AICOM – AI Commander
AICOM – AI Commander connects your WordPress site to any AI agent via MCP (Model Context Protocol) or OpenAPI. Use your existing AI subscription — Claude Code, OpenAI Codex, ChatGPT Custom GPTs, Copilot Studio, Dify, n8n, OpenClaw, Celine, Goose, or any MCP-compatible client — to manage content, build pages, run audits, and automate repetitive tasks, all without leaving your AI interface. No more copy-pasting between your AI assistant and the WordPress dashboard. Describe what you want, and your agent does it — safely, with a full record of every action. Content Management Create, update, and publish posts, pages, and custom post types directly from your AI agent. Build and duplicate Elementor pages, manage menus, upload media, update taxonomies, translate content with Polylang or WPML, and handle bulk SEO fields — titles, meta descriptions, robots directives, social previews — with Yoast SEO or SEOPress, whichever is active on your site. All in a single conversation. What used to take hours of dashboard work can be delegated to your AI in minutes. Safety You Control AICOM puts you in charge at every level: Scope-based API keys — each key grants access only to the operations you explicitly allow. One key for read-only content review, another for full publishing access. Soft Lock / Hard Lock — freeze all write operations (Soft) or block everything except public tools (Hard) with one click from the admin bar or Safety page. Working Hours Schedule — automatically apply Soft or Hard Lock outside your configured working hours and days. Agents can’t make changes at night or on weekends unless you explicitly override it. Dry-run mode — test any operation before it runs. See exactly what would change without touching live data. Confirm flag — destructive operations require an explicit "confirm": true parameter. Accidental deletions are prevented by design. Backup & Restore AICOM automatically snapshots a post, term, or Elementor page/template right before your agent updates, trashes, deletes, or edits it — no extra step required, even if the agent never calls a backup tool itself. If something goes wrong, restore the exact previous version in one call, or undo an entire session at once: the Snapshots page lists every session that touched content, with a one-click Restore session button that reverts every post, term, and Elementor page it modified — including Elementor Theme Builder display conditions. Backups are stored in the database and can be cleaned up automatically based on age or total size. Full Audit Trail Every request is logged: timestamp, remote IP, API key label, tool used, parameters, result, and response time. Logs are grouped into named sessions — when an agent opens a session, all its actions are recorded together so you can review, replay, or undo an entire workflow at once. The Audit Logs page includes a session activity chart and a direct Restore button for each session. Built for Reliable Automation AICOM speaks strict MCP JSON-RPC: every successful call returns a content field for full client compatibility, protocol errors use standard integer codes, and errors from a tool that actually ran are reported as isError so your agent can see and react to them. Pass an idempotency_key on any write call and a retried request (dropped connection, flaky client) returns the original result instead of repeating the action — no duplicate posts from an accidental double-send. Responses are hardened against corrupted output, so your agent always gets valid JSON back. Works Well With Small & Local Models Not every AI agent is Claude or GPT-4 class. AICOM is built to stay usable even for smaller, local, or context-constrained models: tools/search — keyword search over tool names and descriptions, tuned for models that don’t know exact tool names: handles full-sentence queries (“how do I add a photo to my page”), common synonyms (shop → WooCommerce, translate → Polylang/WPML), typo tolerance, and plurals. tools/describe — fetch one tool’s full parameter schema by exact name, on demand — pairs with tools/search so a model never has to load the entire tool catalog just to find what it needs. Compact Tool List (per API key) — an optional setting that strips parameter descriptions from tools/list to cut context size by roughly a third, while always keeping every parameter’s name, type, and whether it’s required — a model can still build a correct call without the extra explanatory text. Off by default; capable models see the full list as before. Scoped discovery — tools/list only ever shows the tools a key can actually call. A key without WooCommerce access never sees WooCommerce tools, so a smaller model isn’t wading through options it’s not allowed to use anyway. Reusable Skills Let your agent turn a workflow it just performed into a saved, reusable recipe. After finishing a session, AICOM can suggest saving what was done — the exact sequence of tool calls, rules, and expected inputs — as a named Skill. Next time a similar task comes up, the agent fetches the Skill and follows it, instead of re-figuring out the same multi-step process from scratch. Skills are versioned (every edit keeps a full revision history), matched by similarity before creating a duplicate, and scoped like any other capability — a key needs manage.skills to create or edit one. Accessibility Audits — New in v3.2.0 AICOM now includes a dedicated Accessibility module so your AI agent can audit and fix WCAG issues across your entire site — no external tools or services required: Site report — instantly see how many images are missing alt text across your entire media library, with a ranked preview of the top offenders and a percentage score. Post audit — scan any post or page for heading hierarchy errors (missing H1, skipped heading levels), images without alt text, and links with non-descriptive anchor text (“click here”, “read more”). Each issue is rated by severity and the post receives an overall accessibility score from 0 to 100. Fix in place — set alt text on any media library image in one call. Pass an empty string to correctly mark it as decorative (aria-hidden). Full dry-run support so you can preview changes before saving. Screenshot before & after — combine AICOM’s audit tools with your AI agent’s browser capabilities to capture a visual record of the page before and after remediation. A typical AI-driven accessibility workflow: run the site report, get the list of problem images, let the agent analyse each image visually and write descriptive alt text, apply the fixes — then run the audit again to confirm the score improved. All in one session, with a full audit trail. Supported Modules WordPress Core — posts, pages, custom post types, terms, meta, options, menus, plugins Media — upload, update, delete media; direct file system access Users & Roles — create, update, manage users and role assignments Backup — automatic snapshots for posts, terms, and Elementor pages/templates before every write; session-wide restore Sessions — named audit sessions with grouped action history Accessibility — site-wide alt text audit, post-level WCAG check, alt text fixes WooCommerce (optional) — products, categories, settings Elementor (optional) — page creation from template, widget inspection, theme builder conditions Polylang (optional) — translations, language assignment, string management, and one-call bilingual post pair creation WPML (optional) — translation language assignment and translation-group linking for posts and taxonomy terms Yoast SEO (optional) — read and write SEO titles, meta descriptions, Open Graph and Twitter card fields; bulk audit across all posts in one session SEOPress (optional) — read and write SEO titles, meta descriptions, robots directives, canonical URLs, Open Graph and Twitter card fields; bulk audit across all posts in one session Skills (optional) — save, version, and run reusable multi-step workflows Clautron (optional) — blueprint management, capability catalog, event analytics ECS (optional) — Ele Custom Skin color schemes, font schemes, custom looks Who is this for? Content teams using Claude, ChatGPT, or any AI assistant who want it to publish and update WordPress content directly Agencies managing multiple client sites and wanting AI-assisted workflows with a full paper trail Developers building AI-powered WordPress tools or automation pipelines Accessibility specialists who want to audit and remediate WCAG issues at scale with AI assistance Claude Code users — point AICOM as an MCP server from your terminal and control WordPress alongside your code OpenAI Codex users — connect Codex to your site via AICOM’s MCP endpoint and let it manage content as part of your dev workflow ChatGPT, Copilot Studio, Dify, n8n users — import the OpenAPI schema URL into any OpenAPI-compatible client; all tools are discovered automatically with Bearer auth OpenClaw / Celine / Goose users — native MCP connector, works out of the box How it works AICOM exposes a secure HTTP endpoint on your WordPress site. Your AI agent sends structured MCP requests, AICOM authenticates the request, checks scopes and lock state, executes the operation, logs it, and returns a structured response. AI Agent → AICOM Endpoint → WordPress API Key Scopes Each API key is granted specific scopes — you control exactly what each AI agent can and cannot do. Dozens of granular scopes are available, grouped by area: read.wp, `write.wp.posts`, `delete.wp.posts`, `manage.taxonomies`, `manage.meta`, `manage.media`, `manage.files`, `manage.wordpress.settings`, `manage.plugins`, `manage.backups`, `manage.a11y`, `manage.users`, `manage.roles`, `manage.skills`, plus one `read.*`/`manage.*` pair per optional integration (WooCommerce, Elementor, Polylang, WPML, Yoast, SEOPress, Clautron). Built-in presets (Content Assistant, Translator, SEO Editor, Site Maintenance, Full Admin, and more) bundle the right scopes for a common role in one click — see the full list and descriptions on the **API Keys** page. Endpoint REST API: POST /wp-json/aicom/v1/mcp Fallback (no mod_rewrite required): POST /?aicom=1 Health check: GET /?aicom=1 Authentication Authorization: Bearer aicom_XXXXXXXX_ or: X-API-Key: aicom_XXXXXXXX_ MCP Request Example {"jsonrpc":"2.0","method":"tools/call","params":{"name":"wp.posts.list","arguments":{"post_type":"post","posts_per_page":10}},"id":1}
StrifeBridge MCP
StrifeBridge MCP turns your WordPress site into an MCP (Model Context Protocol) endpoint that AI assistants like Claude can connect to directly. Instead of describing a change to an AI and then applying it yourself, you ask and it happens. Want to add a blog post? Ask Claude. Need to update a menu item? Ask Claude. Wondering which pages are missing SEO metadata? Ask Claude to check and fix them. StrifeBridge MCP exposes a structured, authenticated REST API and MCP server inside your WordPress install. AI assistants that support MCP (ChatGPT, Claude.ai, Claude Desktop, Gemini, Cursor, Windsurf, and any MCP-capable agent framework) can connect to it and perform tasks across your site through natural language. Connections use OAuth 2.1 and act as a real WordPress account, so an assistant is held to that account’s permissions. What you can do Create, update, and delete posts, pages, and custom post types Upload files to the media library and manage attachments Read and write WordPress options, with a security blacklist for sensitive keys Manage navigation menus, taxonomy terms, and widgets List, activate, deactivate, and delete plugins List users and inspect their roles Get site info, flush rewrite rules See and control what the AI does Every tool call is recorded in an activity log — what ran, whether it worked, and where the request came from, including refused calls and failed sign-in attempts. The Settings screen shows recent activity at a glance. Safe Mode adds guardrails on top of the per-tool-group toggles: Never publish — new posts stay drafts, and updates cannot publish them Trash instead of delete — deletions stay recoverable Read-only mode — the AI can look but not touch How it works Install and activate the plugin Go to Settings and copy your Server URL Paste it into your AI assistant as a custom MCP connector The assistant sends you back to WordPress to sign in and approve the connection Ask the assistant to do things on your site No middleware, no third-party relay service. Every request goes from your AI assistant directly to your own WordPress site. You own the endpoint, you own the token, and you can revoke access at any time from Settings. Compatible with ChatGPT — via OAuth Google Gemini — via OAuth Claude.ai (web and desktop), and Claude Code Cursor Windsurf Any MCP-capable agent framework ChatGPT and Gemini require OAuth, which arrived in version 3.0.0. The others accept either OAuth or the legacy token. Security StrifeBridge MCP was designed with security as a first-class concern: OAuth 2.1 with mandatory PKCE (S256 only; the plain method is refused), single-use 60-second authorization codes, exact-match redirect URIs, and rotating refresh tokens Tokens, authorization codes, and client secrets are stored only as hashes and compared in constant time with hash_equals() Every connection is bound to a WordPress account and subject to that account’s capabilities, and can be revoked individually from Settings WordPress secret keys, auth salts, and the plugin’s own token are blacklisted from the options API Emergency Lockdown button in Settings disables the entire API with one click Every tool group (posts, media, menus, etc.) can be individually toggled off from Settings The plugin includes no outbound network calls, no analytics, and no tracking Compatibility with self-hosted WordPress StrifeBridge MCP works on any self-hosted WordPress installation running WordPress 5.6 or higher. WordPress.com and WordPress Multisite are not currently supported. Extending StrifeBridge MCP StrifeBridge MCP exposes extension hooks that let add-on plugins register additional MCP tools without modifying the core plugin. Developers can hook into sbmcp_register_rest_routes, sbmcp_mcp_tools, sbmcp_mcp_tool_call, sbmcp_tool_groups, and sbmcp_admin_after_settings to add routes, tools, admin UI, and tool groups. This is how separately distributed add-ons extend the plugin with features like file editing, database queries, and user management. Privacy StrifeBridge MCP keeps an activity log in your own WordPress database, in a table named {prefix}sbmcp_audit_log. Each entry records the time of the request, the name of the tool that ran, a short sanitized summary of what it acted on, whether the call succeeded, failed, or was refused, and — unless you turn it off — the IP address the request came from. Nothing leaves your site. The log is local to your database. The plugin makes no outbound network calls and sends no analytics or telemetry anywhere. No content or secrets are stored. Argument summaries are allowlisted per tool, so option values, post content, widget settings, uploaded file data, and API tokens are never written to the log. A tool the plugin does not recognize records no arguments at all. IP logging is optional. “Log IP addresses” under Settings → StrifeBridge MCP → Safety is on by default and can be switched off, after which new entries store no address. Entries already recorded keep the addresses they were written with; deleting those is a matter of waiting for them to be pruned, or clearing the table. Entries are pruned automatically. A daily scheduled task keeps the free version to a rolling window of 30 days or 1000 entries, whichever comes first. Older entries are deleted permanently. Everything is removed on uninstall. Deleting the plugin through the WordPress admin drops the log table and removes every option the plugin created. Deactivating alone leaves the log in place, so it survives a temporary deactivation. If your site is subject to GDPR or similar regulation, note that IP addresses are personal data. Either switch IP logging off, or account for this log in your own privacy policy and retention practices.
