Enable Abilities for MCP vs Smart Local AI – Browser-Based Private AI Tools

Enable Abilities for MCP gives you full control over which WordPress Abilities are available to AI assistants through the MCP (Model Context Protocol) Adapter. WordPress 6.9 introduced the Abilities API, allowing external tools to discover and execute actions on your site. This plugin extends that functionality by registering a comprehensive set of content management abilities and providing a simple admin interface to toggle each one on or off. Connect from claude.ai with just a URL Since version 2.1 the plugin ships an embedded OAuth 2.1 server built for claude.ai custom connectors. Add your site in claude.ai → Settings → Connectors, log in with your WordPress user, approve the consent screen — connected. No Client ID, no Application Password, no local configuration. Works from the claude.ai web app, mobile apps, and Claude Desktop Each team member authenticates with their own WordPress account and role — a subscriber can never do what only an editor should Every ability execution lands in the activity log under the real user’s name Works on single sites, subdirectory installs, and multisite networks (network-activate so the main site serves the OAuth discovery documents for every subsite) Prefer tokens? Application Passwords (per-user) and a single-admin Bearer token connect Claude Desktop / Claude Code, OpenAI Codex CLI, and Google Antigravity — the Connection tab generates ready-to-paste configuration for each client, and fills in your credentials automatically. Features 91 abilities organized in 18 categories: Core, Read, Write, SEO (Rank Math), SEO (SEOPress), SEO (Yoast), Navigation Menus, Utility, Multilanguage, Custom Post Types, WooCommerce, The Events Calendar, Code Snippets, JetEngine Options Pages, Elementor, LearnDash, Tutor LMS, and AI Agent Readiness (llms.txt) WooCommerce integration — dedicated abilities to manage products, orders, and customers using the native WooCommerce API (HPOS-compatible, formally declared) The Events Calendar integration — list, get, create, and update events with venue, organizer, and date filters claude.ai OAuth custom connector — connect from claude.ai (web, mobile, or desktop) with zero local setup: an embedded OAuth 2.1 server with Client ID Metadata Document (CIMD) support lets each user log in with their own WordPress account and role Admin dashboard with toggle switches for each ability Per-ability control — expose only what you need Third-party ability control — abilities registered by other MCP-ready plugins (e.g. Fluent Forms) appear in the same dashboard, grouped by plugin, with the same per-ability toggles; disabling one removes it from every MCP server on the site Secure by design — proper capability checks, input sanitization, and per-post permission validation WPCS compliant — fully passes WordPress Coding Standards (phpcs) MCP-ready — all abilities include show_in_rest and mcp.public metadata Available Abilities Read (safe, query-only): Get posts with filters (status, category, tag, search) Get single post details (content, SEO meta, featured image) Get categories, tags, pages, comments, media, and users Write (create & modify): Create, update, and delete posts Create categories and tags Create pages Moderate comments Reply to comments as the authenticated user Upload images from external URLs to the media library (with optional auto-assign as featured image) Duplicate any post, page, or custom post type item — including all post meta (ACF, SEO, featured image) and taxonomy terms; saved as a draft by default SEO — Rank Math: Get full Rank Math metadata for any post/page (title, description, keywords, robots, Open Graph, SEO score) Update Rank Math metadata: SEO title, description, focus keyword, canonical URL, robots, Open Graph, primary category, pillar content SEO — SEOPress: Get full SEOPress metadata for any post/page (title, description, focus keyword, robots, canonical, Open Graph, Twitter Card) Update SEOPress metadata: SEO title, description, focus keyword, canonical URL, robots directives, Open Graph, Twitter Card SEO — Yoast SEO: Get full Yoast SEO metadata for any post/page (title, description, focus keyphrase, canonical, robots, Open Graph, Twitter Card) Update Yoast SEO metadata: SEO title, description, focus keyphrase, canonical URL, robots (noindex, nofollow, advanced), Open Graph, Twitter Card Get Yoast sitemap index — fetch and parse the sitemap index, returning all registered sitemap URLs with last modification date Custom Post Types: List all registered custom post types with configuration and taxonomies Get items from any CPT with filtering, search, and taxonomy queries Get full details of a CPT item including all meta fields (WooCommerce, ACF, JetEngine, etc.) Create, update, and delete CPT items with taxonomy and meta field support Get CPT taxonomies with their terms Assign taxonomy terms to CPT items WooCommerce: List products with price, SKU, stock status, categories, and type Get full product detail including gallery, attributes, and variations Update product price, sale price, stock quantity, and status List orders with customer, total, status, and date (HPOS-compatible) Get full order detail: line items, billing/shipping, totals, and notes Update order status with optional note List customers with email, name, total spent, and order count The Events Calendar: List events with start/end date, venue, organizer, and date range filter Get full event detail with resolved venue address and organizer contact Create new events with title, description, dates, venue, and organizer Update existing events Navigation Menus: List menus with item counts and theme locations, and get one menu’s full item hierarchy Create a new menu, and add pages, posts, categories, tags, or custom URLs as items (with parent and position) Update an item’s title, URL, parent, or position Remove an item, assign a menu to a theme location, or delete a menu entirely (opt-in — destructive) Tutor LMS: Read a lesson’s video source configuration (type, value, and runtime) Set a lesson’s video source (external URL, YouTube, Vimeo, HTML5, or a third-party source such as Bunny.net) using Tutor’s own storage function — avoids the string-only limitation of the generic Update Post Meta ability, which Tutor cannot read back List courses, and get a single course’s full detail with its topics/lessons hierarchy Get a user’s enrollment status and completion progress for a course Get a user’s quiz attempt results, optionally filtered to a single quiz Enroll a user in a course, and unenroll them (both opt-in, manage_options only) Utility: Search and replace text in post content Site statistics overview (includes custom post type counts) Update any post meta field by exact key (with protected internal key blocklist) Requirements WordPress 6.9 or later (Abilities API) MCP Adapter plugin installed and configured PHP 8.0 or later

Smart Local AI brings machine learning directly to the browser. Every ML model runs on-device in the visitor’s or editor’s browser using Transformers.js and WebGPU/WASM. No data is ever sent to external servers, no cloud API keys are needed, and there are zero recurring costs. Modules RelevantFlow — Semantic Content Recommendations Traditional related-posts plugins match by shared tags or categories. RelevantFlow uses a sentence-transformer model (all-MiniLM-L6-v2) to understand the meaning of your content and recommend posts that are genuinely related — even when they share no tags at all. Understands synonyms and concepts (e.g. “Salah” and “Islamic Prayer” match) Works with any content type — Posts, Pages, WooCommerce Products, or custom post types Displays a responsive card widget below your content Three layout templates: cards, list, and grid Custom placement via CSS selector or shortcode [atlas_ai_relevantflow] Theme customization with presets (Default, Light, Dark, Minimal) and custom colors Embedding index built in-browser by editors — zero server load Nightly cron flags new/updated content for re-indexing PersonaFlow — Personalized Content Recommendations PersonaFlow delivers personalized content recommendations based on visitor behavior — like Netflix for your WordPress site. It tracks 30 behavioral signals (scroll depth, reading time, click patterns, etc.) and computes a per-visitor taste vector to surface the most relevant content for each individual visitor. Personalized recommendations powered by real-time behavioral tracking 30 behavioral signals including scroll depth, reading time, and engagement patterns Per-visitor taste profile computed entirely in the browser — no server-side tracking WooCommerce integration for product recommendations Three layout templates: cards, list, and grid Custom placement via CSS selector or shortcode [atlas_ai_personaflow] Theme customization with presets and custom colors All tracking data stays on the visitor’s device — fully GDPR compliant Automatic taste decay ensures recommendations stay fresh and relevant AltGenius — Automatic Alt Text Generation Missing alt text hurts SEO rankings and violates ADA/WCAG accessibility guidelines. AltGenius generates descriptive alt text for every image in your media library — entirely in the browser. Two AI models: ViT-GPT2 (fast) and Florence-2 (detailed) Bulk Scan to audit and fix your entire media library at once Auto-generate on media upload Editor sidebar panel for per-image control with prefix/suffix No per-image fees, no cloud processing Key Features Zero Cost — No API keys, no subscriptions, no per-request fees Privacy by Architecture — All ML inference runs in the browser; data never leaves the device GDPR Compliant — No external data transmission means no DPA required Shared Hosting Compatible — No server-side ML dependencies; works anywhere WordPress runs WebGPU + WASM — Hardware-accelerated inference with automatic fallback Modular — Enable only the modules you need; each can work standalone Cached Models — ML models are cached in IndexedDB after first download for instant reuse Themeable — Built-in theme presets and custom color options to match any WordPress theme Upgrade to Pro Get more powerful AI modules and premium features with Smart Local AI Pro. Have questions or need support? Contact us. How It Works All AI processing runs in your browser. No server-side ML is required. On first use, models are downloaded from Hugging Face and cached in the browser’s IndexedDB — this one-time download may take 1–2 minutes depending on your connection. After that, models load instantly. RelevantFlow (Related Posts) Go to Smart Local AI > Dashboard and enable the RelevantFlow module (or follow the setup wizard after activation) Select which content type to index from the Content Type selector on the Dashboard (defaults to Posts) Go to the RelevantFlow tab and click Build Index — this downloads the MiniLM model (~23 MB) and generates an embedding for each published item of the selected content type You need at least 2 published items of the selected content type for recommendations to appear Visit any item on the frontend — a “You Might Also Enjoy” section will appear below the content showing semantically related items PersonaFlow (Personalized Recommendations) Go to Smart Local AI > Dashboard and enable the PersonaFlow module Go to the PersonaFlow tab to configure display settings (number of recommendations, layout template, appearance) Visit posts on the frontend — PersonaFlow will track reading behavior and build a taste profile After a few page views, personalized recommendations will appear below the content based on the visitor’s interests Use the shortcode [atlas_ai_personaflow] to place recommendations anywhere in your theme AltGenius (Image Alt Text) Go to Smart Local AI > Dashboard and enable the AltGenius module Upload an image via Media > Add New Media File — the model downloads on first use (~300 MB for ViT-GPT2) and alt text is generated automatically Or go to Smart Local AI > Bulk Alt Text and click Start Bulk Scan to generate alt text for all existing images missing it Or edit any post with images in the Block Editor — the AltGenius sidebar panel shows each image with a Generate Alt Text button External Services This plugin connects to the following external services. No user data or site content is transmitted to these services — only the ML model files are downloaded. Hugging Face Model Hub ML models are downloaded from the Hugging Face Model Hub (https://huggingface.co/) on first use and cached in the browser’s IndexedDB. The following models are used: RelevantFlow: Xenova/all-MiniLM-L6-v2 (~23 MB) — Sentence transformer for content embeddings AltGenius (ViT-GPT2): Xenova/vit-gpt2-image-captioning (~300 MB) — Image captioning model AltGenius (Florence-2): onnx-community/Florence-2-base-ft (~460 MB) — Advanced image captioning model These models are open-source and licensed under Apache 2.0 or MIT. No user content, images, or site data is uploaded to Hugging Face — the connection is download-only. Hugging Face Terms of Service Hugging Face Privacy Policy