LighthouseSAFE
MCP server that enables AI agents to perform comprehensive web audits using Google Lighthouse with 13+ tools for performance, accessibility, SEO, and security analysis.
Overview
From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.
[](https://www.npmjs.com/package/@danielsogl/lighthouse-mcp) [](./LICENSE) [](https://nodejs.org) [](https://github.com/danielsogl/lighthouse-mcp-server/actions) [](https://codecov.io/gh/danielsogl/lighthouse-mcp-server) [](https://github.com/sponsors/danielsogl)
A Model Context Protocol (MCP) server that provides comprehensive web performance auditing and analysis capabilities using Google Lighthouse. This server enables LLMs and AI agents to perform detailed website performance assessments, accessibility audits, SEO analysis, security checks, and Core Web Vitals monitoring.
🌟 Key Features
- 🚀 Performance Analysis: Complete Lighthouse audits with Core Web Vitals, performance scores, and optimization recommendations
- ♿ Accessibility Audits: WCAG compliance checking and accessibility score analysis
- 🔍 SEO Analysis: Search engine optimization audits and best practice recommendations
- 🔒 Security Assessment: HTTPS, CSP, and security vulnerability scanning
- 📊 Resource Analysis: JavaScript, CSS, image, and font optimization opportunities
- 📱 Mobile vs Desktop: Comparative analysis across devices with throttling options
- **⚡ Cor
16a988a2f999OBSERVED · 2026-10-07Connect
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 @danielsogl/[email protected]
{
"mcpServers": {
"lighthouse-mcp": {
"command": "npx",
"args": [
"-y",
"@danielsogl/[email protected]"
]
}
}
}Exposed tools (11)
10 read · 1 write · 0 destructive.
| Tool | Risk | Description |
|---|---|---|
analyze_resources | read | |
check_performance_budget | read | |
compare_mobile_desktop | read | |
find_unused_javascript | read | |
get_accessibility_score | read | |
get_core_web_vitals | read | |
get_lcp_opportunities | read | |
get_performance_score | read | |
get_security_audit | read | |
get_seo_analysis | read | |
run_audit | write |
Trust audit
SAFEgrade B · trust 89/100 Nothing in the source contradicts what it says it does. Grade A is reserved for packages that have also passed the behavioural sandbox.
| Layer | What it checks | Result |
|---|---|---|
| L0 | Provenance & inventory | PASS |
| L1 | Static analysis of the code | PASS |
| 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
- none-observed
- Shell
- none-observed
- Dependencies
- not all pinned
- Secrets in source
- none-found
Findings (5)
.prettierrc.json
.release-please-manifest.json
const { isError, payload } = await callTool("get_performance_score", { url: "http://127.0.0.1:1/" });url: `http://127.0.0.1:${port}/`,@modelcontextprotocol/sdk, chrome-launcher, lighthouse, zod, @eslint/js, @typescript-eslint/eslint-plugin, @typescript-eslint/parser, @vitest/coverage-v8
Gates applied: no_behavioural_pass.
16a988a2f999full audit observations/trust-audit/mcp-server/danielsogl__lighthouse-2.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 |
|---|---|---|---|---|---|
| 2026-10-07 | 16a988a2f999 | SAFE | B | 89 | first audit |
Questions
What is the Lighthouse MCP server?
MCP server that enables AI agents to perform comprehensive web audits using Google Lighthouse with 13+ tools for performance, accessibility, SEO, and security analysis.
What tools does Lighthouse expose?
11 in total: 10 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?
The audit found nothing in the source that contradicts what it says it does, and graded it B (89/100). Grade A is held back for packages that have also passed a sandboxed behavioural run, which is why a clean server reads B.
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 @danielsogl/lighthouse-mcp at 2.0.1.
How current is this page?
The grade is for one exact copy of the source (16a988a2f999), read on 2026-10-07. The repository is watched and re-audited when it changes.