Log inSubmit server
Agent Audit logo

Agent Audit

Turns Lighthouse and page-inspection results into prioritized fix packs for coding agents.

InstallRepositoryWebsite
Full README Compare alternatives Embed widget Claim this listing

Install Agent Audit

Pick your client, then add it in one click or paste the config.

STDIONode.js
~/Library/Application Support/Claude/claude_desktop_config.json
claude_desktop_config.json
{
  "mcpServers": {
    "agent-audit": {
      "command": "npx",
      "args": [
        "-y",
        "@fullstackdegen/agent-audit"
      ],
      "env": {
        "LIGHTHOUSE_MCP_ALLOW_LOCALHOST": "YOUR_VALUE_HERE"
      }
    }
  }
}

Settings → Developer → Edit Config, merge this into mcpServers, then fully quit and reopen Claude Desktop.

Values are written into the snippet above so you can paste it as is. They never leave your browser.

We couldn’t confirm it starts correctly

We ran the install command but it didn't respond within our test window — this can mean a slow first-time install rather than a real problem.

npx -y @fullstackdegen/agent-audit

No response to initialize.

This is an experimental automated check and can have false negatives — missing environment variables, a slow cold install, etc. It doesn’t necessarily mean something’s wrong. Last checked 7d ago.

Overview

The agent-audit MCP server runs Lighthouse and bounded same-page inspection against a target URL, then returns structured findings for coding agents. It covers mobile and desktop performance, accessibility, SEO, Core Web Vitals, indexability, and AI visibility signals. Use it when an agent needs prioritized implementation steps, repository search hints, and measurable verification criteria instead of a raw Lighthouse report. Public URLs are supported by default, with an explicit option for localhost audits.

Use cases

  • Audit a production website for Lighthouse and SEO issues
  • Generate prioritized accessibility fix packs for a coding agent
  • Check a localhost application before release
  • Compare repeated mobile and desktop audit results
  • Verify website changes against measurable acceptance criteria

Key features

  • Mobile and desktop Lighthouse audits
  • Core Web Vitals distributions
  • Technical SEO and accessibility checks
  • Bounded same-page inspection
  • Structured agent fix packs
  • Localhost audit opt-in

Tools1

What Agent Audit lets your agent do. Expand a tool for its parameters.

Self-reported~22 tokens of context

Security & health

What it can reach and how reliably it runs — from our own checks, not the maintainer’s claims.

ActiveLast checked 1d ago

Recent health check succeeded.

5/5 checks healthy over the last 41d

Supply-chain signal

No high-severity advisories surfaced by our automated scan.

Critical 0High 0Medium 0Low 0

Scanned 15d ago via OSV.dev · @fullstackdegen/agent-audit (npm)

Adoption & maintenance

Factual signals from GitHub, npm, and our automated checks — not a rating.

GitHub stars4Stargazers on the source repository.
npm downloads222Package downloads in the last 30 days.
Last commit1mo agoMost recent push to the default branch.
Install checkInconclusiveDidn't respond in our test window — often a slow first install.
Tools exposed1Callable tools this server registers over MCP.
Directory activity1 viewsConfig copies, upvotes, and views on AllMCPs.

How Agent Audit works

What agent-audit does

The agent-audit MCP server converts website audits into an issue backlog that a coding agent can inspect and act on. It combines Google Lighthouse results with bounded inspection of the audited page. The resulting report includes prioritized issues, evidence, suggested actions, acceptance criteria, and fix packs.

Audits cover mobile and desktop Lighthouse scores for Performance, Accessibility, Best Practices, and SEO. They also report distributions for FCP, Speed Index, LCP, TBT, and CLS. Page inspection adds checks for broken links, accessible link names, metadata, canonical tags, robots signals, JSON-LD, Open Graph data, indexability, images, assets, and LLM visibility. When enough page content is available, the report can also include a conservative llms.txt draft.

The agent-audit MCP server is intended for workflows where an agent will search a repository, make focused changes, rerun an audit, and compare the result with defined acceptance criteria.

How it works

The analyze_website_performance tool accepts a URL and an optional audit mode. fast performs one mobile run and one desktop run. reliable, the default, performs three runs for each profile and reports medians with variability ranges.

Results are exposed as MCP structuredContent with schema validation, alongside Markdown generated from the same canonical report. Fix packs contain issue identifiers, priority, severity, affected profiles, repository search hints, implementation steps, acceptance criteria, and rerun guidance. Search hints are clues rather than guaranteed file paths, so the agent must inspect the repository before editing.

For implementation work, use structuredContent as the authoritative data and Markdown as the execution summary. A typical loop is to process fix packs by priority, map evidence to source files or components, apply one focused change, run repository tests, rerun the audit, and check the acceptance criteria.

Setup and configuration

The package requires Node.js 20 or newer and Google Chrome or Chromium. Start the server with:

Terminal
npx -y @fullstackdegen/agent-audit

It can be registered as a local stdio server in Claude Desktop, Claude Code, Codex, VS Code with GitHub Copilot, and Cursor. Cursor and other clients can pass --local when auditing a local application.

By default, only publicly routable HTTP and HTTPS URLs are accepted. Run the server with --local, or set LIGHTHOUSE_MCP_ALLOW_LOCALHOST=true, to permit localhost, *.localhost, 127.0.0.0/8, and ::1. Private network ranges, metadata addresses, and other non-public destinations remain blocked.

Tools and capabilities

The agent-audit MCP server exposes analyze_website_performance. Its supported capabilities include:

  • Running mobile and desktop Lighthouse audits.
  • Repeating audits and reporting medians and variability.
  • Inspecting same-origin page content with bounded fetch limits.
  • Detecting performance, accessibility, SEO, indexability, asset, and AI-discovery issues.
  • Returning structured fix packs with repository hints and verification steps.
  • Producing schema-validated MCP output and equivalent Markdown.

Limitations and notes

The server launches Chrome against user-provided URLs, so URL validation is part of its security model. It rejects unsupported protocols, embedded credentials, loopback targets unless local access is enabled, and addresses that resolve to private, link-local, multicast, reserved, or cloud-metadata networks.

Inspection is bounded by time, byte-size, and resource limits. Audit results can vary between runs; reliable mode exposes that variability but does not eliminate it. Fix-pack repository hints are not confirmed paths, and an audit report alone is not evidence that a code change is complete. The agent should rerun the audit and compare results with the stated criteria.

Read the full README View source on GitHub

Reviews

No reviews yet — be the first to share how it worked for you.

Frequently Asked Questions about Agent Audit

agent-audit is an MCP server that connects coding agents to Chrome, Google Lighthouse, and bounded inspection of public or explicitly allowed local webpages. Its main tool, analyze_website_performance, produces mobile and desktop audit results, site intelligence, prioritized issues, and fix packs with implementation and verification guidance.

Install and run it with `npx -y @fullstackdegen/agent-audit`. Node.js 20 or later and Google Chrome or Chromium are required. The package can then be registered as a local stdio MCP server in supported clients such as Claude Desktop, Claude Code, Codex, VS Code, and Cursor.

Yes, agent-audit can scan localhost after local access is explicitly enabled. Start it with `--local` or set `LIGHTHOUSE_MCP_ALLOW_LOCALHOST=true`; this permits localhost, `*.localhost`, loopback IPv4, and `::1`, while other private and reserved network ranges remain blocked.

agent-audit checks Lighthouse Performance, Accessibility, Best Practices, and SEO on mobile and desktop. It also inspects metadata, links, canonical and robots signals, structured data, Open Graph data, indexability, images, assets, and LLM visibility, with optional conservative `llms.txt` draft generation.

Yes, agent-audit works with Cursor as a local stdio MCP server. Configure the server with `npx` and `@fullstackdegen/agent-audit`; add `--local` when the target is a localhost application rather than a publicly routable URL.

Related MCP servers

All in Coding Agents All alternatives
Add a badge to your READMEShow it’s listed — live SVG, Markdown or HTML.

AllMCPs Directory Badge

Full Badge Customizer

Showcase your server listing on GitHub or your project documentation. Embed this dynamic SVG badge to highlight official listing status and live engagement.

Badge Style:
Live Dynamic SVG PreviewAgent Audit AllMCPs Directory Badge
Markdown (GitHub README)
[![AllMCPs](https://allmcps.com/api/badge/agent-audit?style=directory)](https://allmcps.com/mcp/agent-audit)
HTML Embed
<a href="https://allmcps.com/mcp/agent-audit"><img src="https://allmcps.com/api/badge/agent-audit?style=directory" alt="Agent Audit on AllMCPs" /></a>