外掛標籤
開發者團隊
② 後台搜尋「AI Data Layer – AI SEO & AI Search Optimization: llms.txt, MCP Server, Schema (AEO/GEO)」→ 直接安裝（推薦）
原文外掛簡介
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 (
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:
AI Data Layer cloud service (operated by the plugin author; hosted on Supabase).
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
OpenRouter / large language model (used by the cloud service to perform extraction).
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
Wikidata (used by the cloud service to verify entities).
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
Stripe (payments).
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
