Skip to main content
Glama

XeoRank

by com.xeorank
OverviewDiscussionsAdmin

wp_create_page

Create a NEW DRAFT Elementor page OR blog post (set post_type='post' for a blog post; pages use the canvas template, posts the theme template). Safe — never touches existing/live pages). For a real design pass sections — the native Elementor CONTAINER spec (see wp_update_page for the shape + widget catalog, and elementor_search/elementor_get for exact widget fields); otherwise it seeds a heading+text. Requires writes enabled. If a Global Brand Kit is set, reference @tokens in widget styles (style.color:'@primary', style.typographyToken:'h1') instead of hardcoding hex/fonts — call wp_get_brand_kit first. Returns the new post_id.

Input Schema

NameRequiredDescriptionDefault
tagsNoComma-separated tag names or IDs. Connector v0.8.0+.
titleYesPage/post title
atomicNoEditor V4 ATOMIC spec (JSON array) for sites where Editor V4 is active: [{type: heading|paragraph|image|button|div|flex|grid|tabs, …}]; tabs = {type:"tabs", tabs:[{label, children:[…]}], active:0}. XeoRank emits valid V4 JSON (e-tabs/e-tabs-menu/e-tab/e-tabs-content-area/e-tab-content, typed envelopes, ids). wp_widget_schema("e-tabs") and wp_section_recipes("v4-tabs") show the shape. Raw elements also accepted via elementor_data/elements.
blocksNoGutenberg block markup (<!-- wp:heading -->…) — creates a BLOCK page instead of Elementor; plugin transport + Connector v0.3.0+
dry_runNoBuild + round-trip validate + return a preview (warnings, size) WITHOUT creating the page (no quota used)
headingNoOptional H1 heading text (used only if no sections)
site_idYesThe WordPress site ID
subtextNoOptional intro paragraph (used only if no sections)
sectionsNoPREFERRED for designs: native Elementor CONTAINER spec — [{direction,width,children:[{widthPercent,widgets:[{type,...}]}]}]
post_typeNopage (default) | post — use 'post' to create a blog post
categoriesNoComma-separated category names or IDs, e.g. "Guides, SEO". Names that do not exist are created. Needed for a taxonomy-driven archive — a Loop Grid queries by term, so an uncategorised post never appears in one. Connector v0.8.0+.
featured_imageNoFeatured image for a post: an attachment ID, or an image URL to sideload into the media library. REQUIRED for a post to appear in a Loop Grid or Posts widget — those render the thumbnail, so a post without one shows blank. Connector v0.8.0+.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.6/5.0
Behavior4/5

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

Annotations already declare destructiveHint=false and readOnlyHint=false, so the description goes further by asserting 'Safe — never touches existing/live pages', noting it creates a DRAFT, stating the write-enable prerequisite, and disclosing the return value ('Returns the new post_id'). It doesn't detail quota/rate-limit behavior beyond the dry_run note, but the added context is substantial.

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?

Information-dense and front-loaded with the core action and the page/post distinction. It is a long run-on with many parentheticals, but nearly every clause earns its place; only minor tightening is possible.

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

Completeness5/5

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

For a 12-parameter mutation tool with no output schema, it covers the design spec path, brand-kit integration, dry_run preview semantics, the seeded fallback, and states the return value. Nothing an agent needs to call it correctly 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 3 is the baseline, but the description adds real meaning beyond the schema: the precedence between `sections` and the heading/subtext fallback, how @tokens replace hardcoded hex/fonts, and the requirement to call wp_get_brand_kit first. This is genuine semantic value, not restatement.

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

Purpose5/5

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

States a specific verb+resource ('Create a NEW DRAFT Elementor page OR blog post') and immediately disambiguates the two variants via post_type. It clearly separates itself from siblings like wp_update_page, wp_create_template, and wp_create_menu.

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

Usage Guidelines5/5

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

Explicitly says when to use each mode (post_type='post' for blog posts; pass `sections` for a real design, otherwise it seeds a heading+text) and routes the agent to wp_update_page for the container shape, elementor_search/elementor_get for widget fields, and wp_get_brand_kit first when a Brand Kit exists. Prerequisites ('Requires writes enabled') are stated.

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

All XeoRank toolsInspect
Try in Browser
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources