Skip to content
Docs

WordPress and WooCommerce

The RankX AI MCP tools that edit a connected WordPress site or WooCommerce store, the scopes they need, and the safety rules every edit follows.

These tools let an assistant read and edit a connected WordPress site or WooCommerce store through RankX AI: posts, pages, blocks, SEO titles and meta descriptions, structured data, redirects, media, terms and products. They change a live, public website, so every edit dry-runs first or acts only on what a person has approved, every write is verified by reading it back, and a write that cannot be done safely is refused.

The Shopify tools follow the same rules. The one difference: WordPress keeps revisions, while Shopify keeps none, so on Shopify RankX AI records the previous value itself.

ToolScopeWhat it does
get_publication_statusreadWhere a Content Studio article stands on its website after publish_content_item, with each field (body, SEO title, meta description, schema, featured image, categories and tags, author, slug) reported as verified, written, not writable, failed or skipped.
publish_content_itempublishSends an approved Content Studio article to the connected WordPress site as a draft, scheduled for later or live now, and verifies it by reading the post back. It changes a real public website, spends no credits and refuses an article nobody has approved.
wp_advanced_requestsite_adminSends one specific REST request to a connected WordPress site, for anything the other tools do not cover. Available on every connected WordPress site; WooCommerce customer, order, subscription and checkout routes answer only where an administrator has switched on store customer and order data. Its result cannot be verified afterwards, which is why it dry runs first.
wp_bulk_updatepublishApplies one change across an explicit list of ids. The live call is refused unless it carries the batch id the dry run returned for exactly that list.
wp_create_contentpublishPublishes a new post or page. It creates a draft unless you explicitly ask to publish, and an idempotency key makes a retry return the original rather than creating a second post.
wp_create_productcommerceAdds a new product to a connected WooCommerce store, always as a draft. It cannot publish, so a human reviews the price and details in WooCommerce first.
wp_create_termpublishCreates one category, tag or custom taxonomy term. A name that already exists under different capitalisation is reported back rather than silently reused, and rename and delete deliberately do not exist.
wp_delete_contentpublishMoves a post or page to the trash, where it can be restored. There is no permanent delete and no flag that makes one.
wp_describe_sitepublishDescribes what a connected WordPress site actually supports: which content types are editable, which taxonomies exist, whether SEO fields are writable, and whether a page builder is in use. Call it first, because nothing about a WordPress site can be assumed.
wp_edit_blockspublishAdds, places or removes whole blocks on a page, which a text patch deliberately cannot do. Its outline action is free and lists every block with its id.
wp_get_contentpublishReads one post, page or custom object, including whether its body can be rewritten at all. A long body is truncated and says so, which matters because a whole-body write would delete the part you did not see.
wp_get_schemapublishReads the structured data on a WordPress page: which SEO plugin runs and where a new schema would go, every schema stored for the page, and every other JSON-LD node the live page prints, which is how duplicates show up.
wp_get_seo_coveragepublishChecks which SEO features a WordPress site actually outputs, read as a visitor would, from the title and meta description to structured data, the sitemap, robots.txt and llms.txt, and says for each whether it is printed, missing, partial or printed twice, and where it is fixed.
wp_list_contentpublishLists posts, pages or any custom content type. Every row reports whether its body can be rewritten, so page-builder pages are visible rather than discovered on a refusal.
wp_list_productscommerceLists WooCommerce products with prices, stock status and how much description each carries, flagging the ones too thin to sell or rank. Read only.
wp_list_redirectspublishShows which redirect manager a WordPress site uses, the redirects already there with their hit counts and, where the site keeps a 404 log, the missing addresses visitors actually hit.
wp_list_revisionspublishLists a post or page's WordPress revisions, which is what an edit can be rolled back to. Some content types have none, and it says so plainly.
wp_list_termspublishLists categories, tags and custom taxonomy terms. List before creating with wp_create_term: a term that already exists under different capitalisation is not found by name, and near-duplicate terms are hard for a customer to undo.
wp_manage_redirectpublishAdds or removes a redirect on a live WordPress site through its own redirect manager. It only redirects an address that is genuinely missing, to a page on the same site that loads directly, and it dry runs by default.
wp_mediapublishLists media library images, uploads a new one, or sets alt text, caption and title. Its missing-alt list comes from a bounded scan and always reports the scanned and total figures.
wp_patch_contentpublishChanges specific text inside an existing page without rewriting the rest of it. Preferred over a whole-body update: it is safe on long pages and far cheaper, and if any edit fails to match, nothing is written.
wp_site_adminsite_adminInspects a site's settings, menus, users, comments, widgets, templates, plugins and themes. Only site settings and comment moderation can be changed; plugins, themes and users are read only.
wp_update_contentpublishUpdates the title, body, excerpt, slug, categories, tags or featured image of an existing page. It replaces the whole body, so a small edit belongs in wp_patch_content instead.
wp_update_productcommerceRewrites a WooCommerce product's description and SEO fields. Price, stock, status and the product URL cannot be changed by this tool and are reported before and after so you can see they were not.
wp_update_schemapublishAdds, replaces or removes one schema on a WordPress page through the site's SEO plugin, never by editing the page body. It dry runs by default and refuses the write if the page's schema changed after wp_get_schema read it.
wp_update_seopublishSets the SEO title and meta description of a post or page. Many SEO plugins do not expose these fields at all, and it refuses rather than appearing to succeed.

The table above is generated from RankX AI itself rather than written by hand, as at 30 September 2026 (source b27dec96). When the product changes, this page changes with it.

A typical request to an assistant with these tools connected:

Describe my connected WordPress site, then list the pages with thin meta descriptions and dry run a fix for the worst five.

Call wp_describe_site first

A WordPress site exposes only what its plugins and the connected account allow, so nothing about it can be assumed. wp_describe_site reports which content types exist and are editable, which taxonomies exist, whether SEO fields are writable, whether WooCommerce is present, and whether a page builder is in use.

The other tools, and their refusals, make more sense with that answer in hand.

Scopes for the WordPress tools

Three scopes reach a WordPress site, and none of them is write:

ScopeReaches
publishContent, taxonomies, media, SEO metadata, structured data, redirects, revisions, bulk edits, and publishing Content Studio articles
commerceWooCommerce products
site_adminSite settings, comment moderation, and the advanced request tool

The reads need these scopes too. They use your stored WordPress credential against your own site, and one of them returns prices and stock for a whole catalogue, so a read credential cannot call them.

Scopes are fixed when a credential is issued. A credential created before these tools existed was granted to act inside RankX AI only, so these tools were given their own scopes rather than added to an existing one.

The five safety rules

1. Every edit dry-runs by default

An assistant must opt in to changing a live site. The dry run uses the same pipeline as the real write, so its warnings are the warnings the write will produce.

The one write here with no dry run is publish_content_item, and a person's decision stands in its place. It refuses an article nobody has approved, and it takes the action (draft, schedule or publish) as an explicit instruction.

2. Explicit ids only

No tool finds a target by title or fuzzy match, which is how the wrong live article gets edited. Get the id from wp_list_content or wp_list_products.

3. Page-builder pages are protected

Pages whose builder stores content outside the page body are listed as not writable and refuse a body write, with no override from MCP. A builder RankX AI does not recognise is treated the same way, so the guard holds for builders it has never seen.

4. Writes are verified by reading them back

RankX AI checks every write by reading the object back, never by a success response, because some plugins report success while saving nothing. The read-back bypasses the site's page cache, so a cached copy cannot hide a successful write.

5. Nothing you send is discarded

A body the converter cannot map to native blocks is kept verbatim in a raw HTML block and reported.

Choosing the right write tool

Prefer the smallest edit that does the job:

You want toUseNot
Change some text on an existing pagewp_patch_contentwp_update_content
Add, move or remove a whole blockwp_edit_blockswp_patch_content, which refuses
Replace an entire page bodywp_update_contentanything, if the page is long
Create a new post or pagewp_create_content
Change the same field on many pageswp_bulk_updatea loop of single writes

wp_patch_content is the default for editing an existing page. It changes exact text inside existing blocks and nothing else, so it is safe on a long page and far cheaper than resending the whole body. If any of its edits fails to match, nothing is written.

wp_update_content replaces the whole body. wp_get_content truncates a very long body and says so, and sending a truncated body back would delete the part you did not see. That is the most damaging mistake available here, and the tool warns about it in its own description.

wp_edit_blocks has a free outline action that lists every block with its id, index, depth and a text preview; call it before targeting a block. Prefer its structured block input over raw markup: it builds correct markup from a media id, URL and alt text, so the block is not flagged invalid in the editor.

wp_create_content creates a draft unless you explicitly ask to publish. Pass an idempotency key, and a retried call returns the original post instead of creating a second one.

Bulk edits

wp_bulk_update applies one change across an explicit list of ids. Its live call is refused unless it carries the batch id the dry run returned for exactly that list, so a changed list needs a new dry run.

It always returns per-item results. Report failures one by one rather than summarising the run as a success.

SEO titles and meta descriptions

wp_update_seo sets the SEO title and meta description of a post or page. On a site with the optional RankX AI plugin, it writes them through every major SEO plugin, All in One SEO included, and on a site with no SEO plugin at all.

Without the RankX AI plugin, it depends on the site's SEO plugin. Some expose these fields by default, some only per content type, some once a small registration is added, and All in One SEO keeps them in its own database tables, which only the RankX AI plugin reaches.

When a write is not possible, the tool names which case applies and, where a registration would fix it, returns the snippet with the site's own field names. wp_update_seo writes the SEO title and meta description only; Open Graph and Twitter fields are refused on every site.

Publishing a Content Studio article

publish_content_item sends an approved Content Studio article to the connected WordPress site: as a draft (saved on the site, not public), scheduled at least two minutes ahead, or published now. It spends no credits.

Approval comes first, as its own step: approve_content_item records the person's sign-off, and an unapproved article is refused with that as the remedy. The tool also refuses while the same article is already being published, and on a Website with several connected WordPress sites you name the one to use.

It returns at once and the work continues in the background. Poll get_publication_status until it settles. It reports each field (body, SEO title, meta description, schema, featured image, categories and tags, author, slug) as verified, written, not writable, failed or skipped, so pass those on rather than saying "published".

A state of unconfirmed means the write may have landed but could not be read back. Check the site, and do not publish again.

Structured data

wp_get_schema reports which SEO plugin runs, where a new schema would be stored, every schema already stored for a page, and every other JSON-LD node the live page prints, which is how duplicates show up.

wp_update_schema adds, replaces or removes one schema through that SEO plugin, never by editing the page body. It dry-runs by default, shows the before and after and any duplicate of the same type, and refuses the write if the page's schema changed after it was read.

Redirects

wp_list_redirects shows which redirect manager takes new redirects (the Redirection plugin, Rank Math, or the RankX AI plugin itself), or why none can and what fixes that. It also lists the redirects already there and, where the site keeps a 404 log, the missing addresses visitors actually hit.

wp_manage_redirect adds or removes one. It redirects only an address that is genuinely missing, because redirecting a page that still loads would hide it, and the destination must be on the same site and load directly: no chains, and not the homepage. It dry-runs by default, and a real run is confirmed by reading the redirect back and following the old address.

SEO coverage check

wp_get_seo_coverage reads a site's pages as a visitor would and reports, for the title, meta description, canonical, robots tag, Open Graph, the Twitter card, structured data, breadcrumbs, the XML sitemap, robots.txt and llms.txt, whether each is printed, missing, only on some pages or printed twice, and where it is fixed.

It works whatever SEO plugin the site runs, including ones RankX AI has no integration for, and it changes nothing.

Products

wp_list_products reports each WooCommerce product's price, stock status, storefront visibility and how much description it carries, and flags the ones too thin to sell or rank. wp_update_product rewrites descriptions and SEO fields only. wp_create_product adds a new product, always as a draft, so a person reviews the price and details in WooCommerce before it goes on sale.

Products have no revision history in WordPress, so a product edit cannot be rolled back from the site. wp_list_revisions reports plainly when a content type has none, so check it before proposing a change someone may want to undo.

What the WordPress tools never do

These limits are built into the tools, and no input changes them:

  • No user writes, and no application password creation.
  • No plugin or theme install, activation or update. wp_site_admin reads them only.
  • No redirect without a redirect manager it can read back. With none of the three installed, wp_manage_redirect refuses and wp_list_redirects names the fix.
  • No permanent deletion. wp_delete_content moves a post to the trash, and no flag changes that.
  • No price, stock, status or slug change on a product. wp_update_product has no input for any of them, and reports the price before and after.
  • No product publishing. wp_create_product always creates a draft.
  • No order, customer or refund writes.

The advanced request tool

wp_advanced_request sends one REST request to a connected WordPress site, for a plugin's own endpoints that no named tool covers. It is available on every connected site and needs the site_admin scope.

WooCommerce customer, order, subscription and checkout routes answer only where an administrator has switched on store customer and order data for that connection. Some routes stay blocked whatever the settings: creating application passwords, permanent deletion, plugin and theme changes, user changes, refunds, changing the site address, bulk endpoints, and a query that tries to change the route or method.

The meaning of an arbitrary route is not known, so a read-back cannot confirm the result. Instead, it is checked before it runs: it dry-runs, shows the exact request, and the person decides.

Example prompts

Change the phrase 'AI monitoring' to 'AI visibility tracking' on page 412. Dry run first.

Show me the block outline of page 88, then insert an image after the second heading using media id 3391 with alt text describing the dashboard.

Which of my media library images have no alt text? Report the scanned and total figures with the count.

Which 404s are visitors hitting most? Dry run a redirect for the top one to the page that replaced it.

Approve content item X, then publish it to my site as a draft and tell me which fields were verified.

List WooCommerce products whose description is too thin, and rewrite the top three. Confirm the prices did not change.

Where to go next

Questions

Do I need the RankX AI WordPress plugin to use these tools?

No. The tools work through the WordPress connection you set up in RankX AI. The optional RankX AI plugin widens what they can write, such as SEO fields on sites whose SEO plugin does not expose them, and gives redirects a home on sites with no redirect plugin.

Can an assistant delete pages or change product prices?

No. wp_delete_content only moves a post or page to the trash, where it can be restored, and wp_update_product has no input for price, stock, status or the product URL.

How do I undo an edit made through these tools?

Posts and pages keep WordPress revisions, which wp_list_revisions lists. WooCommerce products have no revision history in WordPress, so check before changing one; the dry run shows the exact change first.

Last updated

Cookie settings

Choose which cookies we can use. You can change this at any time from “Cookie settings” in the footer.

Essential

Security, bot protection and remembering your choice. The site needs them to run, and they do not identify you. Always on.

Google Analytics cookies that tell us which pages are read and which links are followed, so we can improve them. Off until you switch it on.

Tells advertisers when their advert led to your visit. Includes the Meta (Facebook) pixel and the LinkedIn Insight Tag, which set cookies on this domain (LinkedIn also on linkedin.com) and can be told if you later start a trial.

More in the cookie policy and the privacy policy.