Veljko V.

Structurify processes your WordPress content through Claude AI and generates structured knowledge data that makes your site understandable to AI systems — including ChatGPT, Perplexity, Google AI Overviews, and LLM crawlers.
What it does:
<ul>
<li>Generates AI summaries, FAQs, intent classifications, and entity graphs for every page and post</li>
<li>Outputs a canonical <code>llms.txt</code> knowledge index that AI crawlers can consume</li>
<li>Injects FAQ Schema.org structured data into your pages automatically</li>
<li>Provides REST API endpoints for AI systems to query your site’s knowledge</li>
<li>Scores each page with an AI-readiness score (0–100) based on content quality signals</li>
<li>Supports WooCommerce products with typed product intelligence</li>
<li>Builds a site-wide canonical entity graph with descriptions and page relationships</li>
<li>Includes an AI Answer Preview — see how AI would answer questions about your site</li>
</ul>
REST API endpoints included:
<ul>
<li><code>/structurify/v1/ai.json</code> — Full site knowledge index</li>
<li><code>/structurify/v1/llms.txt</code> — llms.txt for LLM crawlers</li>
<li><code>/structurify/v1/page?url={url}</code> — Structured data for a single page</li>
<li><code>/structurify/v1/search?q={query}</code> — Full-text search across summaries</li>
<li><code>/structurify/v1/entities.json</code> — Site-wide entity graph</li>
<li><code>/structurify/v1/entity/{slug}</code> — Canonical entity detail</li>
<li><code>/structurify/v1/ai-feed.json</code> — Recent updates feed</li>
<li><code>/structurify/v1/trust.json</code> — E-E-A-T trust signals</li>
<li><code>/structurify/v1/ai-score.json</code> — AI-readiness scores per page</li>
</ul>
Requirements:
<ul>
<li>A Claude API key from <a href="https://www.anthropic.com/" rel="nofollow ugc">Anthropic</a> (claude.ai)</li>
<li>WordPress 6.4 or higher</li>
<li>PHP 8.0 or higher</li>
</ul>
<h3>External services</h3>
This plugin connects to the Anthropic Claude API to process your WordPress content and generate AI summaries, FAQs, entity graphs, and structured schema data.
What is sent and when: 
When you click “Process All Content” (or cron runs automatically), the text content of your pages and posts is sent to Anthropic’s Claude API. The plugin sends the page title, body text, and metadata required to generate structured AI outputs. No personally identifiable information about your site visitors is transmitted — only the published content you choose to process.
Why it is sent: 
The content is processed by Claude AI to produce summaries, intent classifications, FAQ pairs, entity graphs, and an AI-readiness score for each page. These outputs are stored locally in your WordPress database and served via the plugin’s REST API endpoints.
Service provider: 
Anthropic, PBC — https://www.anthropic.com/
<ul>
<li>Terms of Service: https://www.anthropic.com/legal/consumer-terms</li>
<li>Privacy Policy: https://www.anthropic.com/legal/privacy</li>
</ul>
You are responsible for obtaining your own Anthropic API key and are billed directly by Anthropic based on token usage. By using this plugin you agree to Anthropic’s terms of service and privacy policy.

Structurify

AI-powered structured data for WordPress — auto-generate JSON-LD schema and get discovered by search engines and AI crawlers.

Mescio

Mescio for Agents makes your WordPress site AI-ready by silently serving posts, pages and WooCommerce products as clean, structured Markdown to any AI agent or LLM pipeline that requests it — using the standard HTTP <code>Accept: text/markdown</code> content negotiation header.
Human visitors using a browser are completely unaffected. Mescio for Agents only activates when an AI agent or crawler explicitly asks for Markdown.
<h4>Why Markdown?</h4>
Feeding raw HTML to an AI is expensive and noisy. A heading like <code>## About Us</code> costs ~3 tokens in Markdown vs 12–15 tokens as HTML — before accounting for <code><div></code> wrappers, navigation bars and script tags that carry zero semantic value. This blog post you are reading takes 16,180 tokens in HTML and 3,150 tokens in Markdown. That is an 80% reduction.
Markdown has become the lingua franca for AI systems. Mescio for Agents lets your site speak it natively, at zero cost to your human visitors.
<h4>How it works</h4>
When an HTTP client sends a request with <code>Accept: text/markdown</code>, Mescio for Agents intercepts the WordPress request lifecycle before any template is rendered, converts the post content to clean Markdown, and returns it with the correct <code>Content-Type: text/markdown</code> header.
<pre><code>curl https://yoursite.com/your-post/ \
 -H "Accept: text/markdown"
</code></pre>
<h4>Features</h4>
<ul>
<li>Zero configuration — works out of the box on any singular post, page or custom post type</li>
<li><code>/llms.txt</code> endpoint — auto-generated index of all your content in the <a href="https://llmstxt.org" rel="nofollow ugc">llmstxt.org</a> standard format, so AI agents can discover what’s on your site</li>
<li><code>/llms-full.txt</code> endpoint — full site content in a single Markdown file, ready for RAG pipelines</li>
<li>WooCommerce support — product pages include price, SKU, stock status, rating, attributes and gallery; products are grouped by category in <code>llms.txt</code></li>
<li>YAML front matter — every document includes structured metadata (title, description, URL, date, categories, tags, featured image)</li>
<li>Multilingual — detects language via WPML, Polylang, TranslatePress or WordPress locale; emits <code>Content-Language</code> and <code>Link: rel=alternate</code> headers</li>
<li>REST API endpoint — <code>/wp-json/mescio-for-agents/v1/markdown?id=<post_id></code> or <code>?url=<permalink></code></li>
<li>Page builder cleanup — aggressively strips Elementor, Divi, WPBakery and Beaver Builder layout noise</li>
<li>Token count header — <code>X-Markdown-Tokens</code> tells AI pipelines how large the document is before processing</li>
<li>Content Signals — emits <code>Content-Signal: ai-train=yes, search=yes, ai-input=yes</code></li>
<li>Correct HTTP caching — <code>Vary: Accept</code> ensures CDNs cache HTML and Markdown versions separately</li>
</ul>
<h4>Response headers</h4>
<ul>
<li><code>Content-Type: text/markdown; charset=utf-8</code></li>
<li><code>Content-Language: it</code> (or detected language)</li>
<li><code>Vary: Accept</code></li>
<li><code>X-Markdown-Tokens: 725</code></li>
<li><code>Content-Signal: ai-train=yes, search=yes, ai-input=yes</code></li>
<li><code>Link: <url>; rel="alternate"; hreflang="en"</code> (when translations available)</li>
</ul>
<h4>Multilingual plugin support</h4>
<ul>
<li>WPML — reads language and available translations automatically</li>
<li>Polylang — reads language and links to translated post IDs</li>
<li>TranslatePress — reads <code>trp_language</code> post meta</li>
<li>Manual — configure primary language and additional languages in Settings → Mescio for Agents</li>
</ul>
<h4>REST API</h4>
<pre><code>GET /wp-json/mescio-for-agents/v1/markdown?id=42
GET /wp-json/mescio-for-agents/v1/markdown?url=https://yoursite.com/my-page/
</code></pre>
<h4>Developer hooks</h4>
Filter: <code>mescio_enabled_post_types</code> — add or remove post types dynamically.
Filter: <code>mescio_pre_convert_content</code> — modify the HTML before conversion to Markdown.
Filter: <code>mescio_post_convert_content</code> — modify the Markdown after conversion.
<h4>Privacy</h4>
This plugin does not collect, store or transmit any personal data. It does not set cookies. It does not make external HTTP requests.

Mescio for Agents


simple, plug and play, for any website; implemented on tens of sites and validated the setup with cloudflare's free isitagentready.com check for content, everything is in the green.


plug and play AI discoverability

Mescio for Agents serves your WordPress content as clean Markdown to AI agents and GPT crawlers. Human visitors never notice a thing.

Structurify vs Mescio for Agents