MCP App Store
by KeenEthics
AlchemyAgent icon

AlchemyAgent MCP Server for Claude

By AlchemyLeads

Overview

AlchemyAgent checks how a website performs for search engines and AI assistants. Ask about any public site in plain English and Claude can: - Run Google PageSpeed Insights with real-user Core Web Vitals (LCP, INP, CLS), the Lighthouse score and the biggest speed fixes. - Show how a site's real-user Core Web Vitals changed over the last 40 weeks, from the Chrome UX Report. - Check whether AI and search crawlers (GPTBot, OAI-SearchBot, ChatGPT-User, ClaudeBot, PerplexityBot, Googlebot, Google-Extended, Bingbot and more) can reach a page: robots.txt rules per bot, noindex directives, a firewall probe, sitemap and llms.txt. - Show what AI crawlers that don't run JavaScript actually see in a page's raw HTML, and flag JavaScript app shells that look empty to them. - Check agent readiness: llms.txt validation, Markdown pages, MCP and API discovery files, feeds and sitemap freshness. - Audit JSON-LD structured data against Google's rich-result requirements, including broken JSON, relative URLs, non-ISO dates, dangling references and duplicate schema. - Grade security headers with Mozilla HTTP Observatory and list exactly which headers to add. - Check a brand's Wikidata entry, the facts AI assistants and Google's Knowledge Graph draw on, and whether the site's schema links to it. - Find Wikipedia articles that link to a domain and the brand article's page views. - Compare up to 10 domains by Tranco popularity rank, a free stand-in for domain authority. - Find AI-assistant queries in a pasted Google Search Console export: conversational prompts, follow-up pivots, AI-visibility tracker probes and chat reply artefacts. - Explain how to connect your own Search Console, GA4 and Bing Webmaster Tools data with an AlchemyAgent account. Every tool is read-only and works on public websites. No account or API key is needed. Built by AlchemyLeads, a revenue-first AI search agency.

How to connect

  1. Claude: Open the AlchemyAgent listing in the Claude connectors directory and choose Connect. Claude listing AlchemyAgent exposes 12 tools here.

Tools

agent_readiness

Claude
Check how ready a site is for AI agents: llms.txt (validated against the llmstxt.org format, with broken-link check) and llms-full.txt, Markdown versions of pages, agent and API discovery files (MCP, A2A agent card, RFC 9727 API catalog, OpenAPI), RSS/Atom feeds, sitemap size and freshness, and Organization/WebSite schema. Gives a starter llms.txt when missing.

ai_crawler_check

Claude
Check whether AI and search crawlers (GPTBot, OAI-SearchBot, ChatGPT-User, ClaudeBot, PerplexityBot, Googlebot, Google-Extended, Bingbot, CCBot and more) can reach a page: robots.txt rules per bot, noindex/X-Robots-Tag directives, a user-agent probe for firewall/CDN blocks, sitemap and llms.txt presence, which bots publish IP ranges for allowlisting, and AI usage preferences (Cloudflare Content-Signal, IETF Content-Usage, TDMRep, noai). Use when someone asks why they don't show up in ChatGPT/Perplexity/AI answers, or whether they block AI bots. Follows RFC 9309 robots.txt rules and the operators' published crawler docs, e.g. https://developers.openai.com/api/docs/bots and https://docs.perplexity.ai/guides/bots.

ai_render_check

Claude
Show what AI crawlers that don't run JavaScript (GPTBot, ClaudeBot, PerplexityBot, CCBot) actually see on a page: readable words in the raw HTML, title, meta description, H1 and headings, JSON-LD, images without alt text, and whether the page is a JavaScript app shell that looks empty to them. Use when someone asks why AI assistants don't mention or cite a page, or whether a React/Next/Webflow/Shopify page is readable by AI.

authority_check

Claude
Compare up to 10 domains (a site and its competitors) by Tranco popularity rank (top 1M sites). A free stand-in for domain authority. Uses the Tranco API (https://tranco-list.eu).

cwv_trend

Claude
Show how a site's real-user Core Web Vitals (LCP, INP, CLS, FCP, TTFB) changed over the last ~40 weeks, from the Chrome UX Report History API. Use for 'are we getting faster?', before/after a redesign or migration, or comparing then vs now. Pass a homepage for the whole site (origin) or a deeper URL for that page; falls back to the origin when the page has too little traffic. Uses the Chrome UX Report History API (https://developer.chrome.com/docs/crux/history-api).

data_connections

Claude
Explain how to connect the user's own Google Search Console, GA4 and Bing Webmaster Tools data to AlchemyAgent. This free connector has no account, so it can't hold connections; use this when someone asks about their own search traffic, queries or analytics.

entity_check

Claude
Check how a brand appears in Wikidata, the open knowledge base that Google's Knowledge Graph and AI assistants draw brand facts from. Finds the item by the site's official website (or by brand name), lists its facts (description, type, founding date, headquarters, social profiles, Wikipedia article), flags gaps, and checks whether the homepage's Organization schema links to it in sameAs. Uses the Wikidata API and query service (https://www.wikidata.org/wiki/Wikidata:Data_access).

gsc_query_classifier

Claude
Classify a Google Search Console queries export to find AI-assistant traffic: conversational prompts, follow-up pivots, AI-visibility tracker probes, agent prompts, pasted strings and chat reply artefacts, with impressions per bucket. Export from Search Console > Performance > Export > CSV and pass the contents of Queries.csv as csv_text. Processed in memory and not stored. Also returns candidate queries that the rules can't classify on their own.

pagespeed_check

Claude
Run Google PageSpeed Insights on a public URL. Returns real-user Core Web Vitals (LCP, INP, CLS from the Chrome UX Report), the Lighthouse performance score, lab metrics and the biggest speed opportunities. Use when someone asks if a site is slow, about Core Web Vitals, or for a PageSpeed score. Uses the Google PageSpeed Insights API v5 (https://developers.google.com/speed/docs/insights/v5/get-started).

schema_check

Claude
Check a page's JSON-LD structured data against Google's rich-result requirements for common types (Organization, LocalBusiness, Product, Article, FAQPage, BreadcrumbList, Review, Event, VideoObject, Service, JobPosting and more). Flags invalid JSON, missing required properties, relative URLs, non-ISO dates, dangling @id references, duplicate entities from two plugins, and self-serving reviews. Rules follow Google Search structured data docs (https://developers.google.com/search/docs/appearance/structured-data/search-gallery).

security_headers

Claude
Grade a site's security headers with Mozilla HTTP Observatory and list exactly which headers are missing or weak (HSTS, Content-Security-Policy, X-Content-Type-Options, frame protection, Referrer-Policy, Permissions-Policy), plus HTTPS and cookie flags. Uses the Mozilla HTTP Observatory API v2 (https://developer.mozilla.org/en-US/observatory/docs/faq).

wikipedia_presence

Claude
Find Wikipedia articles (in the 10 largest language editions) that link to a domain, and the brand's own Wikipedia article page views over the last 12 months (found through Wikidata). Use for brand authority, digital PR and 'are we cited on Wikipedia?' questions. Uses the MediaWiki API and Wikimedia Pageviews API (https://www.mediawiki.org/wiki/API:Exturlusage).

Similar Apps

Listed on MCP App Store

Listed on MCP App Store

Add this badge to your site or README. It links to this page.

HTML

<a href="https://mcp-app-store.keenethics-labs.com/app/alchemyagent"><img src="https://mcp-app-store.keenethics-labs.com/badges/listed-on-mcp-app-store.svg" alt="Listed on MCP App Store" width="220" height="44"></a>

Markdown

[![Listed on MCP App Store](https://mcp-app-store.keenethics-labs.com/badges/listed-on-mcp-app-store.svg)](https://mcp-app-store.keenethics-labs.com/app/alchemyagent)