Skip to content
MCP server

Lighthouse & Accessibility Audit for AI Agents

Lighthouse, Core Web Vitals and axe accessibility audit with a PASS or FAIL verdict

Install
Pricing
Paid
Platforms
API
Runs
Remotely
Version
1.0.0
Listing updated
3 days ago

About Lighthouse & Accessibility Audit for AI Agents

Lighthouse & Accessibility Audit for AI Agents is a paid MCP server for developer tools. It runs as a hosted remote server, so there is nothing to install locally.

This is an Apify Actor exposed over MCP, built so an agent gets a decision instead of a 2 MB report. Each URL is run through Lighthouse three times per device type, and the response gives the median scores and the spread, which the author says makes the numbers stable enough to gate a deploy on. Audits run on a dedicated Chrome rather than your own machine.

You set minimum scores for performance, accessibility, SEO and best practices, plus limits for LCP, CLS and total blocking time, and choose the axe impact level that fails the run. The output lists each failed check in plain words, for example performance 72 below 90, with the top five fixes ranked by estimated points and pointing at an element or a file. axe-core checks cover WCAG 2.2 A and AA plus best-practice rules, grouped by impact. Links to the full Lighthouse report in JSON and HTML are returned separately.

Up to 50 public URLs can go in one run, on mobile and desktop. Pricing is per URL per form factor, and pages that fail to load are not charged.

Install

Run in a terminal

claude mcp add --transport http lighthouse-gate 'https://mcp.apify.com/?tools=fluidfaith/lighthouse-gate'

Add to Settings → Connectors → Add custom connector

https://mcp.apify.com/?tools=fluidfaith/lighthouse-gate
Install in CursorOpens Cursor, which asks you to confirm. Or add it by hand:

Add to ~/.cursor/mcp.json

{
  "mcpServers": {
    "lighthouse-gate": {
      "url": "https://mcp.apify.com/?tools=fluidfaith/lighthouse-gate"
    }
  }
}
Install in VS CodeOpens VS Code, which asks you to confirm. Or add it by hand:

Add to .vscode/mcp.json

{
  "servers": {
    "lighthouse-gate": {
      "type": "http",
      "url": "https://mcp.apify.com/?tools=fluidfaith/lighthouse-gate"
    }
  }
}

Add to ~/.codeium/windsurf/mcp_config.json

{
  "mcpServers": {
    "lighthouse-gate": {
      "serverUrl": "https://mcp.apify.com/?tools=fluidfaith/lighthouse-gate"
    }
  }
}

Add to your client's MCP settings (most use this shape)

{
  "mcpServers": {
    "lighthouse-gate": {
      "type": "http",
      "url": "https://mcp.apify.com/?tools=fluidfaith/lighthouse-gate"
    }
  }
}

What it does

Median of three runs
Reports median Lighthouse scores and their spread for stable results.
Verdict against thresholds
Returns PASS, FAIL or ERROR using minimum scores and vitals limits you set.
Ranked top fixes
Lists up to five fixes with the element or file and estimated points gained.
axe accessibility checks
Runs axe-core WCAG 2.2 A and AA rules and groups violations by impact.
Mobile and desktop
Audits both form factors in one call.
Compact output
Keeps the response small and saves the full report as a link.

Good for

  • Gate a deploy on performance and accessibility scores
  • Ask an agent which fixes will raise a page's score most
  • Audit several pricing and landing pages in one run
  • Track Core Web Vitals regressions after a release
  • Find serious colour-contrast violations

Pricing

Paid

$0.02 per URL per form factor; failed loads free

Prices change. Check apify.com before you buy.

Lighthouse & Accessibility Audit for AI Agents FAQ

How much does it cost?

$0.02 per URL per form factor, so one URL on mobile and desktop is $0.04. Pages that fail to load are free.

How many URLs per run?

Up to 50 public http(s) URLs.

What does the verdict mean?

PASS, FAIL or ERROR, where ERROR means the page could not be audited and is not charged.

How do I connect it?

Use Apify's MCP URL with your Apify token as a bearer header, or call the Actor through the Apify API.

Is Lighthouse & Accessibility Audit for AI Agents free?

No. Lighthouse & Accessibility Audit for AI Agents is a paid product.

How do I add Lighthouse & Accessibility Audit for AI Agents to Claude Code?

Run this command in your terminal: claude mcp add --transport http lighthouse-gate 'https://mcp.apify.com/?tools=fluidfaith/lighthouse-gate'

What are the best alternatives to Lighthouse & Accessibility Audit for AI Agents?

The closest alternatives to Lighthouse & Accessibility Audit for AI Agents are REA, Codebase Memory, GitHub, Serena MCP: the IDE for your agent and XERJ.

Alternatives to Lighthouse & Accessibility Audit for AI Agents

  1. REA

    MCP server

    CLI and MCP server that lets coding agents reverse engineer apps and binaries

    Runs locally
    • Open source
    • 464K GitHub stars
    • Developer tools
  2. Codebase Memory

    MCP server

    Local MCP server that builds a code knowledge graph for AI coding agents

    Runs locally
    • Open source
    • 48.7K GitHub stars
    • Knowledge and memory
  3. GitHub

    MCP server

    Official MCP server connecting AI assistants to GitHub repos, issues and workflows

    Not checked yet
    • Remote
    • Open source
    • 34.5K GitHub stars
    • Developer tools
  4. MCP toolkit giving coding agents symbol-level code retrieval and editing

    Runs locally
    • Open source
    • 31.5K GitHub stars
    • Developer tools
  5. XERJ

    MCP server

    Local search engine for AI agents with cited answers over your code and docs

    Runs locally
    • Open source
    • 19.2K GitHub stars
    • Knowledge and memory
  6. Ouroboros

    MCP server

    Spec-first layer that pins requirements and verifies results of AI coding agent work

    Runs locally
    • Open source
    • 6.4K GitHub stars
    • Developer tools