Skip to main content
Glama

royal-mcp__wp_get_posts

Read-onlyIdempotent

Get WordPress posts (supports custom post types). Each item includes date (publish date, site local time), modified (last change, ISO 8601 UTC) and content_length (bytes of stored post_content) so you can size-check before fetching — on page-builder sites a short page can still carry a very large body. Sort with orderby / order; use modified_after to find posts edited recently. Content edits, Royal MCP custom-field tools, ACF field writes (acf_update_field) and Elementor writes update modified; other plugins changing only custom fields may leave it unchanged. (site: demo.royalplugins.com) Through Royally: read-only, runs straight away.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "royal-mcp__wp_get_posts"
  }
}

Input Schema

NameRequiredDescriptionDefault
orderNoasc or desc. Default: asc (A to Z) for orderby title, desc for every other sort.
searchNoSearch term
statusNoPost status (publish, draft, etc)
includeNoUp to 100 post IDs. Returns exactly those posts (any status you can read, trashed posts included) in this order; per_page, search, orderby, order and modified_after are ignored (invalid values are still refused).
orderbyNoSort field (default date, the publish date). modified sorts by the last change.
site_idNoSite to run this tool on: 8ef2e52b-bd07-4671-a363-ebe8b480b65c (https://demo.royalplugins.com)
per_pageNoNumber of posts (max 100)
post_typeNoPost type slug (default: post). Use wp_get_post_types to discover available types
with_contentNoWhen true, each item adds content_text (content with shortcodes and tags removed, whitespace collapsed, at most 3000 characters) and content_truncated.
modified_afterNoOnly items last modified after this moment: a date (2026-11-01) or date and time (2026-11-01T09:30:00Z). No timezone means UTC.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed4 schema fields changed
    • changedInput schema / properties / include / description
      Previous value: -"Up to 100 post IDs. Returns exactly those posts (any status you can read, trashed posts included) in this order; per_page and search are ignored."New value: +"Up to 100 post IDs. Returns exactly those posts (any status you can read, trashed posts included) in this order; per_page, search, orderby, order and modified_after are ignored (invalid values are still refused)."
    • addedInput schema / properties / modified_after
      Added value: +{
      +  "description": "Only items last modified after this moment: a date (2026-11-01) or date and time (2026-11-01T09:30:00Z). No timezone means UTC.",
      +  "type": "string"
      +}
    • addedInput schema / properties / order
      Added value: +{
      +  "description": "asc or desc. Default: asc (A to Z) for orderby title, desc for every other sort.",
      +  "enum": [
      +    "asc",
      +    "desc"
      +  ],
      +  "type": "string"
      +}
    • addedInput schema / properties / orderby
      Added value: +{
      +  "description": "Sort field (default date, the publish date). modified sorts by the last change.",
      +  "enum": [
      +    "date",
      +    "modified",
      +    "title",
      +    "menu_order",
      +    "id"
      +  ],
      +  "type": "string"
      +}
  2. Added
  3. Removed
  4. First observed

TDQS

A4.2/5.0
Behavior5/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Beyond the readOnly/non-destructive annotations, it discloses that modified is updated by content edits and by Royal MCP custom-field, ACF, and Elementor writes — but not by third-party custom-field-only changes. It also explains timezone handling for date/modified and the byte-based content_length rationale for page-builder sites, which is exactly the kind of non-obvious behavior an agent needs.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Purpose is front-loaded and each subsequent sentence carries real information about output fields, sorting, and change-tracking semantics. The parenthetical '(site: demo.royalplugins.com)' duplicates the site_id enum in the schema and is the one piece of dead weight.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With no output schema, the description does the work of naming the returned per-item fields and their formats, plus the with_content payload shape. It omits pagination and total-count behavior, which matters for a 10-parameter list tool, but nothing about correct invocation is missing.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so the baseline is 3; the description earns extra credit by explaining the orderby/order interaction, the practical purpose of modified_after, and why content_length matters before requesting content. It says nothing about the include-vs-per_page override behavior or search scoping, which are documented only in the schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The opening sentence states a specific verb and resource — 'Get WordPress posts' — and notes the custom-post-type scope, which distinguishes it from page- or single-post-oriented siblings. It does not explicitly name alternatives such as wp_get_post, wp_get_pages, or wp_search, so sibling routing is left partly to inference.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

It gives concrete operational guidance: sort via orderby/order, use modified_after to find recently edited posts, and size-check with content_length before deciding to pull bodies. It stops short of stating when to prefer this over wp_search or wp_get_post, and offers no explicit exclusions.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources