Skip to main content
Glama
WebCake Storefront MCP

WebCake Storefront MCP

by vuluu2k

builder_ref

Read-only

Look up page-building references—element attributes, events, data bindings, schema, guides, and section templates—by selecting an action to compose valid storefront pages.

Instructions

Reference for composing pages: elements, attributes, events, bindings, schema, guides, section templates. Pick the operation with action and pass that action's arguments (help:true returns its full documentation and schema).

  • get_build_guide: Get the BuilderX page authoring guide: page shape, the grid layout model, styling, breakpoints, forms/data, and the build workflow.

  • get_intake_guide: Get the INTAKE questionnaire + build flow to run BEFORE creating a new site/store/page.

  • list_elements: List all BuilderX element/component types you can place on a page, grouped by category with a one-line summary and whether each is a container.

  • get_element: Get the full detail of an element type: category, container flag, summary, KEYS — one line per specials/config key the published renderer reads (`key: meaning · type · one of a|…

  • list_events: List every interaction EVENT you can attach to a node: the triggers (eventName: click/hover/success/submit/…) and the actions (open_page, scroll_to, toggle, open_popup, add_to_c…

  • list_bindings: List every dynamic-data BINDING target: the datasets (product, cart_item, order, order_item, post, category, customer, customer_address, …) and their exact field names ('product…

  • get_page_schema: Get the authoritative JSON Schema (Draft 2020-12) for a page source { sections: [...] } — the structural contract for every node (id/type/specials/runtime{style,config}/childr…

  • list_section_templates: Browse the designer-made section library (the editor's template picker): ready, styled blocks (hero, product showcase, testimonials, footer…) to start from instead of composing …

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": {
      "action": "<action>"
    },
    "name": "builder_ref"
  }
}

Input Schema

NameRequiredDescriptionDefault
helpNoReturn the action's full documentation and argument schema instead of running it
pageNoPage (default 1) [list_section_templates]
termNoSearch template names [list_section_templates]
typeNoElement type, e.g. [get_element]
limitNoPer page (default 12) [list_section_templates]
actionYesWhich operation to run
category_idNoCategory id (from the no-arg call) [list_section_templates]

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv2.8.0

TDQS

A3.8/5.0
Behavior4/5

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

The readOnlyHint=true annotation matches the description's purely consultative verbs (get, list, browse), so nothing is contradicted. Beyond the annotation it discloses a genuinely useful behavior: help:true returns an action's full documentation and argument schema instead of running it, which is the agent's escape hatch for detail the bullets truncate. It doesn't describe result shape or sizes, but as a read-only reference tool that burden is light.

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

Conciseness3/5

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

Front-loading is good: the dispatcher mechanic and the help:true escape hatch come first, before the action list. However, several bullets are cut off mid-sentence ('one of a|…', 'add_to_c…', "'product…"), which wastes tokens on incomplete fragments and makes the list read as pasted rather than authored. Every action does earn a line, but the lines are not finished.

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 seven-parameter, one-required dispatcher with no output schema, the description covers all eight enum values and explains the action/help mechanism, which is what an agent needs to invoke it correctly. The truncated action details leave gaps about what get_element and list_events actually return, but help:true is an explicit documented path to that information.

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

Parameters3/5

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

Schema description coverage is 100% and each parameter is already tagged with the action it belongs to (page/limit/term/category_id → list_section_templates, type → get_element), so the schema does the heavy lifting. The description's contribution is confirming the `action` dispatcher pattern, which is useful but marginal. Baseline 3 applies.

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 names a specific verb+resource class (reference for composing pages) and then enumerates all eight concrete operations, each with a distinct verb and object (list_elements, get_page_schema, list_section_templates). An agent can map any reference lookup to an action without opening the schema. It does not, however, distinguish this reference tool from sibling authoring tools such as build_page or compose.

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?

Per-action guidance is explicit in places: get_intake_guide says to run it BEFORE creating a new site/store/page, get_build_guide covers the authoring workflow, and list_section_templates is positioned as 'start from instead of composing' by hand. What is missing is a top-level rule for when to reach for builder_ref versus the sibling build/compose tools, and no explicit when-not conditions.

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