# RivoPress (remote · {site})

WordPress MCP server with Verified Writes: 127 tools for Claude/ChatGPT, OAuth 2.1, self-hosted.

- Trust score: 73/100 (medium)
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-11-21

## Components

- remote · `{site}`: 73/100 (this document), [markdown](https://verifymcp.io/servers/com-rivopress-rivopress/https-site-wp-json-rivopress-v1-mcp.md), [page](https://verifymcp.io/servers/com-rivopress-rivopress/https-site-wp-json-rivopress-v1-mcp)

## Channel facts

- Endpoint: `https://{site}/wp-json/rivopress/v1/mcp`
- Transports: `streamable-http`
- Auth: `required (not validated)`
- Version: `0.6.1`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically against the live server, and we only credit what we can confirm. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-11-21.

- **Endpoint Security**: 83/100
  - The endpoint's TLS certificate is valid, in date, and uses a strong key.
  - Authorisation is enforced on tool calls, but the challenge carries no valid RFC 9728 metadata, so a client cannot discover where to get a token.
  - HTTPS is enforced; there's no plaintext access path.
  - HSTS check failed: the Strict-Transport-Security header is absent.
  - DNSSEC check failed: this domain isn't protected by DNSSEC.
- **Transport & Reachability**: 100/100
  - Verified streamable-http transport via a live MCP handshake.
- **Schema Quality & AI Usability**: 72/100
  - AI-judged instruction clarity (good).
  - Tool/resource definitions use about 7856 tokens (~61/item across 127 items; 127 tools + 0 resources), lean.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 17/100
  - Stability observed for 5 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 100/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 100% of tool parameters carry a description.
- **Tool Safety**: 75/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - 0 of 8 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation; "posts_publish" implies "publish" and declares no destructiveHint at all, which the MCP spec reads as destructive by default.
  - An AI judge read all 128 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 60/100
  - Spec-recency check failed: implements MCP spec 2025-06-18; the latest is 2026-07-28.

## Install

### How do I install the RivoPress MCP server?

RivoPress is a hosted endpoint at https://{site}/wp-json/rivopress/v1/mcp, so there is nothing to install locally. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

### Claude

```bash
claude mcp add --transport http com-rivopress-rivopress 'https://{site}/wp-json/rivopress/v1/mcp'
```

### Cursor

```json
{
  "mcpServers": {
    "com-rivopress-rivopress": {
      "url": "https://{site}/wp-json/rivopress/v1/mcp"
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "com-rivopress-rivopress": {
      "type": "http",
      "url": "https://{site}/wp-json/rivopress/v1/mcp"
    }
  }
}
```

### Codex

```toml
[mcp_servers.com-rivopress-rivopress]
url = "https://{site}/wp-json/rivopress/v1/mcp"
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "com-rivopress-rivopress": {
      "type": "remote",
      "url": "https://{site}/wp-json/rivopress/v1/mcp",
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add com-rivopress-rivopress --url 'https://{site}/wp-json/rivopress/v1/mcp' --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  com-rivopress-rivopress:
    url: "https://{site}/wp-json/rivopress/v1/mcp"
```

### Netclaw

```json
{
  "McpServers": {
    "com-rivopress-rivopress": {
      "Transport": "http",
      "Url": "https://{site}/wp-json/rivopress/v1/mcp"
    }
  }
}
```

### Vellum

```bash
assistant mcp add com-rivopress-rivopress -t streamable-http -u 'https://{site}/wp-json/rivopress/v1/mcp'
```

### Other

```json
{
  "mcpServers": {
    "com-rivopress-rivopress": {
      "type": "http",
      "url": "https://{site}/wp-json/rivopress/v1/mcp"
    }
  }
}
```

The mcpServers block is a cross-client convention. Remote transports vary, so check your client's docs.

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-11-20 (score 73, +1)

No change was recorded against any check on this day. Stability & Change Management went from 10 to 13. That category is still filling its 30-day observation window: 3 days of observed history at the previous scan, 4 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-11-18 (score 72, +1)

No change was recorded against any check on this day. Stability & Change Management went from 3 to 7. That category is still filling its 30-day observation window: 1 days of observed history at the previous scan, 2 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-11-17 (score 71, 0)

- [functional improvement] Stability: unverified → 0.03

### 2026-11-16 (score 71, +38)

- [security improvement] Transport: unverified → pass
- [security improvement] Injection markers: unverified → pass
- [security] First check of Judged manipulation: pass
- [security] Authorization: Authorisation is enforced on tool calls, but the challenge carries no valid RFC 9728 metadata, so a client cannot discover where to get a token.
- [functional regression] MCP protocol: unverified → fail
- [functional improvement] Tool coverage: unverified → 100
- [functional] First check of Schema quality: fail
- [functional] First check of Destructive annotations: 0
- [functional] First check of Schema quality: pass
- [functional] First check of Schema quality: good
- [functional] First check of Tool coverage: 100

### 2026-11-15 (score 33)

First indexed and scored.

## MCP tools (127)

### `site_info` (~33 tokens)

Get basic information about this WordPress site: name, URL, WordPress and PHP versions, active theme and plugin count.

### `site_health` (~34 tokens)

Run read-only health checks: WordPress core version status, PHP version, REST API availability, debug mode and database table prefix.

### `posts_list` (~83 tokens)

List posts with optional status, search and pagination filters.

Input parameters:

- `page` (integer): Page number (default 1).
- `per_page` (integer): Items per page (max 100, default 20).
- `search` (string): Search term.
- `status` (array): Statuses to include (default: publish, draft, future, pending, private).

### `posts_get` (~33 tokens)

Get one post in full: content, status, terms and featured image.

Input parameters:

- `id` (integer, required): The post ID.

### `posts_create` (~231 tokens)

Create a new post. Defaults to DRAFT. Verified after writing.

Input parameters:

- `comment_status` (string): open or closed.
- `content` (string): Body content (HTML / Gutenberg block markup).
- `date` (string): Publish date (Y-m-d H:i:s). Required when status is future.
- `excerpt` (string): Excerpt.
- `featured_image` (integer): Attachment ID to set as featured image (0 removes it).
- `force` (boolean): Bypass the Duplicate Guard when it reports a likely duplicate (default false — a likely duplicate is refused and the match is reported).
- `parent_id` (integer): Parent item ID (pages / hierarchical types).
- `slug` (string): URL slug (post_name).
- `status` (string): Status: draft (default), pending, private, publish or future. Publish/future need the matching capability; creates are DRAFT unless a status is explicitly given.
- `terms` (object): Map of taxonomy => array of term IDs to assign (replaces existing assignments for those taxonomies).
- `title` (string): Title.

### `posts_update` (~186 tokens)

Update fields of an existing post. Only provided fields change. Verified after writing.

Input parameters:

- `comment_status` (string): open or closed.
- `content` (string): Body content (HTML / Gutenberg block markup).
- `date` (string): New publish date (Y-m-d H:i:s).
- `excerpt` (string): Excerpt.
- `featured_image` (integer): Attachment ID to set as featured image (0 removes it).
- `id` (integer, required): The post ID.
- `parent_id` (integer): Parent item ID (pages / hierarchical types).
- `slug` (string): URL slug (post_name).
- `status` (string): New status (not trash — use the trash tool for that).
- `terms` (object): Map of taxonomy => array of term IDs to assign (replaces existing assignments for those taxonomies).
- `title` (string): Title.

### `posts_publish` (~23 tokens)

Publish a post now.

Input parameters:

- `id` (integer, required): The post ID.

### `posts_schedule` (~45 tokens)

Schedule a post for a future date.

Input parameters:

- `date` (string, required): Future date (Y-m-d H:i:s, site timezone).
- `id` (integer, required): The post ID.

### `posts_trash` (~34 tokens)

Move a post to the trash (recoverable). Never a permanent delete.

Input parameters:

- `id` (integer, required): The post ID.

### `posts_restore` (~30 tokens)

Restore a trashed post back to its pre-trash status.

Input parameters:

- `id` (integer, required): The post ID.

### `posts_duplicate` (~37 tokens)

Duplicate a post as a new DRAFT, copying content, meta, terms and featured image.

Input parameters:

- `id` (integer, required): The post ID.

### `pages_list` (~83 tokens)

List pages with optional status, search and pagination filters.

Input parameters:

- `page` (integer): Page number (default 1).
- `per_page` (integer): Items per page (max 100, default 20).
- `search` (string): Search term.
- `status` (array): Statuses to include (default: publish, draft, future, pending, private).

### `pages_get` (~33 tokens)

Get one page in full: content, status, terms and featured image.

Input parameters:

- `id` (integer, required): The page ID.

### `pages_create` (~231 tokens)

Create a new page. Defaults to DRAFT. Verified after writing.

Input parameters:

- `comment_status` (string): open or closed.
- `content` (string): Body content (HTML / Gutenberg block markup).
- `date` (string): Publish date (Y-m-d H:i:s). Required when status is future.
- `excerpt` (string): Excerpt.
- `featured_image` (integer): Attachment ID to set as featured image (0 removes it).
- `force` (boolean): Bypass the Duplicate Guard when it reports a likely duplicate (default false — a likely duplicate is refused and the match is reported).
- `parent_id` (integer): Parent item ID (pages / hierarchical types).
- `slug` (string): URL slug (post_name).
- `status` (string): Status: draft (default), pending, private, publish or future. Publish/future need the matching capability; creates are DRAFT unless a status is explicitly given.
- `terms` (object): Map of taxonomy => array of term IDs to assign (replaces existing assignments for those taxonomies).
- `title` (string): Title.

### `pages_update` (~186 tokens)

Update fields of an existing page. Only provided fields change. Verified after writing.

Input parameters:

- `comment_status` (string): open or closed.
- `content` (string): Body content (HTML / Gutenberg block markup).
- `date` (string): New publish date (Y-m-d H:i:s).
- `excerpt` (string): Excerpt.
- `featured_image` (integer): Attachment ID to set as featured image (0 removes it).
- `id` (integer, required): The page ID.
- `parent_id` (integer): Parent item ID (pages / hierarchical types).
- `slug` (string): URL slug (post_name).
- `status` (string): New status (not trash — use the trash tool for that).
- `terms` (object): Map of taxonomy => array of term IDs to assign (replaces existing assignments for those taxonomies).
- `title` (string): Title.

### `pages_publish` (~23 tokens)

Publish a page now.

Input parameters:

- `id` (integer, required): The page ID.

### `pages_schedule` (~45 tokens)

Schedule a page for a future date.

Input parameters:

- `date` (string, required): Future date (Y-m-d H:i:s, site timezone).
- `id` (integer, required): The page ID.

### `pages_trash` (~34 tokens)

Move a page to the trash (recoverable). Never a permanent delete.

Input parameters:

- `id` (integer, required): The page ID.

### `pages_restore` (~30 tokens)

Restore a trashed page back to its pre-trash status.

Input parameters:

- `id` (integer, required): The page ID.

### `pages_duplicate` (~37 tokens)

Duplicate a page as a new DRAFT, copying content, meta, terms and featured image.

Input parameters:

- `id` (integer, required): The page ID.

### `content_search` (~96 tokens)

Search posts and pages by keyword across statuses, including drafts and scheduled items (for users allowed to see them).

Input parameters:

- `per_page` (integer): Max results (default 20, max 100).
- `post_types` (array): Post types to search (default: post, page).
- `query` (string, required): Search term.
- `statuses` (array): Statuses to include (default: publish, draft, future, pending).

### `media_list` (~84 tokens)

List media library items (attachments) with search and pagination.

Input parameters:

- `mime_type` (string): Filter by mime type group, e.g. image, video, application/pdf.
- `page` (integer): Page number (default 1).
- `per_page` (integer): Items per page (max 100, default 20).
- `search` (string): Search term.

### `media_get` (~43 tokens)

Get one attachment in full: URL, mime type, dimensions, alt text, caption and the items using it as featured image.

Input parameters:

- `id` (integer, required): Attachment ID.

### `media_upload` (~154 tokens)

Upload a file to the media library from a remote URL (source_url) or base64 data. The file type is validated against the site allowlist first. Provide exactly one source.

Input parameters:

- `alt_text` (string): Alt text (images).
- `base64` (string): Base64-encoded file contents (a data: URI prefix is accepted and stripped).
- `caption` (string): Caption.
- `description` (string): Description.
- `filename` (string): File name including extension. Required for base64 uploads.
- `post_id` (integer): Parent post ID to attach the file to.
- `source_url` (string): Public URL to download the file from.
- `title` (string): Attachment title.

### `media_update` (~71 tokens)

Update an attachment title, alt text, caption or description. Verified after writing.

Input parameters:

- `alt_text` (string): New alt text.
- `caption` (string): New caption.
- `description` (string): New description.
- `id` (integer, required): Attachment ID.
- `title` (string): New title.

### `media_trash` (~62 tokens)

Move an attachment to the trash. GUARD: refuses when the file is a featured image somewhere, unless force=true (editor-level users only).

Input parameters:

- `force` (boolean): Trash even if used as a featured image.
- `id` (integer, required): Attachment ID.

### `media_restore` (~23 tokens)

Restore a trashed attachment.

Input parameters:

- `id` (integer, required): Attachment ID.

### `categories_list` (~56 tokens)

List categories with counts.

Input parameters:

- `hide_empty` (boolean): Hide terms with no posts (default false).
- `per_page` (integer): Max items (default 100, max 500).
- `search` (string): Search term.

### `categories_get` (~25 tokens)

Get one term from categories in full.

Input parameters:

- `id` (integer, required): Term ID.

### `categories_create` (~62 tokens)

Create a term in categories. Verified after writing.

Input parameters:

- `description` (string): Description.
- `name` (string, required): Term name.
- `parent_id` (integer): Parent term ID (hierarchical taxonomies).
- `slug` (string): Slug (optional).

### `categories_update` (~71 tokens)

Update a term in categories. Only provided fields change. Verified after writing.

Input parameters:

- `description` (string): New description.
- `id` (integer, required): Term ID.
- `name` (string): New name.
- `parent_id` (integer): New parent term ID.
- `slug` (string): New slug.

### `categories_delete` (~63 tokens)

Delete a term from categories. GUARD: refuses while posts are assigned unless reassign_to names another term — those posts move there first.

Input parameters:

- `id` (integer, required): Term ID.
- `reassign_to` (integer): Term ID to move assigned posts to before deleting.

### `tags_list` (~56 tokens)

List tags with counts.

Input parameters:

- `hide_empty` (boolean): Hide terms with no posts (default false).
- `per_page` (integer): Max items (default 100, max 500).
- `search` (string): Search term.

### `tags_get` (~25 tokens)

Get one term from tags in full.

Input parameters:

- `id` (integer, required): Term ID.

### `tags_create` (~62 tokens)

Create a term in tags. Verified after writing.

Input parameters:

- `description` (string): Description.
- `name` (string, required): Term name.
- `parent_id` (integer): Parent term ID (hierarchical taxonomies).
- `slug` (string): Slug (optional).

### `tags_update` (~71 tokens)

Update a term in tags. Only provided fields change. Verified after writing.

Input parameters:

- `description` (string): New description.
- `id` (integer, required): Term ID.
- `name` (string): New name.
- `parent_id` (integer): New parent term ID.
- `slug` (string): New slug.

### `tags_delete` (~63 tokens)

Delete a term from tags. GUARD: refuses while posts are assigned unless reassign_to names another term — those posts move there first.

Input parameters:

- `id` (integer, required): Term ID.
- `reassign_to` (integer): Term ID to move assigned posts to before deleting.

### `comments_list` (~106 tokens)

List comments, filterable by status (approved, pending, spam, trash, all) and post.

Input parameters:

- `page` (integer): Page number (default 1).
- `per_page` (integer): Items per page (max 100, default 20).
- `post_id` (integer): Only comments on this post ID.
- `search` (string): Search term.
- `status` (string): Status filter: approved, pending, spam, trash or all (default all).

### `comments_get` (~23 tokens)

Get one comment in full.

Input parameters:

- `id` (integer, required): Comment ID.

### `comments_approve` (~27 tokens)

Approve a comment (make it public).

Input parameters:

- `id` (integer, required): Comment ID.

### `comments_hold` (~26 tokens)

Hold a comment (back to pending moderation).

Input parameters:

- `id` (integer, required): Comment ID.

### `comments_spam` (~24 tokens)

Mark a comment as spam.

Input parameters:

- `id` (integer, required): Comment ID.

### `comments_trash` (~25 tokens)

Move a comment to the trash.

Input parameters:

- `id` (integer, required): Comment ID.

### `comments_restore` (~28 tokens)

Restore a comment from the trash to its previous status.

Input parameters:

- `id` (integer, required): Comment ID.

### `comments_reply` (~64 tokens)

Post a reply to a comment, as the connected user. The reply is created approved when the user may moderate, otherwise pending. Undo trashes the reply.

Input parameters:

- `content` (string, required): Reply text.
- `parent_id` (integer, required): ID of the comment being replied to.

### `menus_list` (~21 tokens)

List all navigation menus with their item counts and assigned theme locations.

### `menus_get` (~26 tokens)

Get one menu with its full item tree.

Input parameters:

- `id` (integer, required): Menu ID.

### `menus_create` (~33 tokens)

Create a new (empty) navigation menu. Add items with menus_update_items.

Input parameters:

- `name` (string, required): Menu name.

### `menus_update_items` (~59 tokens)

Replace ALL items of a menu with the provided list (order is preserved; parent_index links children). The previous items are snapshotted for undo.

Input parameters:

- `id` (integer, required): Menu ID.
- `items` (array, required): Complete new item list.

### `menus_delete` (~41 tokens)

Delete a menu (its items go with it). The full menu is snapshotted first — undo recreates it.

Input parameters:

- `id` (integer, required): Menu ID.

### `blocks_get` (~49 tokens)

Get the Gutenberg block structure of a post or page: a tree of block names, attributes and text previews, with index paths for blocks_update.

Input parameters:

- `post_id` (integer, required): Post or page ID.

### `blocks_update` (~111 tokens)

Replace the inner HTML of ONE block, addressed by its index path (e.g. "0" or "1.0" from blocks_get). Refused if the serialize/re-parse safety check fails. Verified write with undo.

Input parameters:

- `block_path` (string, required): Index path of the block, dot-separated (e.g. "0", "2", "1.0").
- `inner_html` (string, required): New inner HTML for the block.
- `post_id` (integer, required): Post or page ID.

### `seo_get` (~101 tokens)

Read the SEO title, description and focus keyword of a post or term from the active SEO plugin (Rank Math, Yoast or AIOSEO).

Input parameters:

- `plugin` (string): rankmath, yoast or aioseo (optional — auto-detected when omitted).
- `target_id` (integer, required): Post ID or term ID.
- `target_type` (string, required): post or term.
- `taxonomy` (string): Taxonomy (required when target_type is term).

### `seo_set` (~136 tokens)

Set SEO title, description and/or focus keyword on a post or term. Only provided fields change; an empty string clears a field. Verified after writing, undoable.

Input parameters:

- `description` (string): Meta description.
- `focus_keyword` (string): Focus keyword / keyphrase.
- `plugin` (string): rankmath, yoast or aioseo (optional — auto-detected when omitted).
- `target_id` (integer, required): Post ID or term ID.
- `target_type` (string, required): post or term.
- `taxonomy` (string): Taxonomy (required when target_type is term).
- `title` (string): SEO title.

### `seo_audit_scan` (~111 tokens)

Audit published posts/pages for SEO problems in batches: missing meta description / SEO title / focus keyword, bad lengths, missing featured image, thin content, stale posts, and the Rank Math score when available. Returns a cursor to continue the scan.

Input parameters:

- `batch_size` (integer): Items per batch (default 25, max 50).
- `cursor` (integer): Pagination offset from a previous call (default 0).
- `post_type` (string): post, page or both (default post).

### `seo_sweep_plan` (~113 tokens)

Build an SEO fix plan for published posts with fixable issues (missing meta description, focus keyword or SEO title). Proposals are generated locally and stored for 24 hours — nothing is changed until seo_sweep_apply runs.

Input parameters:

- `issues` (array): Issue codes to fix (default: missing_meta_description, missing_focus_keyword).
- `max_items` (integer): Maximum posts in the plan (default 50, max 200).
- `post_type` (string): post, page or both (default post).

### `seo_sweep_apply` (~80 tokens)

Apply a stored SEO sweep plan item by item. Every item is re-read after writing and reported as verified or failed — the batch never claims success for an item that did not verify.

Input parameters:

- `only_ids` (array): Optional: apply only these post ids from the plan.
- `plan_id` (integer, required): Plan id from seo_sweep_plan.

### `duplicate_check` (~86 tokens)

Check a proposed post/page title (plus optional slug and focus keyword) against ALL existing posts and pages — published, scheduled, draft, pending and trashed — and report whether it looks like a duplicate before anything is created.

Input parameters:

- `focus_keyword` (string): Proposed focus keyword (optional).
- `slug` (string): Proposed slug (optional).
- `title` (string, required): Proposed title.

### `cannibalization_scan` (~66 tokens)

Scan published posts for cannibalization: groups sharing the same focus keyword, or with very similar titles in the same category, that compete with each other in search results.

Input parameters:

- `max_items` (integer): Maximum published posts to study (default 500, max 1000).

### `calendar_view` (~94 tokens)

See the publishing calendar: scheduled posts grouped by day over a date range, with per-category totals and (optionally) what already published on those days.

Input parameters:

- `days` (integer): Range length in days (default 30, max 90).
- `include_published` (boolean): Also list posts already published in the range (default false).
- `start` (string): First day (Y-m-d, default today).

### `calendar_gaps` (~53 tokens)

Find holes in the schedule: days in the coming window with nothing scheduled, and categories with no post scheduled at all.

Input parameters:

- `days` (integer): Window in days from today (default 30, max 90).

### `calendar_schedule` (~144 tokens)

Schedule an existing draft on a date at a natural, non-round time (e.g. 10:23 instead of 10:00), or at an exact time when exact_time is true. Verified after writing.

Input parameters:

- `date` (string, required): Date (Y-m-d) — must be in the future.
- `exact_time` (boolean): Use the exact time given in "time" instead of a natural time (default false).
- `id` (integer, required): Draft post/page ID.
- `time` (string): Exact time (H:i) — required when exact_time is true.
- `window` (string): morning, afternoon, evening or day (default day).

### `images_scan` (~113 tokens)

Scan the media library in batches for image problems: missing alt text, oversized files and attachments whose file is missing from disk.

Input parameters:

- `batch_size` (integer): Items per batch (default 25, max 50).
- `cursor` (integer): Pagination offset from a previous call (default 0).
- `max_file_kb` (integer): Files larger than this count as oversized (default 300 KB).
- `only_with_issues` (boolean): Return only attachments that have at least one issue (default true).

### `images_missing_featured` (~71 tokens)

List published posts/pages that have no featured image, in batches.

Input parameters:

- `batch_size` (integer): Items per batch (default 25, max 50).
- `cursor` (integer): Pagination offset (default 0).
- `post_type` (string): post, page or both (default post).

### `images_alt_plan` (~68 tokens)

Build a plan to fill missing image alt text. Proposals come from the attachment title, the parent post title, or the cleaned filename — stored for 24 hours, nothing changed yet.

Input parameters:

- `max_items` (integer): Maximum attachments in the plan (default 50, max 200).

### `images_alt_apply` (~70 tokens)

Apply a stored alt-text plan. Each attachment is re-read after writing; per-item verdicts are reported — a failed item never claims success.

Input parameters:

- `only_ids` (array): Optional: apply only these attachment ids from the plan.
- `plan_id` (integer, required): Plan id from images_alt_plan.

### `links_orphans` (~74 tokens)

Find orphan posts/pages: published content that no other published post or page links to from its body content (menu and widget links do not count).

Input parameters:

- `limit` (integer): Maximum orphans to return (default 50, max 200).
- `offset` (integer): Offset into the orphan list (default 0).

### `links_broken` (~56 tokens)

Find broken internal links in published content: links whose target no longer exists, or points at a trashed/draft/unpublished item.

Input parameters:

- `limit` (integer): Maximum broken links to return (default 50, max 100).

### `links_suggest` (~61 tokens)

Suggest internal links for one post: related published posts it could link to, and related posts that could link to it, scored by shared categories/tags and title overlap. Includes a suggested anchor text for each.

Input parameters:

- `id` (integer, required): Post/page ID.

### `links_apply` (~117 tokens)

Insert an internal link into a post: wrap the given anchor text with a link to the target post. With fallback enabled and the anchor absent, a related-reading paragraph is appended instead. Verified after writing.

Input parameters:

- `anchor_text` (string, required): Visible text to turn into the link (first occurrence).
- `fallback` (boolean): Append a related-reading paragraph when the anchor text is not found (default false).
- `source_id` (integer, required): Post/page that receives the link.
- `target_id` (integer, required): Published post/page being linked to.

### `gsc_status` (~42 tokens)

Report whether Google Search Console data is available to RivoPress (service-account connection), which property it reads, and the exact setup steps when it is not connected.

### `gsc_query` (~88 tokens)

Read Search Console page performance (clicks, impressions, CTR, average position) for a date range. Fails with setup steps when Search Console is not connected.

Input parameters:

- `end_date` (string, required): End date (Y-m-d).
- `limit` (integer): Maximum pages (default 100, max 1000).
- `start_date` (string, required): Start date (Y-m-d).

### `traffic_diagnose` (~105 tokens)

Diagnose falling traffic: compare the last 28 days with the previous 28 in Search Console, flag pages whose clicks/position fell beyond thresholds, and classify each (position drop, CTR drop, lost impressions, possible deindex, stale content). Read-only — nothing is changed.

Input parameters:

- `limit` (integer): Maximum flagged pages (default 50, max 200).
- `min_impressions` (integer): Ignore pages with fewer previous impressions than this (default 50).

### `traffic_fix_plan` (~86 tokens)

Store a Traffic Doctor fix plan: for each post, the fix to make (from the diagnosis). Baselines are captured from Search Console at plan time. Nothing on the site changes in this step.

Input parameters:

- `items` (array, required): Fix items: [{post_id, fix}] where fix describes the change (e.g. "update title", "refresh content", "add internal links").

### `traffic_fix_apply` (~72 tokens)

Mark a fix plan as applied — call this AFTER the plan edits were made with the normal tools (posts_update, seo_set, links_apply). Opens a 14-day recheck for every post in the plan, measured against its captured baseline.

Input parameters:

- `plan_id` (integer, required): Plan id from traffic_fix_plan.

### `traffic_rechecks` (~47 tokens)

List Traffic Doctor rechecks. Those past their 14-day due date are measured against their baseline (when Search Console is connected) with a verdict: recovered, improved, unchanged or worse.

### `woo_status` (~26 tokens)

WooCommerce status: active or not, version, currency, store counts. Read-only.

### `woo_products_list` (~74 tokens)

List products with price, stock and status.

Input parameters:

- `page` (integer): Page number (default 1).
- `per_page` (integer): Items per page (default 20, max 100).
- `search` (string): Search by name or SKU.
- `status` (string): Post status (default publish).

### `woo_product_get` (~23 tokens)

One product in detail.

Input parameters:

- `id` (integer, required): Product id.

### `woo_product_create` (~143 tokens)

Create a product (simple type). Verified Write.

Input parameters:

- `description` (string): Full description (HTML allowed).
- `force` (boolean): Create even if a same-named product exists (default false).
- `name` (string, required): Product name.
- `regular_price` (string): Regular price as a decimal string, e.g. "499.00".
- `sale_price` (string): Sale price (optional).
- `short_description` (string): Short description (optional).
- `sku` (string): SKU (optional).
- `status` (string): publish or draft (default draft).
- `stock_quantity` (integer): Stock quantity (enables stock management).

### `woo_product_update` (~123 tokens)

Update a product's name, prices, SKU, stock or status. Verified Write.

Input parameters:

- `description` (string): New description.
- `id` (integer, required): Product id.
- `name` (string): New name.
- `regular_price` (string): New regular price.
- `sale_price` (string): New sale price (empty string clears it).
- `short_description` (string): New short description.
- `sku` (string): New SKU.
- `status` (string): publish, draft or pending.
- `stock_quantity` (integer): New stock quantity.

### `woo_product_trash` (~33 tokens)

Move a product to trash (never a permanent delete). Verified Write.

Input parameters:

- `id` (integer, required): Product id.

### `woo_orders_list` (~66 tokens)

List recent orders with totals and statuses.

Input parameters:

- `page` (integer): Page number (default 1).
- `per_page` (integer): Items per page (default 20, max 100).
- `status` (string): Order status filter, e.g. processing (optional).

### `woo_order_get` (~31 tokens)

One order in detail: items, totals, customer, addresses.

Input parameters:

- `id` (integer, required): Order id.

### `woo_order_set_status` (~51 tokens)

Change an order's status (e.g. completed, on-hold). Verified Write.

Input parameters:

- `id` (integer, required): Order id.
- `status` (string, required): New status without the wc- prefix.

### `woo_order_add_note` (~58 tokens)

Add an order note (optionally emailed to the customer).

Input parameters:

- `customer_note` (boolean): Send to the customer (default false = private note).
- `id` (integer, required): Order id.
- `note` (string, required): Note text.

### `woo_coupons_list` (~37 tokens)

List coupons with amounts and usage.

Input parameters:

- `per_page` (integer): Items per page (default 20, max 100).

### `woo_coupon_create` (~67 tokens)

Create a coupon. Verified Write.

Input parameters:

- `amount` (string, required): Discount amount as a decimal string.
- `code` (string, required): Coupon code.
- `description` (string): Internal description (optional).
- `discount_type` (string): percent, fixed_cart, fixed_product (default percent).

### `woo_coupon_delete` (~32 tokens)

Move a coupon to trash (never a permanent delete). Verified Write.

Input parameters:

- `id` (integer, required): Coupon id.

### `post_types_list` (~21 tokens)

All registered post types with their taxonomies and capabilities summary.

### `cpt_items_list` (~90 tokens)

List items of a custom post type (post/page/product have dedicated tools).

Input parameters:

- `page` (integer): Page number (default 1).
- `per_page` (integer): Items per page (default 20, max 100).
- `post_type` (string, required): Post type slug.
- `search` (string): Search text (optional).
- `status` (string): Status (default publish).

### `cpt_item_get` (~29 tokens)

One custom post type item with its custom fields.

Input parameters:

- `id` (integer, required): Item id.

### `meta_get` (~38 tokens)

Read one custom field of a post (ACF-aware).

Input parameters:

- `id` (integer, required): Post id.
- `key` (string, required): Meta key.

### `meta_set` (~61 tokens)

Write one custom field of a post (ACF-aware). Verified Write with undo.

Input parameters:

- `id` (integer, required): Post id.
- `key` (string, required): Meta key.
- `value` (string, required): Value (stored as string; JSON values are decoded automatically).

### `elementor_info` (~31 tokens)

Whether a post is built with Elementor, and its widget inventory.

Input parameters:

- `id` (integer, required): Post id.

### `elementor_set_text` (~102 tokens)

Change the text of one Elementor widget setting (e.g. a heading's "title" or a text editor's "editor"). Verified Write.

Input parameters:

- `element_id` (string, required): Elementor element id of the widget (see elementor_info).
- `id` (integer, required): Post id.
- `setting` (string, required): Setting key to change (e.g. title, editor, text).
- `value` (string, required): New value (HTML allowed for editor fields).

### `users_list` (~71 tokens)

List WordPress users with roles (admin only; no password data exists in the output).

Input parameters:

- `per_page` (integer): Items per page (default 20, max 100).
- `role` (string): Filter by role slug (optional).
- `search` (string): Search name/email/login (optional).

### `users_create` (~74 tokens)

Create a user. A strong password is generated internally and NEVER returned — WordPress emails the user a set-password link.

Input parameters:

- `display_name` (string): Display name (optional).
- `email` (string, required): Email address.
- `role` (string): Role slug (default subscriber).
- `username` (string, required): Login name.

### `users_set_role` (~52 tokens)

Change a user's role. Guards: cannot change your own role; cannot demote the last administrator. Verified Write.

Input parameters:

- `role` (string, required): New role slug.
- `user_id` (integer, required): User id.

### `plugins_list` (~20 tokens)

All installed plugins: version, active state, available updates.

### `plugins_set_active` (~71 tokens)

Activate or deactivate a plugin by its file (e.g. "akismet/akismet.php"). RivoPress itself is always refused. Verified by re-reading state.

Input parameters:

- `active` (boolean, required): true to activate, false to deactivate.
- `file` (string, required): Plugin file as shown by plugins_list.

### `themes_list` (~17 tokens)

All installed themes with the active one marked.

### `themes_switch` (~39 tokens)

Switch the active theme by stylesheet slug. Verified by re-reading the active theme.

Input parameters:

- `stylesheet` (string, required): Theme stylesheet slug as shown by themes_list.

### `approval_status` (~25 tokens)

Whether approval mode is on, and how many writes are waiting for an admin decision.

### `approvals_list` (~51 tokens)

List approval requests by status (pending, executed, rejected, failed).

Input parameters:

- `limit` (integer): Max rows (default 50).
- `status` (string): pending (default), executed, rejected or failed.

### `approvals_approve` (~47 tokens)

Approve a queued write: it executes NOW under your admin authority, with all verifications, and the outcome is recorded on the request.

Input parameters:

- `id` (integer, required): Approval request id.

### `approvals_reject` (~41 tokens)

Reject a queued write without executing it.

Input parameters:

- `id` (integer, required): Approval request id.
- `reason` (string): Reason stored on the request (optional).

### `approvals_set_mode` (~43 tokens)

Switch approval mode on or off. When on, writes from below-admin connections queue for approval instead of executing.

Input parameters:

- `enabled` (boolean, required): true = approval mode on.

### `protected_list` (~21 tokens)

The protected items RivoPress will never modify, with titles.

### `protected_set` (~54 tokens)

Replace the protected list with these post/page ids. Writes to protected items are refused before they run.

Input parameters:

- `ids` (string, required): Comma-separated ids, e.g. "12, 345". Empty string clears the list.

### `backup_create` (~37 tokens)

Create a content backup (posts, pages, meta, terms, key options) as a JSON file on the server. Secrets are never included.

### `backups_list` (~16 tokens)

List the backups stored on this server.

### `backup_restore` (~57 tokens)

Restore a backup: existing posts/pages get their snapshotted fields, meta and terms back, each as a verified, journaled write. Missing items are reported, not recreated.

Input parameters:

- `file` (string, required): Backup file name from backups_list.

### `backup_delete` (~27 tokens)

Delete a stored backup file.

Input parameters:

- `file` (string, required): Backup file name from backups_list.

### `sites_add` (~102 tokens)

Register a sister site in the Multi-Site Command Center. The URL must run RivoPress and the token must work there — both are verified before saving.

Input parameters:

- `name` (string, required): Display name for the site, e.g. "King Magazine".
- `token` (string, required): A RivoPress token created ON that site (kept server-side, never shown again).
- `url` (string, required): Site home URL, e.g. https://example.com.

### `sites_list` (~21 tokens)

The sister sites registered in the Command Center (tokens never shown).

### `sites_remove` (~27 tokens)

Unregister a sister site.

Input parameters:

- `site_id` (string, required): Site id from sites_list.

### `sites_health` (~31 tokens)

Health of every registered sister site: reachable, RivoPress/WP versions, Connect Doctor summary, response time.

### `sites_call` (~88 tokens)

Run one tool on a sister site and return its result. sites_* tools cannot be proxied.

Input parameters:

- `args_json` (string): Tool arguments as a JSON object string, e.g. {"per_page":5}. Empty for none.
- `site_id` (string, required): Site id from sites_list.
- `tool` (string, required): Tool name on the sister site, e.g. posts_list.

### `whitelabel_get` (~26 tokens)

The brand name shown in the wp-admin menu and page headings (white-label).

### `whitelabel_set` (~59 tokens)

Set the white-label brand name shown in wp-admin. Empty name resets to "RivoPress". Cosmetics only — endpoints and tool names never change.

Input parameters:

- `name` (string, required): Brand name (max 40 chars), or empty to reset.

### `revisions_list` (~51 tokens)

List the revisions of a post or page (newest first).

Input parameters:

- `per_page` (integer): Max revisions (default 20, max 100).
- `post_id` (integer, required): Post or page ID.

### `revisions_restore` (~62 tokens)

Restore a post or page to one of its revisions. The current state is snapshotted first, so this restore can itself be undone.

Input parameters:

- `post_id` (integer, required): Post or page ID.
- `revision_id` (integer, required): Revision ID (from revisions_list).

### `activity_list` (~53 tokens)

Show recent activity for the connected user: the latest audited tool calls and the latest journalled changes (with change IDs for undo).

Input parameters:

- `limit` (integer): Max entries per list (default 50, max 50).

### `undo_change` (~42 tokens)

Undo one journalled change by its change ID (from activity_list). Restores the exact state captured before that write.

Input parameters:

- `change_id` (integer, required): Change ID.

### `undo_last` (~18 tokens)

Undo the connected user's most recent undoable change.

### `doctor_run` (~71 tokens)

Run the RivoPress Connect Doctor: HTTPS, permalinks, REST index, Authorization-header pass-through, versions, tables, OAuth discovery and security-plugin checks — each with a plain-English fix when it fails.

Input parameters:

- `fresh` (boolean): Bypass the 5-minute result cache and run the checks live.

## Diagnostics

Captured diagnostic sections: TLS, DNSSEC, Authorisation, Transports. The full working is on the page: https://verifymcp.io/servers/com-rivopress-rivopress/https-site-wp-json-rivopress-v1-mcp#diagnostics

## Score history

- 2026-11-21: 73
- 2026-11-20: 73
- 2026-11-19: 72
- 2026-11-18: 72
- 2026-11-17: 71
- 2026-11-16: 71
- 2026-11-15: 33

## Common questions

### What is the RivoPress MCP server?

RivoPress is an MCP server listed in the public MCP registry as com.rivopress/rivopress. WordPress MCP server with Verified Writes: 127 tools for Claude/ChatGPT, OAuth 2.1, self-hosted. This page covers its hosted endpoint (https://{site}/wp-json/rivopress/v1/mcp).

### Is the RivoPress MCP server safe to use?

RivoPress scores 73 out of 100 on VerifyMCP. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

### What tools does the RivoPress MCP server expose?

RivoPress exposes 127 tools: site_info, site_health, posts_list, posts_get, posts_create, and 122 more. Their descriptions and schemas cost roughly 7,825 tokens of context every time the server is loaded.

### Does the RivoPress MCP server require authentication?

Yes. RivoPress asked us for credentials when we connected, so you will need to authorise it in your MCP client before it can do anything.

### Is the RivoPress MCP server still maintained?

RivoPress is still listed as active in the MCP registry. We last reached this channel on 21 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

### What did VerifyMCP test on the RivoPress MCP server?

VerifyMCP ran 13 checks on RivoPress, covering TLS certificate, Authorization, HTTPS, HSTS header and 9 more. Supply Chain Security and Provenance & Transparency do not apply to a hosted endpoint, so they were not tested. The score does not measure everything, and the scoring documentation lists what it leaves out.

## Links

- Remote endpoint: https://{site}/wp-json/rivopress/v1/mcp
- Website: https://rivopress.com/
- Changelog RSS feed: https://verifymcp.io/servers/com-rivopress-rivopress/https-site-wp-json-rivopress-v1-mcp.xml
- Changelog JSON feed: https://verifymcp.io/servers/com-rivopress-rivopress/https-site-wp-json-rivopress-v1-mcp/changelog.json
- Trust report (JSON): https://verifymcp.io/servers/com-rivopress-rivopress/https-site-wp-json-rivopress-v1-mcp.json
- HTML version of this page: https://verifymcp.io/servers/com-rivopress-rivopress/https-site-wp-json-rivopress-v1-mcp
