page
• Filmstrip showing page load progression
• Full-page screenshot with DOM node mapping

get_element_analysis

Get specific DOM elements causing performance issues.

Parameters:

• url (required): URL of the page to analyze
• strategy: "mobile" or "desktop" (default: "mobile")

Returns:

• LCP (Largest Contentful Paint) element details
• CLS (Cumulative Layout Shift) causing elements
• Lazy-loaded LCP warnings

get_network_analysis

Get detailed network waterfall showing all requests with timing and size.

Parameters:

• url (required): URL of the page to analyze
• strategy: "mobile" or "desktop" (default: "mobile")

Returns:

• All network requests with timing data
• Resource breakdown by type
• Total transfer size and request count
• Network RTT and server latency

get_javascript_analysis

Get JavaScript execution breakdown showing performance impact.

Parameters:

• url (required): URL of the page to analyze
• strategy: "mobile" or "desktop" (default: "mobile")

Returns:

• JavaScript bootup time by script
• Main thread work breakdown
• Unused JavaScript analysis
• Duplicated JavaScript modules

get_image_optimization_details

Get specific images needing optimization with exact savings potential.

Parameters:

• url (required): URL of the page to analyze
• strategy: "mobile" or "desktop" (default: "mobile")

Returns:

• Improperly sized images
• Offscreen images (lazy-loading candidates)
• Unoptimized images
• Modern format recommendations (WebP/AVIF)

get_render_blocking_details

Get render-blocking resources and critical request chains.

Parameters:

• url (required): URL of the page to analyze
• strategy: "mobile" or "desktop" (default: "mobile")

Returns:

• Render-blocking CSS and JavaScript files
• Critical request chains showing dependencies
• Total blocking time

get_third_party_impact

Get third-party script impact analysis grouped by entity.

Parameters:

• url (required): URL of the page to analyze
• strategy: "mobile" or "desktop" (default: "mobile")

Returns:

• Impact by provider (Google, Facebook, etc.)
• Transfer size and blocking time per provider
• Recommended facade replacements

get_full_audit

Get comprehensive audit results for all Lighthouse categories.

Parameters:

• url (required): URL of the page to analyze
• strategy: "mobile" or "desktop" (default: "mobile")
• categories: array of categories to audit (default: ["performance", "accessibility", "best-practices", "seo"])

Returns:

• Scores for all categories
• Detailed Core Web Vitals and metrics
• Key failing audits for each category
• Framework-specific advice (if applicable)

crux_summary

Get real-world Core Web Vitals from the Chrome UX Report (field data from actual Chrome users).

Parameters:

• url (required): URL to analyze
• formFactor: "PHONE", "DESKTOP", or "TABLET" (default: "PHONE")

Returns:

• Real-world LCP, CLS, FID, INP, TTFB distributions
• Pass/fail thresholds per Core Web Vital
• Percentile breakdowns (p75)

compare_pages

Compare performance metrics between two URLs side-by-side.

Parameters:

• urlA (required): First URL to compare
• urlB (required): Second URL to compare
• strategy: "mobile" or "desktop" (default: "mobile")

Returns:

• Side-by-side Lighthouse score comparison
• Metric-level diff for LCP, CLS, FCP, TBT, SI
• Winner/loser indication per metric

full_report

Unified report combining Lighthouse lab data with CrUX real-world field data.

Parameters:

• url (required): URL to analyze
• strategy: "mobile" or "desktop" (default: "mobile")

Returns:

• Lighthouse lab scores + CrUX field data in one response
• Lab vs. field comparison for Core Web Vitals
• Actionable recommendations

batch_analyze

Analyze performance for multiple URLs with progress tracking.

Parameters:

• urls (required): Array of URLs to analyze (max 10)
• strategy: "mobile" or "desktop" (default: "mobile")

Returns:

• Performance scores for all URLs
• Sorted ranking by score
• Per-URL metric breakdown

---

Example

answer example from Claude Desktop with pagespeed-insights-mcp 🔥🔥🔥

Complete Ratings for example.com

Now I have the full analysis! Here are all the ratings:

📊 Main Lighthouse Scores

⚡ Detailed Performance Metrics

♿ Detailed Accessibility Scores (92/100)

🏆 Detailed Best Practices Scores (96/100)

🔍 Detailed SEO Scores (100/100)

🔧 Main Performance Issues

📈 Network Metrics

💡 Priority Recommendations

1. 🔴 High Priority:
   • Optimize image sizes (save 1+ MB)
   • Fix aria-label mismatches for accessibility
2. 🟡 Medium Priority:
   • Improve caching policy (TTL >600s)
   • Add width/height attributes for images
3. 🟢 Low Priority:
   • Optimize forced reflows in JavaScript

🎯 Summary

Overall Rating: Good with potential for improvement

• SEO: Perfect (100/100) 🏆
• Best Practices: Excellent (96/100) 🏆
• Accessibility: Good (92/100) ✅
• Performance: Needs attention (67/100) ⚠️

The site has excellent SEO optimization and follows best practices, but needs image optimization to improve performance.

Parameters:

• url (required): URL of the page to analyze
• strategy: "mobile" or "desktop" (default: "mobile")

Development

For better log formatting during development, it is recommended to install pino-pretty globally:

npm install -g pino-pretty

# Development mode
npm run dev

# Build project
npm run build

# Run built server
npm start

Logging / pino-pretty in MCP environments

This MCP server uses pino for logging and enables the pino-pretty transport when NODE_ENV=development.

• If you just want it to work with minimal setup (Claude, Codex, etc.), set:

NODE_ENV=production GOOGLE_API_KEY=your-google-api-key npx pagespeed-insights-mcp

or in your MCP config:

"pagespeed-insights": {
  "command": "npx",
  "args": ["pagespeed-insights-mcp"],
  "env": {
    "GOOGLE_API_KEY": "your-google-api-key-here",
    "NODE_ENV": "production"
  }
}

• If you want pretty logs in development via npx, you can have npx install pino-pretty alongside the server:

"pagespeed-insights": {
  "command": "npx",
  "args": [
    "-y",
    "-p",
    "pino-pretty",
    "-p",
    "pagespeed-insights-mcp",
    "pagespeed-insights-mcp"
  ],
  "env": {
    "GOOGLE_API_KEY": "your-google-api-key-here"
  }
}

Troubleshooting

"Google API key not provided"

Ensure the GOOGLE_API_KEY environment variable is set in your Claude Desktop configuration.

"PageSpeed Insights API error: 403"

Check if PageSpeed Insights API is enabled in your Google Cloud project.

"Invalid URL"

Ensure the URL includes the protocol — only http:// and https:// are accepted. Other schemes (file://, ftp://, javascript:, etc.) are rejected at the schema level.

Requirements

• Node.js 20 or later (Node 18 is EOL since April 2025 and is no longer supported).
• A Google API key with PageSpeed Insights and (optionally) Chrome UX Report APIs enabled.

Security

Please report security issues privately — do not open a public issue. See SECURITY.md for the disclosure policy and operator hardening notes.

Acknowledgments

Special thanks to @engmsaleh (Mohamed Saleh Zaied) for his significant contribution to the development of this project.

A very special thank you to @system-conf for their outstanding and invaluable contribution to the growth and development of this project. Your dedication, expertise, and continuous support have made a tremendous impact — this project wouldn't be where it is today without you. 🙏

License

MIT

Support

For bug reports or feature requests, please create an issue in the repository.