LighthouseCAUTION
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!
Overview
From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.
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
- 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 auditcategories(optional): Array of categories to
997d37e3e9ddOBSERVED · 2026-10-06Connect
Built from this server's own package name, version and transport as found in its source — not copied from anyone's documentation, so it cannot drift against a page we do not control.
claude mcp add lighthouse-mcp -- npx -y [email protected]
{
"mcpServers": {
"lighthouse-mcp": {
"command": "npx",
"args": [
"-y",
"[email protected]"
]
}
}
}Exposed tools (2)
1 read · 1 write · 0 destructive.
| Tool | Risk | Description |
|---|---|---|
get_performance_score | read | Get just the performance score for a URL |
run_audit | write | Run a Lighthouse audit on a URL |
Trust audit
CAUTIONgrade B · trust 89/100 Install with care. The audit found things worth knowing before you trust its output.
| Layer | What it checks | Result |
|---|---|---|
| L0 | Provenance & inventory | PASS |
| L1 | Static analysis of the code | FAIL |
| L2 | Instruction surface (what it tells the agent) | PASS |
| L3 | Class-specific surface | PASS |
| L4 | Behavioural (sandbox) | SKIPPED |
What the source does
- Filesystem
- none-observed
- Network
- declared (3 observation(s))
- Shell
- none-observed
- Dependencies
- not all pinned
- Secrets in source
- none-found
Findings (9)
if (['metadata.google.internal', 'metadata.goog'].includes(hostname)) {chromeFlags: ['--headless', `--proxy-server=http://127.0.0.1:${proxy.port}`,for (const ip of ['10.0.0.1', '172.16.0.1', '192.168.1.1', '169.254.169.254', '::ffff:169.254.169.254', 'fc00::1', 'fe80::1', '0.0.0.0', '100.100.100.200', '224.0.0.1']) assert.equal(isAllowedAddress(
await assert.rejects(resolveTarget('metadata.google.internal.'));if (req.url === '/redirect') { res.writeHead(302, { location: 'http://169.254.169.254/latest/meta-data' }); res.end(); }const socket = net.connect(proxy.port, '127.0.0.1', () => socket.write('CONNECT 169.254.169.254:443 HTTP/1.1\r\nHost: 169.254.169.254:443\r\n\r\n'));if (req.url === '/redirect') { res.writeHead(302, { location: 'http://169.254.169.254/latest/meta-data' }); res.end(); }const blocked = await client.callTool({ name: 'run_audit', arguments: { url: 'http://169.254.169.254/' } });@modelcontextprotocol/sdk, chrome-launcher, ipaddr.js, lighthouse, @types/node, typescript
Gates applied: no_behavioural_pass.
997d37e3e9ddfull audit observations/trust-audit/mcp-server/priyankark__lighthouse-1.json · Report an issue / request a re-scanAudit history
Every audit this server has had. A grade with a past is a grade somebody is still checking.
| Date | Source | Verdict | Grade | Score | Change |
|---|---|---|---|---|---|
| 2026-10-06 | 997d37e3e9dd | CAUTION | B | 89 | first audit |
Questions
What is the Lighthouse MCP server?
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!
What tools does Lighthouse expose?
2 in total: 1 read-only, 1 that write, and 0 that can delete or overwrite. Every one is listed on this page with its risk.
Is Lighthouse safe to connect to an agent?
With care. The audit graded it B (89/100) and found 9 things worth knowing before you trust this server, listed below with the exact line each was found on.
What credentials does Lighthouse need?
No credential environment variables were found in its source, so it appears to need none.
How does Lighthouse run?
It speaks stdio, so it runs as a local process your client starts. It is published on npm as lighthouse-mcp at 0.1.17.
How current is this page?
The grade is for one exact copy of the source (997d37e3e9dd), read on 2026-10-06. The repository is watched and re-audited when it changes.