MCP servers › com.rivopress › rivopress
MCP server · registry snapshot 2026-11-17 · last tested 2026-11-17
rivopress MCP server
Registry name com.rivopress/rivopress
by rivopress.com · domain (the registry's namespace rule)Website ↗
WordPress MCP server with Verified Writes: 127 tools for Claude/ChatGPT, OAuth 2.1, self-hosted. — the publisher's description
Summary
com.rivopress/rivopress is a remote MCP server listed in the official MCP registry at version 0.6.1, under the namespace of the domain rivopress.com. On 2026-11-17 ProtocolProbe connected to it in read-only mode and read its inventory: 127 tools, 0 resources and 0 prompts.
Record checks
1 of 2 record checks met · 7 do not apply
- met: Registry entry is active and says how to run it
- not met: Source repository link opens
- not applicable: Repository is not archived
- not applicable: Code pushed to the repository in the 90 days before our check
- not applicable: Repository publishes a security policy (SECURITY.md)
- not applicable: Package names its licence with a standard (SPDX) identifier
- not applicable: The version the registry lists can be installed and is not withdrawn
- not applicable: npm package carries build provenance (attestation)
- not applicable: No known critical or high advisory in the package or its dependencies
- Not ranked by downloads: a remote server publishes no download figure
- Not ranked by stars: no public GitHub repository
From public records, not a safety rating. Each check with its reason
Operate this server? Correct a fact · README badge · Run the checks yourself · Claim it
Key facts
- Runs
- remote (hosted by the publisher)
- Transport
- streamable HTTP
- Your own values
- none declared (not a guarantee)
- Sign-in
- none needed to open a session
- Tools
- 127
- Last tested
- 2026-11-17
Tool list size
19,724 tokens on Claude Opus 5.5
Added to every request that loads this server's tools (127 tools). Counted with Anthropic's token counter on 2026-11-17, from the tool list we read on 2026-11-17. Median across 28,560 counted servers: 2,657 tokens. How it is counted
How a client gets in
Connects without signing in
Read from the server's public metadata on 2026-11-17 (rivopress.com), in our read-only connection; no tool was called. It may have changed since. How it is read
Tool list at the three APIs
Not sent yet for this version (0.6.1).
Observed fact
This server accepted a session without any credential and lists 36 tools whose name or declaration suggests they change data (posts_create, posts_update, pages_create, pages_update, media_upload and 31 more). That is our reading of the names; we did not call them. Source: our connection, 2026-11-17.
How fresh this is
- Live-tested
- yes, a real session (not a text-only review)
- Last tested
- 2026-11-17
- Mode
- read-only (no tool calls)
- Latest version
- 0.6.1, published 2026-11-16 (registry, as of the 2026-11-17 snapshot)
- First listed version
- 2026-11-15 (earliest version still in the registry; older removed versions would be earlier)
- Version history
- 2 versions listed, 2026-11-15 to 2026-11-16; 2 in the 90 days before the 2026-11-17 snapshot.(versions still listed in the registry only)
Most recent 2 versions
0.6.1· 2026-11-160.6.0· 2026-11-15
- Registry data
- snapshot 2026-11-17
- Package and repository
- checked 2026-11-17
- Engine
- mcp-runtime-engine@0.1.0 · sdk@1.32.0
Dead or stale signals
None found in the records we hold
Looked for and not found: deprecated in the registry. Does not apply: listed version cannot be installed or is withdrawn; repository link does not open; repository archived; no push in over 365 days. Each line is a dated fact from a public record. It does not say whether the server still works, and a record can change after the date shown.
Changes since the last refresh
Version 0.6.0 (published 2026-11-15) → 0.6.1 (published 2026-11-16), between the registry lists of 2026-11-16 and 2026-11-17.
No release note: the registry entry links no GitHub repository.
Source: the official MCP Registry list on 2026-11-16 and on 2026-11-17; release notes from the GitHub Releases API, checked 2026-11-17.
What it is
What does this server offer?
Observed inventoryNone of its 127 tools are described as changing anything. For 127 the reading was uncertain, so no mark is shown.
- site_infoon 28 other servers
“Get basic information about this WordPress site: name, URL, WordPress and PHP versions, active theme and plugin count.”
Takes no inputs.
- site_healthon 1 other server
“Run read-only health checks: WordPress core version status, PHP version, REST API availability, debug mode and database table prefix.”
Takes no inputs.
- posts_liston 1 other server
“List posts with optional status, search and pagination filters.”
4 inputs
statusarray“Statuses to include (default: publish, draft, future, pending, private).”searchstring“Search term.”per_pageinteger“Items per page (max 100, default 20).”pageinteger“Page number (default 1).”
- posts_get
“Get one post in full: content, status, terms and featured image.”
1 input, 1 required
idintegerrequired“The post ID.”
- posts_create
“Create a new post.”
11 inputs
titlestring“Title.”contentstring“Body content (HTML / Gutenberg block markup).”excerptstring“Excerpt.”slugstring“URL slug (post_name).”parent_idinteger“Parent item ID (pages / hierarchical types).”comment_statusstring“open or closed.”termsobject“Map of taxonomy => array of term IDs to assign (replaces existing assignments for those taxonomies).”featured_imageinteger“Attachment ID to set as featured image (0 removes it).”statusstring“Status: draft (default), pending, private, publish or future.”datestring“Publish date (Y-m-d H:i:s).”forceboolean“Bypass the Duplicate Guard when it reports a likely duplicate (default false — a likely duplicate is refused and the match is reported).”
- posts_update
“Update fields of an existing post.”
11 inputs, 1 required
idintegerrequired“The post ID.”titlestring“Title.”contentstring“Body content (HTML / Gutenberg block markup).”excerptstring“Excerpt.”slugstring“URL slug (post_name).”parent_idinteger“Parent item ID (pages / hierarchical types).”comment_statusstring“open or closed.”termsobject“Map of taxonomy => array of term IDs to assign (replaces existing assignments for those taxonomies).”featured_imageinteger“Attachment ID to set as featured image (0 removes it).”statusstring“New status (not trash — use the trash tool for that).”datestring“New publish date (Y-m-d H:i:s).”
- posts_publishon 1 other server
“Publish a post now.”
1 input, 1 required
idintegerrequired“The post ID.”
- posts_schedule
“Schedule a post for a future date.”
2 inputs, 2 required
idintegerrequired“The post ID.”datestringrequired“Future date (Y-m-d H:i:s, site timezone).”
- posts_trash
“Move a post to the trash (recoverable).”
1 input, 1 required
idintegerrequired“The post ID.”
- posts_restore
“Restore a trashed post back to its pre-trash status.”
1 input, 1 required
idintegerrequired“The post ID.”
- posts_duplicate
“Duplicate a post as a new DRAFT, copying content, meta, terms and featured image.”
1 input, 1 required
idintegerrequired“The post ID.”
- pages_liston 2 other servers
“List pages with optional status, search and pagination filters.”
4 inputs
statusarray“Statuses to include (default: publish, draft, future, pending, private).”searchstring“Search term.”per_pageinteger“Items per page (max 100, default 20).”pageinteger“Page number (default 1).”
Show 88 more tools
- pages_get
“Get one page in full: content, status, terms and featured image.”
1 input, 1 required
idintegerrequired“The page ID.”
- pages_create
“Create a new page.”
11 inputs
titlestring“Title.”contentstring“Body content (HTML / Gutenberg block markup).”excerptstring“Excerpt.”slugstring“URL slug (post_name).”parent_idinteger“Parent item ID (pages / hierarchical types).”comment_statusstring“open or closed.”termsobject“Map of taxonomy => array of term IDs to assign (replaces existing assignments for those taxonomies).”featured_imageinteger“Attachment ID to set as featured image (0 removes it).”statusstring“Status: draft (default), pending, private, publish or future.”datestring“Publish date (Y-m-d H:i:s).”forceboolean“Bypass the Duplicate Guard when it reports a likely duplicate (default false — a likely duplicate is refused and the match is reported).”
- pages_update
“Update fields of an existing page.”
11 inputs, 1 required
idintegerrequired“The page ID.”titlestring“Title.”contentstring“Body content (HTML / Gutenberg block markup).”excerptstring“Excerpt.”slugstring“URL slug (post_name).”parent_idinteger“Parent item ID (pages / hierarchical types).”comment_statusstring“open or closed.”termsobject“Map of taxonomy => array of term IDs to assign (replaces existing assignments for those taxonomies).”featured_imageinteger“Attachment ID to set as featured image (0 removes it).”statusstring“New status (not trash — use the trash tool for that).”datestring“New publish date (Y-m-d H:i:s).”
- pages_publish
“Publish a page now.”
1 input, 1 required
idintegerrequired“The page ID.”
- pages_schedule
“Schedule a page for a future date.”
2 inputs, 2 required
idintegerrequired“The page ID.”datestringrequired“Future date (Y-m-d H:i:s, site timezone).”
- pages_trash
“Move a page to the trash (recoverable).”
1 input, 1 required
idintegerrequired“The page ID.”
- pages_restore
“Restore a trashed page back to its pre-trash status.”
1 input, 1 required
idintegerrequired“The page ID.”
- pages_duplicateon 1 other server
“Duplicate a page as a new DRAFT, copying content, meta, terms and featured image.”
1 input, 1 required
idintegerrequired“The page ID.”
- content_search
“Search posts and pages by keyword across statuses, including drafts and scheduled items (for users allowed to see them).”
4 inputs, 1 required
querystringrequired“Search term.”post_typesarray“Post types to search (default: post, page).”statusesarray“Statuses to include (default: publish, draft, future, pending).”per_pageinteger“Max results (default 20, max 100).”
- media_liston 3 other servers
“List media library items (attachments) with search and pagination.”
4 inputs
searchstring“Search term.”mime_typestring“Filter by mime type group, e.g.”per_pageinteger“Items per page (max 100, default 20).”pageinteger“Page number (default 1).”
- media_geton 1 other server
“Get one attachment in full: URL, mime type, dimensions, alt text, caption and the items using it as featured image.”
1 input, 1 required
idintegerrequired“Attachment ID.”
- media_uploadon 2 other servers
“Upload a file to the media library from a remote URL (source_url) or base64 data.”
8 inputs
source_urlstring“Public URL to download the file from.”base64string“Base64-encoded file contents (a data: URI prefix is accepted and stripped).”filenamestring“File name including extension.”titlestring“Attachment title.”alt_textstring“Alt text (images).”captionstring“Caption.”descriptionstring“Description.”post_idinteger“Parent post ID to attach the file to.”
- media_update
“Update an attachment title, alt text, caption or description.”
5 inputs, 1 required
idintegerrequired“Attachment ID.”titlestring“New title.”alt_textstring“New alt text.”captionstring“New caption.”descriptionstring“New description.”
- media_trash
“Move an attachment to the trash.”
2 inputs, 1 required
idintegerrequired“Attachment ID.”forceboolean“Trash even if used as a featured image.”
- media_restore
“Restore a trashed attachment.”
1 input, 1 required
idintegerrequired“Attachment ID.”
- categories_liston 1 other server
“List categories with counts.”
3 inputs
searchstring“Search term.”hide_emptyboolean“Hide terms with no posts (default false).”per_pageinteger“Max items (default 100, max 500).”
- categories_get
“Get one term from categories in full.”
1 input, 1 required
idintegerrequired“Term ID.”
- categories_create
“Create a term in categories.”
4 inputs, 1 required
namestringrequired“Term name.”slugstring“Slug (optional).”descriptionstring“Description.”parent_idinteger“Parent term ID (hierarchical taxonomies).”
- categories_update
“Update a term in categories.”
5 inputs, 1 required
idintegerrequired“Term ID.”namestring“New name.”slugstring“New slug.”descriptionstring“New description.”parent_idinteger“New parent term ID.”
- categories_delete
“Delete a term from categories.”
2 inputs, 1 required
idintegerrequired“Term ID.”reassign_tointeger“Term ID to move assigned posts to before deleting.”
- tags_liston 3 other servers
“List tags with counts.”
3 inputs
searchstring“Search term.”hide_emptyboolean“Hide terms with no posts (default false).”per_pageinteger“Max items (default 100, max 500).”
- tags_geton 1 other server
“Get one term from tags in full.”
1 input, 1 required
idintegerrequired“Term ID.”
- tags_createon 1 other server
“Create a term in tags.”
4 inputs, 1 required
namestringrequired“Term name.”slugstring“Slug (optional).”descriptionstring“Description.”parent_idinteger“Parent term ID (hierarchical taxonomies).”
- tags_update
“Update a term in tags.”
5 inputs, 1 required
idintegerrequired“Term ID.”namestring“New name.”slugstring“New slug.”descriptionstring“New description.”parent_idinteger“New parent term ID.”
- tags_delete
“Delete a term from tags.”
2 inputs, 1 required
idintegerrequired“Term ID.”reassign_tointeger“Term ID to move assigned posts to before deleting.”
- comments_list
“List comments, filterable by status (approved, pending, spam, trash, all) and post.”
5 inputs
statusstring“Status filter: approved, pending, spam, trash or all (default all).”post_idinteger“Only comments on this post ID.”searchstring“Search term.”per_pageinteger“Items per page (max 100, default 20).”pageinteger“Page number (default 1).”
- comments_get
“Get one comment in full.”
1 input, 1 required
idintegerrequired“Comment ID.”
- comments_approve
“Approve a comment (make it public).”
1 input, 1 required
idintegerrequired“Comment ID.”
- comments_hold
“Hold a comment (back to pending moderation).”
1 input, 1 required
idintegerrequired“Comment ID.”
- comments_spam
“Mark a comment as spam.”
1 input, 1 required
idintegerrequired“Comment ID.”
- comments_trash
“Move a comment to the trash.”
1 input, 1 required
idintegerrequired“Comment ID.”
- comments_restore
“Restore a comment from the trash to its previous status.”
1 input, 1 required
idintegerrequired“Comment ID.”
- comments_reply
“Post a reply to a comment, as the connected user.”
2 inputs, 2 required
parent_idintegerrequired“ID of the comment being replied to.”contentstringrequired“Reply text.”
- menus_list
“List all navigation menus with their item counts and assigned theme locations.”
Takes no inputs.
- menus_get
“Get one menu with its full item tree.”
1 input, 1 required
idintegerrequired“Menu ID.”
- menus_create
“Create a new (empty) navigation menu.”
1 input, 1 required
namestringrequired“Menu name.”
- menus_update_items
“Replace ALL items of a menu with the provided list (order is preserved; parent_index links children).”
2 inputs, 2 required
idintegerrequired“Menu ID.”itemsarrayrequired“Complete new item list.”
- menus_delete
“Delete a menu (its items go with it).”
1 input, 1 required
idintegerrequired“Menu ID.”
- blocks_get
“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.”
1 input, 1 required
post_idintegerrequired“Post or page ID.”
- blocks_update
“Replace the inner HTML of ONE block, addressed by its index path (e.g.”
3 inputs, 3 required
post_idintegerrequired“Post or page ID.”block_pathstringrequired“Index path of the block, dot-separated (e.g.”inner_htmlstringrequired“New inner HTML for the block.”
- seo_get
“Read the SEO title, description and focus keyword of a post or term from the active SEO plugin (Rank Math, Yoast or AIOSEO).”
4 inputs, 2 required
target_typestringrequired“post or term.”target_idintegerrequired“Post ID or term ID.”taxonomystring“Taxonomy (required when target_type is term).”pluginstring“rankmath, yoast or aioseo (optional — auto-detected when omitted).”
- seo_set
“Set SEO title, description and/or focus keyword on a post or term.”
7 inputs, 2 required
target_typestringrequired“post or term.”target_idintegerrequired“Post ID or term ID.”taxonomystring“Taxonomy (required when target_type is term).”pluginstring“rankmath, yoast or aioseo (optional — auto-detected when omitted).”titlestring“SEO title.”descriptionstring“Meta description.”focus_keywordstring“Focus keyword / keyphrase.”
- seo_audit_scan
“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 …”
3 inputs
cursorinteger“Pagination offset from a previous call (default 0).”batch_sizeinteger“Items per batch (default 25, max 50).”post_typestring“post, page or both (default post).”
- seo_sweep_plan
“Build an SEO fix plan for published posts with fixable issues (missing meta description, focus keyword or SEO title).”
3 inputs
issuesarray“Issue codes to fix (default: missing_meta_description, missing_focus_keyword).”max_itemsinteger“Maximum posts in the plan (default 50, max 200).”post_typestring“post, page or both (default post).”
- seo_sweep_apply
“Apply a stored SEO sweep plan item by item.”
2 inputs, 1 required
plan_idintegerrequired“Plan id from seo_sweep_plan.”only_idsarray“Optional: apply only these post ids from the plan.”
- duplicate_checkon 1 other server
“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 du…”
3 inputs, 1 required
titlestringrequired“Proposed title.”slugstring“Proposed slug (optional).”focus_keywordstring“Proposed focus keyword (optional).”
- cannibalization_scan
“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.”
1 input
max_itemsinteger“Maximum published posts to study (default 500, max 1000).”
- calendar_view
“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.”
3 inputs
startstring“First day (Y-m-d, default today).”daysinteger“Range length in days (default 30, max 90).”include_publishedboolean“Also list posts already published in the range (default false).”
- calendar_gaps
“Find holes in the schedule: days in the coming window with nothing scheduled, and categories with no post scheduled at all.”
1 input
daysinteger“Window in days from today (default 30, max 90).”
- calendar_schedule
“Schedule an existing draft on a date at a natural, non-round time (e.g.”
5 inputs, 2 required
idintegerrequired“Draft post/page ID.”datestringrequired“Date (Y-m-d) — must be in the future.”windowstring“morning, afternoon, evening or day (default day).”exact_timeboolean“Use the exact time given in "time" instead of a natural time (default false).”timestring“Exact time (H:i) — required when exact_time is true.”
- images_scan
“Scan the media library in batches for image problems: missing alt text, oversized files and attachments whose file is missing from disk.”
4 inputs
cursorinteger“Pagination offset from a previous call (default 0).”batch_sizeinteger“Items per batch (default 25, max 50).”max_file_kbinteger“Files larger than this count as oversized (default 300 KB).”only_with_issuesboolean“Return only attachments that have at least one issue (default true).”
- images_missing_featured
“List published posts/pages that have no featured image, in batches.”
3 inputs
cursorinteger“Pagination offset (default 0).”batch_sizeinteger“Items per batch (default 25, max 50).”post_typestring“post, page or both (default post).”
- images_alt_plan
“Build a plan to fill missing image alt text.”
1 input
max_itemsinteger“Maximum attachments in the plan (default 50, max 200).”
- images_alt_apply
“Apply a stored alt-text plan.”
2 inputs, 1 required
plan_idintegerrequired“Plan id from images_alt_plan.”only_idsarray“Optional: apply only these attachment ids from the plan.”
- links_orphans
“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).”
2 inputs
limitinteger“Maximum orphans to return (default 50, max 200).”offsetinteger“Offset into the orphan list (default 0).”
- links_broken
“Find broken internal links in published content: links whose target no longer exists, or points at a trashed/draft/unpublished item.”
1 input
limitinteger“Maximum broken links to return (default 50, max 100).”
- links_suggest
“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.”
1 input, 1 required
idintegerrequired“Post/page ID.”
- links_apply
“Insert an internal link into a post: wrap the given anchor text with a link to the target post.”
4 inputs, 3 required
source_idintegerrequired“Post/page that receives the link.”target_idintegerrequired“Published post/page being linked to.”anchor_textstringrequired“Visible text to turn into the link (first occurrence).”fallbackboolean“Append a related-reading paragraph when the anchor text is not found (default false).”
- gsc_statuson 1 other server
“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.”
Takes no inputs.
- gsc_queryon 3 other servers
“Read Search Console page performance (clicks, impressions, CTR, average position) for a date range.”
3 inputs, 2 required
start_datestringrequired“Start date (Y-m-d).”end_datestringrequired“End date (Y-m-d).”limitinteger“Maximum pages (default 100, max 1000).”
- traffic_diagnose
“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 im…”
2 inputs
min_impressionsinteger“Ignore pages with fewer previous impressions than this (default 50).”limitinteger“Maximum flagged pages (default 50, max 200).”
- traffic_fix_plan
“Store a Traffic Doctor fix plan: for each post, the fix to make (from the diagnosis).”
1 input, 1 required
itemsarrayrequired“Fix items: [{post_id, fix}] where fix describes the change (e.g.”
- traffic_fix_apply
“Mark a fix plan as applied — call this AFTER the plan edits were made with the normal tools (posts_update, seo_set, links_apply).”
1 input, 1 required
plan_idintegerrequired“Plan id from traffic_fix_plan.”
- traffic_rechecks
“List Traffic Doctor rechecks.”
Takes no inputs.
- woo_status
“WooCommerce status: active or not, version, currency, store counts.”
Takes no inputs.
- woo_products_list
“List products with price, stock and status.”
4 inputs
statusstring“Post status (default publish).”searchstring“Search by name or SKU.”per_pageinteger“Items per page (default 20, max 100).”pageinteger“Page number (default 1).”
- woo_product_get
“One product in detail.”
1 input, 1 required
idintegerrequired“Product id.”
- woo_product_create
“Create a product (simple type).”
9 inputs, 1 required
namestringrequired“Product name.”regular_pricestring“Regular price as a decimal string, e.g.”sale_pricestring“Sale price (optional).”skustring“SKU (optional).”descriptionstring“Full description (HTML allowed).”short_descriptionstring“Short description (optional).”stock_quantityinteger“Stock quantity (enables stock management).”statusstring“publish or draft (default draft).”forceboolean“Create even if a same-named product exists (default false).”
- woo_product_update
“Update a product's name, prices, SKU, stock or status.”
9 inputs, 1 required
idintegerrequired“Product id.”namestring“New name.”regular_pricestring“New regular price.”sale_pricestring“New sale price (empty string clears it).”skustring“New SKU.”descriptionstring“New description.”short_descriptionstring“New short description.”stock_quantityinteger“New stock quantity.”statusstring“publish, draft or pending.”
- woo_product_trash
“Move a product to trash (never a permanent delete).”
1 input, 1 required
idintegerrequired“Product id.”
- woo_orders_list
“List recent orders with totals and statuses.”
3 inputs
statusstring“Order status filter, e.g.”per_pageinteger“Items per page (default 20, max 100).”pageinteger“Page number (default 1).”
- woo_order_get
“One order in detail: items, totals, customer, addresses.”
1 input, 1 required
idintegerrequired“Order id.”
- woo_order_set_status
“Change an order's status (e.g.”
2 inputs, 2 required
idintegerrequired“Order id.”statusstringrequired“New status without the wc- prefix.”
- woo_order_add_note
“Add an order note (optionally emailed to the customer).”
3 inputs, 2 required
idintegerrequired“Order id.”notestringrequired“Note text.”customer_noteboolean“Send to the customer (default false = private note).”
- woo_coupons_list
“List coupons with amounts and usage.”
1 input
per_pageinteger“Items per page (default 20, max 100).”
- woo_coupon_create
“Create a coupon.”
4 inputs, 2 required
codestringrequired“Coupon code.”discount_typestring“percent, fixed_cart, fixed_product (default percent).”amountstringrequired“Discount amount as a decimal string.”descriptionstring“Internal description (optional).”
- woo_coupon_delete
“Move a coupon to trash (never a permanent delete).”
1 input, 1 required
idintegerrequired“Coupon id.”
- post_types_list
“All registered post types with their taxonomies and capabilities summary.”
Takes no inputs.
- cpt_items_list
“List items of a custom post type (post/page/product have dedicated tools).”
5 inputs, 1 required
post_typestringrequired“Post type slug.”statusstring“Status (default publish).”searchstring“Search text (optional).”per_pageinteger“Items per page (default 20, max 100).”pageinteger“Page number (default 1).”
- cpt_item_get
“One custom post type item with its custom fields.”
1 input, 1 required
idintegerrequired“Item id.”
- meta_get
“Read one custom field of a post (ACF-aware).”
2 inputs, 2 required
idintegerrequired“Post id.”keystringrequired“Meta key.”
- meta_set
“Write one custom field of a post (ACF-aware).”
3 inputs, 3 required
idintegerrequired“Post id.”keystringrequired“Meta key.”valuestringrequired“Value (stored as string; JSON values are decoded automatically).”
- elementor_info
“Whether a post is built with Elementor, and its widget inventory.”
1 input, 1 required
idintegerrequired“Post id.”
- elementor_set_text
“Change the text of one Elementor widget setting (e.g.”
4 inputs, 4 required
idintegerrequired“Post id.”element_idstringrequired“Elementor element id of the widget (see elementor_info).”settingstringrequired“Setting key to change (e.g.”valuestringrequired“New value (HTML allowed for editor fields).”
- users_liston 2 other servers
“List WordPress users with roles (admin only; no password data exists in the output).”
3 inputs
rolestring“Filter by role slug (optional).”searchstring“Search name/email/login (optional).”per_pageinteger“Items per page (default 20, max 100).”
- users_createon 1 other server
“Create a user.”
4 inputs, 2 required
usernamestringrequired“Login name.”emailstringrequired“Email address.”rolestring“Role slug (default subscriber).”display_namestring“Display name (optional).”
- users_set_role
“Change a user's role.”
2 inputs, 2 required
user_idintegerrequired“User id.”rolestringrequired“New role slug.”
- plugins_list
“All installed plugins: version, active state, available updates.”
Takes no inputs.
Each quoted sentence is the first sentence of the publisher’s own description. The kind of tool and the “changes data” mark are our AI model’s reading of that description, not something we tested: two differently worded runs had to agree, otherwise no label is shown, and nobody has checked them by hand. A tool without the “changes data” mark is described as only reading, searching or calculating, or the two runs did not agree. No tool was called. Read the publisher’s full description before relying on it. Inputs are the parameters in the tool's own input schema: name, declared type, whether it is required, and the first sentence of its description. The first 100 of 127 tools are listed. Read 2026-11-17.
How well are its tools described?
Features #4 and #5
How clearly this server's own tool descriptions say what a tool does, and how consistent its tool list is. The first part is an AI model's yes/no reading of each description; the second part is counted. We do not turn it into a grade.
Descriptions
AI reading of each description
No AI reading was available for this server's tools (the two runs did not agree, or the listing was not reviewed).
Counted from the listing
- Parameters with a description
- 100% of 291
- Tools with a description
- 100% of 127
- Typical description length
- 96 characters
The tool set
Counted from the listing
- Tools
- 127
- Size of the list
- about 12,223 tokens for an agent to load (characters ÷ 4)
- Naming
- 127 of 127 names use snake_case
AI reading: easy to mix up
No pair found.
The AI items cover 0 of 127 tools: for a tool where two differently worded runs disagreed, that item is left out. They were not checked by hand, and no tool was called. “Easy to mix up” means two tools whose names or descriptions overlap without saying how they differ; the AI found none, comparing tools within groups of 40. We do not rate whether the tool set is complete or whether side effects are spelled out, because our AI reading of those was not reliable enough.
How do I add it to my client?
Config from the registry entry
From the remote endpoint (Streamable HTTP)
We connected to this URL on 2026-11-17 (a read-only session: no tool was called).
This entry needs values of your own (marked < > or { } in the config below), so there is no one-click link: paste the config and fill them in.
Claude Desktop or claude.ai
Settings → Connectors → Add custom connector, then paste:
https://{site}/wp-json/rivopress/v1/mcpCursor · .cursor/mcp.json in a project, or ~/.cursor/mcp.json
{
"mcpServers": {
"rivopress": {
"url": "https://{site}/wp-json/rivopress/v1/mcp"
}
}
}VS Code · .vscode/mcp.json
{
"servers": {
"rivopress": {
"type": "http",
"url": "https://{site}/wp-json/rivopress/v1/mcp"
}
}
}Claude Code
claude mcp add --transport http rivopress "https://{site}/wp-json/rivopress/v1/mcp"Cline · cline_mcp_settings.json (Cline CLI: ~/.cline/data/settings/; in the editor: MCP Servers → Configure → Configure MCP Servers)
{
"mcpServers": {
"rivopress": {
"type": "streamableHttp",
"url": "https://{site}/wp-json/rivopress/v1/mcp",
"disabled": false,
"autoApprove": []
}
}
}Gemini CLI · ~/.gemini/settings.json, or .gemini/settings.json in a project
{
"mcpServers": {
"rivopress": {
"httpUrl": "https://{site}/wp-json/rivopress/v1/mcp"
}
}
}OpenAI Codex · ~/.codex/config.toml, or .codex/config.toml in a trusted project
[mcp_servers.rivopress]
url = "https://{site}/wp-json/rivopress/v1/mcp"Zed · Zed settings file (command: zed: open settings file)
{
"context_servers": {
"rivopress": {
"url": "https://{site}/wp-json/rivopress/v1/mcp"
}
}
}Try it in the MCP Inspector · runs on your machine, opens in your browser · Node 22.19+
npx @modelcontextprotocol/inspector@2.11.0 --server-url "https://{site}/wp-json/rivopress/v1/mcp" --transport http- The URL contains parts in { } that the entry marks as variables; replace them with your own values.
- The server runs on the operator's infrastructure; it may ask you to sign in when you first connect.
- Zed's docs we read on 2026-10-26 describe remote servers by URL and do not name the transport.
- The MCP Inspector lists the server's tools, resources and prompts; a tool you call there runs for real.
Built from the server's registry entry with each client's documented format (checked 2026-10-14; the Cursor link and the VS Code command 2026-10-19; the MCP Inspector command 2026-10-21; Cline, Gemini CLI, OpenAI Codex and Zed 2026-10-26). Values in < > are yours to fill in; this page never contains a key. Where the server needs a setting the entry does not declare, it can still fail to start.
What do the published files and outside lists say?
Read as text · nothing run · no tool called
Package files
- MCP SDK in the package files. Not read yet: added with the next daily run.
- Build workflow. Not read yet: added with the next daily run.
Outside lists
- CVE records (NVD). No CVE record in the NVD feeds we read links this server's repository. Source: read 2026-11-17. This product uses the NVD API but is not endorsed or certified by the NVD.
- GitHub advisories. No GitHub advisory names this entry's listed package. Source: read 2026-11-17. GitHub Advisory Database, CC BY 4.0
- Docker MCP catalogue. Not in the Docker MCP catalogue on 2026-11-17. Source: read 2026-11-17.
- Cline marketplace. Not in the Cline marketplace on 2026-11-17. Source: read 2026-11-17.
Own host
- security.txt. No security.txt at https://rivopress.com/.well-known/ (HTTP 404, 2026-11-17). Source: rivopress.com/.well-known/security.txt · read 2026-11-17.
- A2A agent card. No A2A agent card at https://rivopress.com/.well-known/ (HTTP 404, 2026-11-17). Source: rivopress.com/.well-known/agent-card.json · read 2026-11-17.
Read as text from published files and outside lists. Nothing was installed or run, and no tool was called. A fact, not a rating. How each fact is read
Does the registry listing match what we found?
Feature #6The registry checks an entry when it is published (each new version), and nothing re-checks it on a schedule. A difference below is about the listing, not a judgement of the publisher.
| Registry says | We found | Result | Source · date |
|---|---|---|---|
| Remote endpoint {site}/wp-json/rivopress/v1/mcp | Session opened | matches | our test · 2026-11-17 |
| No credential declared as required | Opened a session without any credential | matches | our test · 2026-11-17 |
Choosing
Record checks
Public records · not a safety rating1 of 2 record checks met · 7 do not apply
- Not ranked by downloads: a remote server publishes no download figure
- Not ranked by stars: no public GitHub repository
- MetRegistry entry is active and says how to run itActive, with a package or a remote address.
- Not metSource repository link opensThe registry entry gives no repository link.What changes this check: This check opens the repository link in the registry entry. GitHub's documentation describes changing a repository's visibility in its Settings, under Danger Zone, Change visibility. GitHub: setting repository visibility
- Does not applyRepository is not archivedNo public GitHub repository to read.
- Does not applyCode pushed to the repository in the 90 days before our checkNo public GitHub repository to read.
- Does not applyRepository publishes a security policy (SECURITY.md)No public GitHub repository to read.
- Does not applyPackage names its licence with a standard (SPDX) identifierRemote server: it ships no package.
- Does not applyThe version the registry lists can be installed and is not withdrawnRemote server: it ships no package.
- Does not applynpm package carries build provenance (attestation)Remote server: it ships no package.
- Does not applyNo known critical or high advisory in the package or its dependenciesRemote server: it ships no package.
Read from public records only: the registry entry, npm/PyPI, GitHub and advisory databases, checked 2026-11-17. No tool was called. Only “met” and “not met” are counted, so the total differs between servers; a check that does not apply or that we could not run is listed, never counted against it. It is not a safety rating, and the same rules apply to every server. How each check works · Leaderboards · How we stay neutral
Common questions about com.rivopress/rivopress
Answered from the data aboveWho publishes com.rivopress/rivopress?
The registry ties the namespace com.rivopress to the domain rivopress.com; only its owner can publish under it. These are facts from the registry and GitHub, not a rating.
Does com.rivopress/rivopress need an API key or sign-in?
It opened a session without any credential on 2026-11-17. The registry entry declares no required credential; no declaration is not a guarantee.
Has com.rivopress/rivopress been security tested?
Partly. 2 of the 14 checks that apply to it were exercised. It accepted a session without any credential and lists tools whose names suggest they change data. We did not call them. ProtocolProbe publishes no security verdict for a named server.
Found this page useful?
Anonymous · no sign-inA quick, anonymous reaction — no account, no email. One per kind from your browser. The tally updates when the page is next refreshed, and it is only a rough count, never a safety rating or a measured number of people.
Compare with another server
Side by side: registry entry, our read-only session, the tools and the 18 classification fields. Same values as each page; no score.
Security testing
What did we test, and what did we leave out?
18 checks · features #1, #2
Open without sign-in
It accepted a session without any credential and lists tools whose names suggest they change data. We did not call them. No security score is given; a check we did not run is never counted as passed.
- Inventory: exercised
- Hidden instructions: exercised
- Real execution: not run · our policy
- Secret leak: not run · nothing to check it against
- Internal addresses: not run · our policy
- Unconfirmed changes: not run · our policy
- Bad input: not run · our policy
- Model requests: not run · nothing to check it against
- Sensitive questions: not run · nothing to check it against
- Folder boundary: not run · our policy
- Log leaks: not run · nothing to check it against
- Hidden content: not run · nothing to check it against
- Fake assistant turns: not applicable
- Token passthrough: not applicable
- Token audience: not applicable
- Sign-in redirect: not run · our policy
- Consent handling: not testable from outside
- Sign-in metadata: not applicable
2 exercised12 not run (reason given)4 not applicable
Each check ends in exactly one state: exercised, not run (with the reason), or not applicable (with the reason). 2 of the 14 checks that apply to it were exercised. We do not publish security-check outcomes for named servers. These 18 checks are separate from the record checks at the top of this page, which read public records only.
- 1Inventory
tool-listReads the declared tools, resources and prompts.exercised - 2Hidden instructions
description-poisoningLooks for hidden instructions in tool descriptions.exercised
- 3Real execution
real-executionCalls a tool and checks what really happens.This check calls the server's tools. ProtocolProbe calls no server's tools for anything it publishes, except for a server whose operator has claimed it and given permission (that server's page says so); an operator can run this check on their own server with our self-test command.not run · our policy - 4Secret leak
canary-leakPlants a fake secret and checks whether it leaks.This check needs at least one successful tool call to have something to check, and no tool was called.not run · nothing to check it against - 5Internal addresses
ssrfChecks whether a tool can be steered to internal addresses.This check calls the server's tools. ProtocolProbe calls no server's tools for anything it publishes, except for a server whose operator has claimed it and given permission (that server's page says so); an operator can run this check on their own server with our self-test command.not run · our policy - 6Unconfirmed changes
write-without-confirmationChecks whether tools that change data act without asking.This check calls the server's tools. ProtocolProbe calls no server's tools for anything it publishes, except for a server whose operator has claimed it and given permission (that server's page says so); an operator can run this check on their own server with our self-test command.not run · our policy - 7Bad input
error-handlingSends bad input and watches how the server answers.This check calls the server's tools. ProtocolProbe calls no server's tools for anything it publishes, except for a server whose operator has claimed it and given permission (that server's page says so); an operator can run this check on their own server with our self-test command.not run · our policy - 8Model requests
samplingChecks whether the server asks the client's model to act for it.This check needs at least one successful tool call to have something to check, and no tool was called.not run · nothing to check it against - 9Sensitive questions
elicitation-sensitive-dataChecks whether the server asks users for sensitive data.This check needs at least one successful tool call to have something to check, and no tool was called.not run · nothing to check it against - 10Folder boundary
root-boundaryChecks whether the server reaches outside the folders it was given.This check calls the server's tools. ProtocolProbe calls no server's tools for anything it publishes, except for a server whose operator has claimed it and given permission (that server's page says so); an operator can run this check on their own server with our self-test command.not run · our policy - 11Log leaks
logging-side-channelChecks whether log messages carry data they should not.This check needs at least one successful tool call to have something to check, and no tool was called.not run · nothing to check it against - 12Hidden content
audience-hidingChecks resources that hide content from the user.This check needs content the server returns, and nothing was read or called.not run · nothing to check it against - 16Sign-in redirect
open-redirectChecks the sign-in redirect for abuse.Testing the sign-in redirect means sending probes to the operator's sign-in service, which we do not do.not run · our policy - 17Consent handling
confused-deputyChecks consent handling when one service acts for another.Depends on the operator's own consent screen, which differs per server and cannot be tested from outside.not testable from outside
- 13Fake assistant turns
fake-assistant-turnChecks prompts that pose as the assistant's own words.The server exposes no prompts.not applicable - 14Token passthrough
token-passthroughChecks whether the server forwards a user's token to other services.The server opened a session without sign-in, so there is no token flow to check.not applicable - 15Token audience
token-audience-validationChecks whether tokens meant for another service are accepted.The server opened a session without sign-in, so there is no token flow to check.not applicable - 18Sign-in metadata
oauth-url-schemeChecks the published sign-in metadata for unsafe URLs.No sign-in (OAuth) metadata is published, so there are no sign-in addresses to check.not applicable
Source: our own test, 2026-11-17, mcp-runtime-engine@0.1.0. Which checks count and why follows our published scoring model.
What happened during the test?
Feature #8
The steps in order, as the test record holds them.
- 0 msStarted a read-only session with the server's remote endpoint
- 1,143 msConnected after 0 redirects. No credential was sent or needed.
- Read the inventory: 127 tools, 0 resources, 0 prompts.
- 5,417 msFinished: 2 checks exercised.
Reference
How is it classified?
18 fields
One value per field, each with its source. Fields written by AI models are marked. A field with no value says why.
“Not stated” means the source did not state it; “does not apply” means it does not apply to this kind of server; “our limit” means our own lookup failed. A linked value opens the directory filtered to the same value.
Cite or correct this page
Sources and corrections
Suggested citation
ProtocolProbe. “com.rivopress/rivopress: MCP server record.” Data checked 2026-11-17. https://protocolprobe.com/mcp/servers/com.rivopress/rivopress
Figures are valid for the date shown. Our facts on this page are CC BY 4.0: reuse them with a link and the check date. Quoted text (the publisher’s descriptions, website quotes, tool names) is not ours to license.
As JSON: this record in the API · API documentation.
Badge for your README
[](https://protocolprobe.com/mcp/servers/com.rivopress/rivopress)
It shows this server's record-check count: facts from public records, no tool called. It is not a security rating or a pass. It links here and updates after each data reload.
Something wrong, or is this yours?
If a fact here is wrong, tell us and we will re-check it. If you operate this server, you can run our checks on it yourself with the free self-test command; we call no server’s tools ourselves for anything shown here, except for a server whose operator has claimed it and given permission (that server's page says so).
Write to hello@protocolprobe.com · corrections log · methodology