Title: AI Data Layer – AI SEO & AI Search Optimization: llms.txt, MCP Server, Schema (AEO/GEO) Author: aidatalayer Published: 26. juni 2026 Last modified: 2. juli 2026 --- Søk gjennom innstikk ![](https://ps.w.org/ai-data-layer/assets/banner-772x250.png?rev=3587219) ![](https://ps.w.org/ai-data-layer/assets/icon-256x256.png?rev=3587219) # AI Data Layer – AI SEO & AI Search Optimization: llms.txt, MCP Server, Schema (AEO/GEO) Av [aidatalayer](https://profiles.wordpress.org/citemysite/) [Last ned](https://downloads.wordpress.org/plugin/ai-data-layer.1.13.0.zip) * [Detaljar](https://nn.wordpress.org/plugins/ai-data-layer/#description) * [Omtalar](https://nn.wordpress.org/plugins/ai-data-layer/#reviews) * [Installasjon](https://nn.wordpress.org/plugins/ai-data-layer/#installation) * [Utvikling](https://nn.wordpress.org/plugins/ai-data-layer/#developers) [Hjelp](https://wordpress.org/support/plugin/ai-data-layer/) ## Skildring **AI search optimization built on a verified entity graph — not just static files.** AI search engines — ChatGPT, Claude, Perplexity, Gemini and Google AI Overviews — increasingly answer your visitors» questions directly. To be found and cited, your site needs structured, machine-readable, _trustworthy_ data. Most AI SEO plugins generate an llms.txt file and template schema and stop there. AI Data Layer goes further: it analyses your published content with cloud AI, extracts the real-world entities it is about, verifies them against **Wikidata**, and builds a persistent, site-wide semantic entity graph — then exposes that verified knowledge everywhere AI systems look for it. Your complete AI layer, on your own domain: * **JSON-LD schema** for search engines and AI Overviews * An **/llms.txt** index and token-efficient **Markdown copies** for LLM retrieval * A **public read-only REST API** for agents and integrations * A **per-site MCP (Model Context Protocol) server** so connected AI assistants can query your content live This is Answer Engine Optimization (AEO) and Generative Engine Optimization (GEO) with verifiable data underneath — you approve everything before it goes live. **What it does** * Extracts entities from your posts and pages and validates them against Wikidata, so AI systems get disambiguated, authoritative identifiers (`sameAs`) — not guesses. * Generates JSON-LD schema (Article/HowTo/FAQ + entity `about[]` with `sameAs`) and outputs it in the page ``. * Publishes canonical entity pages at `/entities/{id}` and lists them in your sitemap, giving AI a stable place to resolve who and what your content is about. * Serves an `/llms.txt` index and token-efficient Markdown copies (`. md`, `/llms-full.txt`) purpose-built for LLM retrieval. * Exposes a public read-only REST API (`/wp-json/ai/v1/*`) and a per-site Model Context Protocol (MCP) server so connected AI assistants can query your content. * Maps your organisation’s open-web identity with the **Entity Profile** — your` sameAs` identity links, recognition-readiness and the highest-impact gaps to close. * Scores how interconnected your content is («semantic cohesion») and recommends improvements, including a Topic Clusters map. **Why the entity graph matters for AI visibility** Template schema tells AI what _type_ of page it is looking at. A Wikidata-grounded entity graph tells AI what your content is _about_ — with identifiers it can verify against an independent source. That verifiability is what makes content citable by answer engines rather than merely crawlable. AI Data Layer is the only WordPress plugin built around this extraction verification publication pipeline. **How analysis works** Analysis runs in the AI Data Layer cloud service (it is compute-intensive and is not performed on your server). When you analyse a post, the plugin sends that post’s content to the service, which extracts entities and structured data and returns them for your review. You approve what gets published. **Licensing** A licence key is required to run analyses. A free trial (10 analyses) can be activated in one click from the setup screen — no card required. Paid plans and one-time credit packs are available; you manage billing through Stripe’s hosted checkout and customer portal (the plugin never handles your card details). ### External services This plugin connects to external services. It is not functional without the AI Data Layer cloud service, because content analysis is performed remotely. The services below are contacted, what is sent, and when: 1. **AI Data Layer cloud service** (operated by the plugin author; hosted on Supabase). 2. * **What is sent:** your licence key; your site domain; and, when you analyse a post, that post’s title, content and URL. Activating a trial also sends your site’s admin email address. * **When:** on licence validation, when you analyse a post (manually or via the optional auto-analyse setting), when you activate a trial, and when you open billing. * **Endpoint:** https://oerlbhrokgkwhtzzxndw.supabase.co * **Terms:** https://ai-datalayer.com/terms — **Privacy:** https://ai-datalayer. com/privacy 3. **OpenRouter / large language model** (used by the cloud service to perform extraction). 4. * **What is sent:** the post content you submit for analysis is processed by a large language model (gpt-4o-mini via OpenRouter) to extract entities and structured data. * **When:** during each analysis you initiate. * **Terms:** https://openrouter.ai/terms — **Privacy:** https://openrouter.ai/ privacy 5. **Wikidata** (used by the cloud service to verify entities). 6. * **What is sent:** extracted entity names are checked against the public Wikidata API to confirm identifiers. No site or personal data is sent. * **When:** during each analysis, after extraction. * **Terms / Privacy:** https://foundation.wikimedia.org/wiki/Policy:Terms_of_Use— https://foundation.wikimedia.org/wiki/Policy:Privacy_policy 7. **Stripe** (payments). 8. * **What is sent:** to start a subscription or buy credits, the plugin asks the cloud service to create a Stripe Checkout or Billing Portal session; you are then redirected to Stripe’s hosted pages to enter payment details. The plugin does not collect or store card data. * **When:** when you click an upgrade / buy-credits / manage-subscription action. * **Terms:** https://stripe.com/legal/consumer — **Privacy:** https://stripe.com/ privacy ## Skjermbilete [⌊The dashboard: analysed pages, your entity registry, and a Content Network score for semantic cohesion.⌉⌊The dashboard: analysed pages, your entity registry, and a Content Network score for semantic cohesion.⌉[ The dashboard: analysed pages, your entity registry, and a Content Network score for semantic cohesion. [⌊Every page with its analysis status and topic — analyse or review in one click.⌉⌊ Every page with its analysis status and topic — analyse or review in one click.⌉[ Every page with its analysis status and topic — analyse or review in one click. [⌊Review and approve every extracted entity, each backed by the supporting quote from your content.⌉⌊Review and approve every extracted entity, each backed by the supporting quote from your content.⌉[ Review and approve every extracted entity, each backed by the supporting quote from your content. [⌊Schema.org / JSON-LD markup generated per page — you approve it before it goes live.⌉⌊Schema.org / JSON-LD markup generated per page — you approve it before it goes live.⌉[ Schema.org / JSON-LD markup generated per page — you approve it before it goes live. [⌊Question-and-answer pairs generated from your content, with on-page FAQ output.⌉⌊ Question-and-answer pairs generated from your content, with on-page FAQ output.⌉[ Question-and-answer pairs generated from your content, with on-page FAQ output. [⌊The structured data behind your public endpoints (llms.txt, Markdown copies, JSON- LD).⌉⌊The structured data behind your public endpoints (llms.txt, Markdown copies, JSON-LD).⌉[ The structured data behind your public endpoints (llms.txt, Markdown copies, JSON- LD). [⌊Your site-wide entity registry — types, occurrence counts, synonyms and Wikidata IDs.⌉⌊Your site-wide entity registry — types, occurrence counts, synonyms and Wikidata IDs.⌉[ Your site-wide entity registry — types, occurrence counts, synonyms and Wikidata IDs. [⌊Drill into any entity: canonical label, definition, synonyms and every page it appears on.⌉⌊Drill into any entity: canonical label, definition, synonyms and every page it appears on.⌉[ Drill into any entity: canonical label, definition, synonyms and every page it appears on. [⌊Topic clusters, grouped automatically by the entities your pages share.⌉⌊Topic clusters, grouped automatically by the entities your pages share.⌉[ Topic clusters, grouped automatically by the entities your pages share. [⌊The shared-entity graph — see how your pages connect and where internal-linking gaps are.⌉⌊The shared-entity graph — see how your pages connect and where internal- linking gaps are.⌉[ The shared-entity graph — see how your pages connect and where internal-linking gaps are. ## Installasjon 1. Upload the plugin to `/wp-content/plugins/ai-data-layer`, or install it from the Plugins screen. 2. Activate the plugin. 3. Open **AI Data Layer** in the admin menu and either activate the free trial or paste your licence key. 4. Review and approve the extracted entities, schema and FAQs for each post, then click **Apply to Site**. 5. Verify your AI endpoints: visit `/llms.txt`, view a page’s source for JSON-LD, or open `/wp-json/ai/v1/`. ## Vanlege spm. ### What is llms.txt? llms.txt is an emerging standard (llmstxt.org) — think robots.txt, but for AI. It gives AI crawlers a machine-readable index of your site and where to find clean, token-efficient copies of your content. AI Data Layer generates `/llms.txt` automatically, plus a whole-site `/llms-full.txt` and per-page Markdown versions. ### What is an MCP server? The Model Context Protocol (MCP) is an open standard for connecting AI assistants to data and tools. AI Data Layer runs a per-site MCP server so connected assistants( such as Claude) can query your content and entities directly — a live, queryable AI layer rather than static files. ### What is AEO / GEO / AI search optimization? Answer Engine Optimization (AEO) and Generative Engine Optimization (GEO) are the next step after SEO: instead of optimising for ranked blue links, you make your content readable, verifiable and citable by AI answer engines like ChatGPT, Perplexity and Google AI Overviews. AI Data Layer provides the structured, Wikidata-verified foundation those systems rely on. ### How is this different from other llms.txt or schema plugins? Most plugins output template schema and a static llms.txt file. AI Data Layer extracts the actual entities your content is about, verifies them against Wikidata, and stores them in a persistent, queryable graph — then publishes that graph as JSON-LD schema, llms.txt, Markdown, canonical entity pages, a REST API and an MCP server. The verified entity layer underneath is the difference. ### Does this work without an account? A licence key is required because analysis runs in the cloud. You can activate a free trial (10 analyses) in one click, with no card. ### Is my content sent to a third party? Yes — analysing a post sends that post’s content to the AI Data Layer cloud service, which uses a large language model to extract structured data. See the «External services» section for full details. Nothing is sent until you analyse a post (or enable auto-analyse). ### Does it handle my payment card? No. Billing is handled entirely by Stripe’s hosted checkout and customer portal; the plugin never sees or stores card details. ### Is it compatible with my SEO plugin? Yes. When an SEO plugin (Yoast, Rank Math, AIOSEO, SEOPress, The SEO Framework) is detected, AI Data Layer emits only its unique schema nodes and defers page/breadcrumb schema to your SEO plugin. You can change this in Settings. ## Omtalar There are no reviews for this plugin. ## Bidragsytarar og utviklarar “AI Data Layer – AI SEO & AI Search Optimization: llms.txt, MCP Server, Schema ( AEO/GEO)” is open source software. The following people have contributed to this plugin. Contributors * [ aidatalayer ](https://profiles.wordpress.org/citemysite/) [Omset “AI Data Layer – AI SEO & AI Search Optimization: llms.txt, MCP Server, Schema (AEO/GEO)” til ditt eige språk.](https://translate.wordpress.org/projects/wp-plugins/ai-data-layer) ### Interested in development? [Les kjeldekoden](https://plugins.trac.wordpress.org/browser/ai-data-layer/), sjekk [SVN-lageret](https://plugins.svn.wordpress.org/ai-data-layer/) eller abonner på [utviklingsloggen](https://plugins.trac.wordpress.org/log/ai-data-layer/) med [RSS](https://plugins.trac.wordpress.org/log/ai-data-layer/?limit=100&mode=stop_on_copy&format=rss). ## Endringslogg #### 1.13.0 * New **Entity Profile** tab — a visual map of how the open web identifies your organisation (your `sameAs` identity links), with a recognition-readiness panel and tailored, business-type-aware suggestions for the highest-impact gaps to close. * Add an identity link straight from the profile: it writes to your Organization schema and AI endpoints in one click. #### 1.12.0 * «Analyse All» now queues content in the background, so large sites no longer time out, with a live progress bar on the Content screen showing how many pages remain. * Cleaner entity graph: relationship edges that pointed to entities not in your registry are no longer shown, so the Topic Clusters and network views render without broken connections. * «Analyse All» now only queues as many pages as your remaining quota allows and tells you how many need more credits, instead of queuing pages that would fail. #### 1.11.2 First public release. * AI content analysis — extracts entities, relationships, summaries and FAQs from your posts and pages. * A site-wide entity graph, with entities verified against Wikidata. * JSON-LD schema output (Article / HowTo / FAQ, plus entity about[] with sameAs). * Canonical entity pages at /entities/{id}, listed in your sitemap. * An /llms.txt index and AI-optimised Markdown copies of your content (per-page. md and a whole-site /llms-full.txt). * A public read-only REST API and a per-site Model Context Protocol (MCP) server. * Topic clusters, a semantic cohesion score, and plain-English recommendations. * Review-and-approve workflow — you approve every suggestion before it is published. * Compatible with major SEO plugins (defers duplicate schema automatically). ## Om * Version **1.13.0** * Last updated **1 dag sidan** * Active installations **Færre enn 10** * WordPress version ** 6.0 eller nyare ** * Tested up to **7.0** * PHP version ** 7.4 eller nyare ** * Language * [English (US)](https://wordpress.org/plugins/ai-data-layer/) * Tags * [aeo](https://nn.wordpress.org/plugins/tags/aeo/)[ai seo](https://nn.wordpress.org/plugins/tags/ai-seo/) [llms.txt](https://nn.wordpress.org/plugins/tags/llms-txt/)[mcp](https://nn.wordpress.org/plugins/tags/mcp/) [schema](https://nn.wordpress.org/plugins/tags/schema/) * [Avansert vising](https://nn.wordpress.org/plugins/ai-data-layer/advanced/) ## Vurderingar No reviews have been submitted yet. [Your review](https://wordpress.org/support/plugin/ai-data-layer/reviews/#new-post) [See all reviews](https://wordpress.org/support/plugin/ai-data-layer/reviews/) ## Contributors * [ aidatalayer ](https://profiles.wordpress.org/citemysite/) ## Hjelp Har du noko å seia? Treng du hjelp? [Sjå hjelpeforumet](https://wordpress.org/support/plugin/ai-data-layer/)