Git-native content governance for AI agents — 27 deterministic MCP tools over stdio and HTTP.
Nothing to run from here
WordPress Headless is installed from its publisher's own source and answers where it runs, so this marketplace is not in the path of a single call. There is no address here to send one to, and a panel that pretended otherwise would be showing you an answer we made up. Install it and call it from your own client — the Installation tab has the entry for each one.
96/100
trust score
22
tools declared
local
runs on your machine
—
downloads a day
What it does
Read WordPress content, ACF fields, and Yoast SEO data, and safely edit drafts.
Quickstart
# 1 — add it to Claude Code
claude mcp add --scope user --env 'WP_URL=${WP_URL}' --transport stdio wordpress-headless-mcp '--' npx -y wp-headless-mcp
# 2 — ask your agent for something these tools do
# get_acf_fields, content_audit, get_menu and 19 more
It needs WP_URL: this reads it from your environment, so export it first.
WordPress Headless costs nothing on mcprush: there is no plan to choose here, no cap to set and nothing mcprush can bill you for.
Publishernot claimed
AUAll 1 server
aj-ua1 server
1 category
Collected from a public index. Nobody has claimed this account, so nothing here was written by its author — claim it if it is yours.
Installation
Where are you running it?
Every route below installs the same thing and ends at the same approval screen. This one runs on your machine: your client starts WordPress Headless as a process under your own user, with your files and your network, so the tool surface below is what it can do to your computer rather than to a server somewhere else. Its scan result is on the Security tab — read the surface before you approve it.
Claude Codedeclared by this listing
This is a public server: you run it yourself and this marketplace is not in the path. You need Node.js — the current LTS (24) is the safe choice; npx comes with it. Claude Code registers it in one command; --scope user makes it available in every project. Claude Code reads WP_URL (Base URL of the WordPress site, without a trailing slash) from your environment each time it starts the server, so the value stays out of its config: export it in your shell profile (macOS, Linux), or run setx WP_URL … and open a new terminal (Windows). The '--' is in quotes so that PowerShell passes it on.
claude mcp add --scope user --env 'WP_URL=${WP_URL}' --transport stdio wordpress-headless-mcp '--' npx -y wp-headless-mcpReconnect, or start a new session, and the tools appear in the model’s tool list.
Free on mcprush, and it runs from its publisher’s own package: this marketplace is not in the path, so there is no key of ours to hold and no card to add.
What it asks of you
It reaches a system of yours, so it needs settings only you can give it: WP_URL — Base URL of the WordPress site, without a trailing slash. You set it in your own client’s config, on your machine — this marketplace never holds it.
What it writes
One config entry your client uses to start the process locally. A local server runs with your file system and your network, which is why it is priced without metering.
What you approve
22 tools, with what each one reads, writes and reaches shown before you agree — the same list on every route above. Read the tool surface.
Tool surface
What the model actually sees. Descriptions are diffed on every release — see version history.
Read from its source code. A server that builds its tool list when it starts can list more tools than this.
Returns the ACF custom fields of one item with each field's label, type, field group, and value.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| post_type | string | no | Post type slug, e.g. "page" or "project" |
| id | yes | — | |
| slug | yes | — | |
| max_chars | yes | — |
Scans items and lists content problems: missing featured image, missing alt text (featured and ACF images),
| Parameter | Type | Required | Notes |
|---|---|---|---|
| post_type | string | no | Post type slug to audit. Omit to audit every content type. |
| stale_months | integer | no | Flag items not modified for this many months |
| include_drafts | boolean | no | Also audit drafts and items pending review |
| page | integer | no | Page of 100 items per post type |
Returns a navigation menu as a tree of titles and URLs. Pass a menu slug or theme location;
| Parameter | Type | Required | Notes |
|---|---|---|---|
| menu | string | no | Menu slug, e.g. "main-menu" |
| location | string | no | Theme location, e.g. "primary" |
Full-text search across published posts, pages, and custom post types. "results" are title and body
| Parameter | Type | Required | Notes |
|---|---|---|---|
| query | string | yes | Search terms |
| post_type | string | no | Limit to one post type slug (see list_post_types), e.g. "page" or "project" |
| include_acf | boolean | no | Also search ACF field values (first page only) |
| per_page | integer | no | Results per page |
| page | integer | no | Page number |
Lists the content types on the site (posts, pages, and custom post types such as projects),
No parameter schema on file.
Returns one published item by ID or slug: title, URL, dates, author, featured image, terms,
| Parameter | Type | Required | Notes |
|---|---|---|---|
| post_type | string | no | Post type slug, e.g. "post", "page", "project" |
Lists published items of one post type, newest first by default, with optional filters.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| post_type | string | no | Post type slug, e.g. "post", "page", "project" |
| taxonomy | string | no | Taxonomy slug to filter by, e.g. "category" or "post_tag" |
| terms | array | no | Term slugs or numeric IDs in that taxonomy. Requires taxonomy. |
| include_acf | boolean | no | Include shortened ACF fields for each item (useful when content lives in ACF) |
Lists terms in a taxonomy with how many published items use each.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| taxonomy | string | no | Taxonomy slug, e.g. "category" or "post_tag" |
| search | string | no | Keyword filter on term names |
| hide_empty | boolean | no | Skip terms with no published items |
| per_page | integer | no | — |
| page | integer | no | — |
Overview for PWA developers: each post type with its REST route, taxonomies (with REST field names),
No parameter schema on file.
Full ACF field definitions: labels, types, return formats, choices, required flags, sub fields, and
| Parameter | Type | Required | Notes |
|---|---|---|---|
| post_type | string | no | Only groups that apply to this post type. Required without acf-json. |
Returns the raw JSON a PWA would receive from a WordPress REST route (wp/v2/* or yoast/v1/get_head),
| Parameter | Type | Required | Notes |
|---|---|---|---|
| route | string | yes | REST route without /wp-json/, e.g. "wp/v2/project" or "wp/v2/pages/4" |
| query | object | no | Query parameters, e.g. {"acf_format": "standard", "_embed": "1"} |
| per_page | integer | no | Items for collection routes |
| max_chars | integer | no | — |
Generates TypeScript interfaces for a post type's REST response, including typed ACF fields
| Parameter | Type | Required | Notes |
|---|---|---|---|
| post_type | string | yes | Post type slug, e.g. "project" or "page" |
| acf_format | string | no | — |
Checks the site against the requirements for headless use: public post types missing from the REST API,
No parameter schema on file.
Reports what a PWA build needs to know: WordPress version (if published), REST namespaces and detected
No parameter schema on file.
Creates a new draft post, page, or custom post. It is never published: an editor reviews it in wp-admin.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| post_type | string | no | Post type slug, e.g. "post", "page", "project" |
| copy_from | integer | no | — |
| title | string | no | Title. Required unless copy_from is set. |
| content_html | string | no | Body as HTML (the site uses the Classic Editor) |
| excerpt | string | no | — |
| slug | string | no | — |
| template | string | no | Page template file, e.g. "page-templates/home.php" |
| featured_media | integer | no | Media ID for the featured image |
| terms | object | no | Terms by taxonomy slug, e.g. {"category": ["news"], "post_tag": ["gsap"]}. Replaces existing terms. |
| acf | object | no | ACF field values by field name. Images and related posts take IDs. |
Updates a draft or pending item: title, HTML content, excerpt, slug, template, featured image, terms,
| Parameter | Type | Required | Notes |
|---|---|---|---|
| post_type | string | no | — |
| id | integer | yes | — |
| title | string | no | — |
| content_html | string | no | — |
| excerpt | string | no | — |
| slug | string | no | — |
| template | string | no | — |
| featured_media | integer | no | — |
| terms | object | no | Terms by taxonomy slug, e.g. {"category": ["news"], "post_tag": ["gsap"]}. Replaces existing terms. |
| status | string | no | "pending" submits it for review; it never publishes |
Sets ACF custom field values on a draft or pending item. Field names are checked against its field groups
| Parameter | Type | Required | Notes |
|---|---|---|---|
| post_type | string | no | — |
| id | integer | yes | — |
| fields | object | yes | Field values by field name |
Lists unpublished items (drafts and items pending review) of one post type, newest change first.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| post_type | string | no | — |
| per_page | integer | no | — |
| page | integer | no | — |
Downloads a file from a public URL and adds it to the media library with alt text and caption.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| url | string | yes | Public http(s) URL of the file |
| alt_text | string | yes | Alt text describing the image, for accessibility and SEO |
| caption | string | no | — |
| title | string | no | — |
| filename | string | no | File name to store, without path |
| attach_to | integer | no | ID of a draft to attach the file to |
Returns Yoast SEO data for one post, page, or custom post (by post_type with id or slug),
| Parameter | Type | Required | Notes |
|---|---|---|---|
| post_type | string | no | Post type slug, e.g. "page" or "project" |
| id | yes | — | |
| slug | yes | — | |
| url | string | no | Any URL on the site (for archives and other non-post pages). Overrides post_type, id, and slug. |
Scans published items and lists the ones with SEO problems: noindex, missing or too long titles,
| Parameter | Type | Required | Notes |
|---|---|---|---|
| post_type | string | no | Post type slug to scan. Omit to scan every content type (up to 100 items each). |
| severity | string | no | "error" lists only serious issues (noindex, missing title) |
| page | integer | no | Page of 100 items to scan, when one post type has more than 100 |
Returns the site name, tagline, URL, and timezone, plus the organization behind the site
No parameter schema on file.
Free
$0 forever
- Every tool, no call limit
- No card, and mcprush charges nothing for it
- Source published under MIT
- Runs on your machine — nothing of it reaches our gateway
- Nothing to cap, because mcprush bills nothing
What counts against your monthly calls
| Tool | Unit | Calls used | Out of the allowance |
|---|
Nothing here is billable: mcprush charges nothing to install WordPress Headless or to call it, at any volume.
Call allowance · this installenforced at the gateway
Monthly allowance, in calls
—
—
Alert at 80% · then the tool returns a normal MCP error
Used this month: —
ATrust score 96 / 100
Release 1.0.0 · scanned 10 Nov 2026
Two independent axes, because powerful and malicious are different questions. The grade is threat only. The capability level is blast radius, and it is never a penalty on the grade — it is priced as one subtract-only term in the score, where you can see it.
Threat score100
Client score96
Findings0 threat · 2 capability
Capabilitymoderate
Coveragesource
Verificationrepo
Surface digestb9f92932b19feecc73b53212d0e146e0f86a3644a62bf3c255dbc2e51906e733
Score vectorthreat 100 → client 96
| Term | Level | What it prices | Points |
|---|---|---|---|
| capability-exposure | moderate | capability blast radius (moderate) — client exposure if the model is manipulated | −3 |
| verification-discount | repo | publisher verification (public source) — no provenance, but the source is public and inspectable | −1 |
| coverage-honesty | source | inspection depth (source) — how much of the target the scan could see | −0 |
score = clamp(round(threatScore − E_cap − E_ver − E_cov), 0, 100). No model, no opinion, no network call at scoring time: the same methodology version against the same bytes always produces this number, and every line above is a field of the report rather than a summary of it.
What the scan could actually read
A grade is only as meaningful as its coverage, so the scanner publishes its own depth before it publishes its result.
Tool surfaceread
Implementation sourceread
Package metadataread
Live transportnot available
Tools were statically extracted from the published source (22 recovered), not enumerated from a running server. Tool-poisoning, Unicode-smuggling, capability and toxic-flow analysis ran on this inferred surface, but a mis-parsed registration could be missed or mis-attributed, so tool-derived findings are capped below “confirmed”. To grade the real runtime surface, scan the running server: --command "npx -y <package>".
Capability — what it could do if the model were manipulated
Tags derived from each tool’s schema and the implementation, not from what the tool calls itself. moderate is the level these add up to.
| Tool | Capability tags | Why the tag was assigned |
|---|---|---|
| get_acf_fields | no tags | |
| content_audit | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| get_menu | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| search_content | no tags | |
| list_post_types | no tags | |
| get_post | no tags | |
| list_posts | no tags | |
| list_terms | no tags | |
| describe_content_model | no tags | |
| get_acf_schema | no tags | |
| sample_payload | no tags | |
| generate_ts_types | no tags | |
| check_site_requirements | no tags | |
| site_health | no tags | |
| create_draft | external-sink | external-sink: declares readOnlyHint: false, openWorldHint: true |
| update_post | external-sink | external-sink: declares readOnlyHint: false, openWorldHint: true |
| update_acf_fields | external-sink | external-sink: declares readOnlyHint: false, openWorldHint: true |
| list_drafts | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| upload_media | external-sink | external-sink: declares readOnlyHint: false, openWorldHint: true |
| get_seo_meta | no tags | |
| find_seo_issues | no tags | |
| get_company_info | no tags |
Toxic-flow graph
The lethal trifecta, checked as a graph rather than as a checklist: untrusted input, a sensitive source and an external sink have to meet before there is a path worth worrying about.
flow-1
Untrusted input can drive an external action even though no sensitive source is exposed.
Supply chain and provenance
Integrityfirst-seen
Surface digestb9f92932b19feecc
Scanned2026-11-10
This is the first scan of this surface here, so there is nothing yet to compare it against.
Every result on this tab comes from one deterministic pass over the published package — offline, rule by rule, and auditable line by line above. Same methodology version, same bytes, same score.
Release history
Always latest — the install command names no version, so it installs the newest release when it runs; the current release on file is 1.0.0. Pin a release below and the command asks for exactly that one.
1.0.0
undated
latestNo release note was published with this version.
—
no reviews yet
Who can review
One review per account, from a signed-in account that does not publish this listing. Nothing else is asked — you can say what you think before you install it. Publishers can reply once per review, and a review can be edited or deleted by whoever wrote it.
Sign in to write one
Any signed-in account that does not publish WordPress Headless can review it, once — before installing it or after. A review from an account that has installed it is marked as one.
No reviews yet
Nobody has reviewed this listing. The rating on the card is the mean of the reviews written here and nothing else, so there is no rating until somebody writes the first — which takes a signed-in account that does not publish it, and nothing else.