lighthouse-mcp
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!
Safety scan
A static text scan, not a guarantee. Select the badge to see what was scanned and every finding.
Check it deeper on your machine
It has changed since its scan on 11 Nov 2026.
As a Claude Code plugin, install it and then ask Claude Code:
/plugin marketplace add keithmackay/mackayi/plugin install scanskillsafety@mackayiDo a deep scan of https://github.com/priyankark/lighthouse-mcp with scanskillsafety
Or from a terminal, clone it and run it:
git clone https://github.com/keithmackay/scanskillsafety-skill ~/.claude/skills/scanskillsafetynode ~/.claude/skills/scanskillsafety/cli.cjs --deep 'https://github.com/priyankark/lighthouse-mcp'
It checks the exact commit: every file, its packages against OSV (api.osv.dev), how it compares with this page's scan (findsafeskills.com receives the repository's address), and, if you agree, Claude reading every file with your own Claude subscription. It never runs the code.
Badge for your README
Markdown
[](/listings/priyankark--lighthouse-mcp)HTML
<a href="/listings/priyankark--lighthouse-mcp"><img src="/api/listings/priyankark--lighthouse-mcp/badge.svg" alt="findsafeskills safety rating" /></a>Install
Install instructions from the README
As written by the repo's author. findsafeskills has not verified these steps.
Option 1: From MCP Registry (Recommended)
This server is available in the [Model Context Protocol Registry](https://registry.modelcontextprotocol.io/servers/io.github.priyankark/lighthouse-mcp). 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
What was scanned
The files the safety scan read, as written by the repository's author and shown as plain text. Lines with a finding are marked.
README.md · README · 172 lines
View this file on GitHub (read at the repository's current version: the scan did not record which commit it read)
This file has changed since it was scanned, so this is not exactly the text that was scanned, and no line is marked. The findings are listed with the safety scan above.
- # 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](https://registry.modelcontextprotocol.io/servers/io.github.priyankark/lighthouse-mcp). Install it using your MCP client or Claude Desktop.
- ### Option 2: Using npx
- You can run the tool directly using npx without installation:
- ```bash
- npx lighthouse-mcp
- ```
- ### Option 3: Global Installation
- Install the package globally from npm:
- ```bash
- npm install -g lighthouse-mcp
- ```
- Then run it:
- ```bash
- lighthouse-mcp
- ```
- ### Option 4: Local Development
- 1. Clone this repository
- 2. Install dependencies:
- ```bash
- npm install
- ```
- 3. Build the project:
- ```bash
- npm run build
- ```
- 4. Run the server:
- ```bash
- npm start
- ```
- ## MCP Configuration
- ### When installed via npm (global or npx)
- Add the following to your MCP settings configuration file:
- ```json
- {
- "mcpServers": {
- "lighthouse": {
- "command": "npx",
- "args": ["lighthouse-mcp"],
- "disabled": false,
- "autoApprove": []
- }
- }
- }
- ```
- ### When using local development version
- Add the following to your MCP settings configuration file:
- ```json
- {
- "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"
- - `device` (optional): Device to emulate (defaults to "mobile")
- - Options: "mobile", "desktop"
- - `throttling` (optional): Whether to apply network throttling (defaults to true)
- **Example:**
- ```json
- {
- "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:**
- ```json
- {
- "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 22.19+
- - Chrome/Chromium browser (for Lighthouse)
- ## Security
- Chrome runs with its sandbox enabled. Localhost, IPv4 loopback, and IPv6 loopback remain supported by default. Private, link-local, cloud metadata, and other non-public destinations are blocked, including requests made by redirects and page resources. Connections use validated IP addresses to prevent DNS rebinding. Because loopback access is intentional, audit only pages you trust to access services on your own machine. For hostile sites, use a separate environment with network isolation.
- Audits are limited to one at a time and time out after 120 seconds. Chrome and the audit proxy are cleaned up after success or failure.
- ### Public-only audits
- Set `AUDIT_ALLOW_LOOPBACK=false` to reject loopback destinations as well as private and metadata addresses. Hosted workers must use this setting and infrastructure egress isolation. Local development keeps loopback access by default.
- ## Maintainer CI and releases
- GitHub Actions runs the build, network and release-policy tests, npm security audit, and real Chrome smoke tests on the minimum supported Node version and Node 24. Node 24 also installs the npm tarball in a clean temporary project and checks its executable, dependencies, MCP version, and browser audits.
- Every push to `main` runs the release pipeline. When package files change, it automatically increments the patch version (or honors a larger version already committed), synchronizes package metadata, repeats validation, commits and tags the release, publishes to npm with provenance, and creates a GitHub release. Changes limited to documentation, tests, or workflows do not publish a new version. Runtime server versions come from `package.json`.
- Dependabot checks npm and GitHub Actions weekly. A successful PR CI run automatically merges npm updates only when all existing changed dependencies are stable patch/minor upgrades and only `package.json` / `package-lock.json` changed. Major upgrades, 0.x minor upgrades, downgrades, prereleases, and GitHub Actions changes require review. The merge job runs only trusted code from `main`, verifies the tested PR head, and explicitly dispatches publishing after a bot merge.
- npm publishing uses the `npm` GitHub environment and an npm trusted publisher for `priyankark/lighthouse-mcp`, workflow `publish.yml`, environment `npm`, with direct publishing allowed. No npm token is stored in GitHub. The environment accepts deployments only from `main`.
- To retry a failed release, rerun the **Publish** workflow or run `./release.sh`. The pipeline reuses an unpublished version and skips an already published, unchanged package. If a reserved release tag points to different code, it stops rather than overwriting that version. For a breaking change, update `package.json` and `package-lock.json` to the intended major/minor version in the reviewed PR before merging.
Ratings and comments
Sign in to rate this skill.
Sign inFree to use. If it’s helped, pass it on.