Site Audit MCP Server
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| APIFY_TOKEN | No | Your Apify API token (https://console.apify.com/settings/integrations) | |
| GOOGLE_PSI_API_KEY | No | Optional Google PageSpeed Insights key (audit_pagespeed only) |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
Site Audit MCP: run website-audit tools (schema/AI-readiness, accessibility, tech stack, PageSpeed, AI-crawler access, page change monitoring, pay-transparency posting monitor). Each call runs a public Apify Actor on the caller's own Apify account and is billed there. Pass dryRun:true to preview without cost. Only public pages are checked.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": true
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| audit_schema_ai_readinessA | Check public pages for JSON-LD structured data, Open Graph, canonical/SEO signals, llms.txt and AI-crawler robots.txt cues. Returns a plain-English readiness score per page. Informational only; not a ranking or citation guarantee. |
| audit_accessibilityA | Run axe-core accessibility checks (WCAG 2.x A/AA by default) on public pages and list violations by impact. Static HTML only (no login, no JavaScript rendering). Useful for EAA readiness reviews; not a legal compliance certificate. |
| detect_tech_stackB | Detect CMS, JavaScript frameworks, analytics, marketing tags and CDNs from public HTML and response headers, using curated fingerprints. |
| audit_pagespeedA | Run Google PageSpeed Insights (Lighthouse) on a list of URLs, a sitemap, or a same-domain crawl, on mobile and/or desktop, with aggregated scores. Requires your own free Google PageSpeed Insights API key (googleApiKey, or the GOOGLE_PSI_API_KEY environment variable when running locally). Each URL x device is one billed audit. |
| audit_ai_crawler_accessA | Check whether ChatGPT, Perplexity, Claude, Apple and Google AI crawlers can reach a website: robots.txt (RFC 9309), noindex tags and optional simulated live requests. Returns per-crawler allow/block results and fixes. |
| monitor_page_changesA | Check public pages against their previous snapshot and report new/unchanged/changed with a plain-words summary of what changed (price, date and number changes, added/removed sections) and routine noise (timestamps, ads) filtered out. The first call for a watchlist stores the baseline; later calls report changes. Use the same watchlistId each time. |
| monitor_pay_transparencyA | Screen the public job postings on Greenhouse, Lever or Ashby careers boards for POTENTIAL pay-transparency issues (missing, open-ended or unparseable pay ranges, missing benefits or close-date wording where a law asks for it) under US state and city laws, with Canadian and EU notes. Every flagged item is a potential issue that needs human review, not a finding of violation, and this is not legal advice. Re-run with the same watchlistId to get changes since the last run. Pay per event: $0.02 per initial or changed posting check, $0.005 per verified unchanged recheck (maxJobsPerCompany bounds the cost). |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 7 tools
Most tools have clearly distinct audit targets: accessibility, tech stack, PageSpeed, page changes, and pay transparency. The two AI-related audits could be mildly confused because both inspect AI/SEO signals and robots.txt cues, but their descriptions distinguish structured-data readiness from crawler access.
The set mostly follows an action_noun pattern: audit_*, detect_*, monitor_*. Minor deviations appear in longer names like audit_schema_ai_readiness and audit_ai_crawler_access, and audit_pagespeed embeds a product name, but the convention remains readable.
Seven tools is well-scoped for a site-audit server: enough to cover multiple audit categories without overwhelming an agent. Each tool appears to earn its place as a distinct audit or monitoring capability.
The surface covers many important public-site audit areas: structured data/AI readiness, accessibility, tech stack, PageSpeed, AI crawler access, page-change monitoring, and pay-transparency screening. Some common site-audit checks are absent, such as general on-page SEO metadata, broken links, redirects, and security headers, but agents can work around these gaps for the core workflows shown.