Skip to main content
Glama
Sign In
MCP Hub

MCP Hub

by airano-ir
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Hybrid

WordPress: Wp customizer changeset

wordpress_specialist_wp_customizer_changeset
Destructive

Inspect, publish, or discard a pending WordPress customizer changeset, letting you review queued changes before applying them or clear them when no longer needed.

Instructions

[UNIFIED] Inspect or commit the pending customizer changeset. action='get' returns the pending changeset payload (or {status:'empty'} when nothing is queued). action='apply' publishes it; action='discard' trashes it. S-24: apply requires the caller to also hold the customize cap (same bar as /wp-admin/customize.php); manage_options alone is not enough. Apply is racy with concurrent edits via the customizer UI — this is intentional and mirrors WP's own behaviour. Requires Airano MCP Bridge v2.17.0+.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "site": "<site>",
      "action": "<action>"
    },
    "name": "wordpress_specialist_wp_customizer_changeset"
  }
}

Input Schema

NameRequiredDescriptionDefault
siteYes
actionYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv3.14.0

TDQS

A4.5/5.0
Behavior5/5

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

Goes well beyond the annotations by splitting the read vs. destructive paths (get is safe and may return {status:'empty'}; apply/discard mutate), disclosing the extra capability requirement, the intentional race with concurrent customizer edits, and a minimum bridge version. These are exactly the facts an agent cannot infer from destructiveHint=true alone.

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?

Front-loaded with the core purpose, then mode-by-mode detail, then caveats. Nearly every clause earns its place; the '[UNIFIED]' tag and 'S-24:' internal ticket reference are minor noise for an external caller.

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?

For a two-parameter mutation tool with no output schema, the description covers the empty-state return, permission bar, concurrency behavior, and version prerequisite. What's missing is the return value of apply/discard and whether trashing is recoverable, which matters given destructiveHint=true.

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 0% and 'action' has no enum, so the description carries the full burden — it defines all three accepted values and their side effects, which is the critical missing semantics. It adds nothing about 'site' (presumably self-evident) and gives no format guidance, keeping it short of a 5.

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 pair and resource ('Inspect or commit the pending customizer changeset') and then enumerates all three modes with their effects. An agent knows exactly what the tool touches and which mode does what without opening the schema.

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?

Each action value is given a clear condition: 'get' for inspecting, 'apply' to publish, 'discard' to trash. The capability note ('apply requires the customize cap; manage_options alone is not enough') tells the caller when the call will fail. It stops short of naming sibling tools for related option/theme work, so no explicit alternative routing.

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

Deploy Server

Other Tools