Lighthouse MCP
Enables AI models to perform Google Lighthouse website performance analysis, including Core Web Vitals, accessibility, SEO audits, and actionable optimization recommendations. Provides comprehensive web performance insights through natural language i
What is Lighthouse MCP?
Lighthouse MCP is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to enables ai models to perform google lighthouse website performance analysis, including core web vitals, accessibility, seo audits, and actionable optimization recommendations. provides comprehensive w...
Enables AI models to perform Google Lighthouse website performance analysis, including Core Web Vitals, accessibility, SEO audits, and actionable optimization recommendations. Provides comprehensive web performance insights through natural language i
This server falls under the Monitoring & Observability category on MCPgee, the world's largest MCP server directory with 33,000+ servers.
Features
- Enables AI models to perform Google Lighthouse website perfo
Use Cases
Maintainer
Works with
Installation
Manual Installation
npx lighthouse-mcpConfiguration
Configuration Details
claude_desktop_config.json
Performance
Response Metrics
Resource Usage
How to Set Up and Use Lighthouse MCP
Lighthouse MCP wraps Google Lighthouse inside an MCP server so AI assistants can run full website audits—performance, accessibility, SEO, PWA readiness, and security—through natural language. It exposes over a dozen focused tools including Core Web Vitals checks, unused JavaScript analysis, and mobile-versus-desktop comparisons, plus eight built-in prompt templates for generating actionable reports. Developers and performance engineers use it to diagnose web performance regressions and get prioritised optimisation recommendations without leaving their AI coding environment.
Prerequisites
- Node.js 18 or later installed
- Google Chrome or Chromium installed on the machine running the server
- An MCP-compatible client such as Claude Desktop or Claude Code
- Optionally, the CHROME_PATH environment variable set if Chrome is not in the default location
Confirm Chrome is installed
Lighthouse MCP launches a headless Chrome instance to perform audits. Verify Chrome or Chromium is available on your system before configuring the server.
google-chrome --version || chromium --versionOpen your MCP client configuration file
For Claude Desktop this is claude_desktop_config.json (macOS: ~/Library/Application Support/Claude/claude_desktop_config.json). For VS Code, open your settings.json and find the mcpServers key.
Add the Lighthouse MCP server entry
The server requires no API keys. npx downloads and runs @danielsogl/lighthouse-mcp on demand. Set CHROME_PATH only if Chrome is installed in a non-standard location.
{
"mcpServers": {
"lighthouse": {
"command": "npx",
"args": ["-y", "@danielsogl/lighthouse-mcp@latest"]
}
}
}Restart your MCP client
Quit and reopen Claude Desktop (or reload your editor) to activate the new server. No build step is required.
Run your first audit
Ask your AI assistant to run a Lighthouse audit against any public URL. The server launches a headless Chrome session and returns the full audit JSON, then the AI summarises the results.
Lighthouse MCP Examples
Client configuration
Standard claude_desktop_config.json entry. Add --no-headless and --profile-path args if you need to audit sites that require a logged-in Chrome session.
{
"mcpServers": {
"lighthouse": {
"command": "npx",
"args": ["-y", "@danielsogl/lighthouse-mcp@latest"]
}
}
}Prompts to try
Example requests that exercise the run_audit, get_core_web_vitals, find_unused_javascript, get_seo_analysis, and compare_mobile_desktop tools.
- "Run a full Lighthouse audit on https://example.com and give me the top 5 issues"
- "What are the Core Web Vitals scores for https://mysite.io and how do they compare to Google's thresholds?"
- "Find all unused JavaScript on https://example.com that I could defer or remove"
- "Compare the performance score of https://example.com on mobile vs desktop"
- "Generate a performance improvement plan for https://example.com based on its audit results"
- "Check the accessibility score and list WCAG violations for https://example.com"Troubleshooting Lighthouse MCP
Error: Chrome not found or cannot be launched
Set the CHROME_PATH environment variable in your MCP config to the full path of your Chrome executable, e.g. /usr/bin/google-chrome or /Applications/Google Chrome.app/Contents/MacOS/Google Chrome.
Audit times out or returns empty results for localhost URLs
Lighthouse runs inside a separate Chrome process that may not share your machine's localhost routing. Try using your machine's LAN IP (e.g. http://192.168.1.x:3000) or use --no-headless with a persistent Chrome profile so the browser can reach your local dev server.
npx takes a long time on the first invocation
npx downloads @danielsogl/lighthouse-mcp from the npm registry on first use. Subsequent runs use the cached package. Ensure npm's cache directory is writable (~/.npm).
Frequently Asked Questions about Lighthouse MCP
What is Lighthouse MCP?
Lighthouse MCP is a Model Context Protocol (MCP) server that enables ai models to perform google lighthouse website performance analysis, including core web vitals, accessibility, seo audits, and actionable optimization recommendations. provides comprehensive web performance insights through natural language i It connects AI assistants to external tools and data sources through a standardized interface.
How do I install Lighthouse MCP?
Follow the installation instructions on the Lighthouse MCP GitHub repository. Clone the repo, install dependencies, and add the server config to your AI client.
Which AI clients work with Lighthouse MCP?
Lighthouse MCP works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.
Is Lighthouse MCP free to use?
Yes, Lighthouse MCP is open source and available under the MIT license. You can use it freely in both personal and commercial projects.
Lighthouse MCP Alternatives — Similar Monitoring & Observability Servers
Looking for alternatives to Lighthouse MCP? Here are other popular monitoring & observability servers you can use with Claude, Cursor, and VS Code.
Netdata
★ 78.9kReal-time infrastructure monitoring with metrics, logs, alerts, and ML-based anomaly detection.
Kubeshark
★ 11.9keBPF-powered network observability for Kubernetes. Indexes L4/L7 traffic with full K8s context, decrypts TLS without keys. Queryable by AI agents via MCP and humans via dashboard.
Mission Control
★ 4.9kSelf-hosted AI agent orchestration platform: dispatch tasks, run multi-agent workflows, monitor spend, and govern operations from one mission control dashboard.
Grafana
★ 3.0kThis MCP server enables natural-language querying of Grafana logs by automatically detecting log sources and service labels. It provides read-only access to log data with intelligent caching for efficient repeat queries.
Sentrux
★ 2.4kReal-time architectural sensor that helps AI agents close the feedback loop, enabling recursive self-improvement of code quality. Pure Rust.
OpenInference
★ 986OpenTelemetry Instrumentation for AI Observability
Browse More Monitoring & Observability MCP Servers
Explore all monitoring & observability servers available in the MCPgee directory. Each server includes setup guides for Claude, Cursor, and VS Code.
Set Up Lighthouse MCP in Your Editor
Choose your AI client for step-by-step setup instructions.
Quick Config Preview
Add this to your claude_desktop_config.json or .cursor/mcp.json
Ready to use Lighthouse MCP?
Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.