Skip to main content
Glama
WebCake Storefront MCP

WebCake Storefront MCP

by vuluu2k

theme

List custom site designs, semantically search marketplace templates by natural language, and create new sites from selected templates via action-based operations.

Instructions

Site themes and templates. Pick the operation with action and pass that action's arguments (help:true returns its full documentation and schema).

  • list_themes: List all custom themes of the site.

  • semantic_search_themes: Semantic search across the theme marketplace using bge-m3 embeddings (cosine similarity).

  • list_template_themes: Search/list the public Webcake template marketplace (api.storecake.io).

  • create_site_from_template: Create a NEW site from a marketplace TEMPLATE (the dedicated "use this template" API).

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": "theme"
  }
}

Input Schema

NameRequiredDescriptionDefault
qNoKeyword to search themes [list_template_themes]
helpNoReturn the action's full documentation and argument schema instead of running it
langNoLanguage code (default 'vi') [list_template_themes]
nameNoName for the new site [create_site_from_template]
pageNoPage number (default 1) [list_template_themes]
slugNoURL-safe slug for the new site (auto-generated if omitted) [create_site_from_template]
limitNoNumber of matches to return (default 5, max 10) [semantic_search_themes, list_template_themes]
queryNoNatural-language description of the desired website (industry + features) [semantic_search_themes]
actionYesWhich operation to run
theme_idNoMarketplace theme id (from semantic_search_themes / list_template_themes) [create_site_from_template]
switch_toNoSwitch the session to the new site after creating it (saved for next session) [create_site_from_template]

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv2.8.0

TDQS

A3.6/5.0
Behavior3/5

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

Annotations only supply readOnlyHint=false for the whole tool, which is a coarse signal since three of four actions are reads. The description adds real context: help:true returns full documentation and schema, create_site_from_template creates a NEW site, and switch_to persists the session switch for the next session. It does not disclose what the create action returns, whether creation is reversible, or permission requirements.

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?

The definition is front-loaded with the routing instruction and then a bulleted action list, so the agent can scan it quickly. Every line corresponds to a real action; only the repeated 'action' framing is slightly redundant.

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

Completeness3/5

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

For an 11-parameter multiplexed tool with no output schema, the description covers action selection but not outcomes — notably no hint that create_site_from_template returns an identifier used to chain into page or publish_site operations, and no correction of the coarse readOnlyHint=false across read-only list actions. The help:true escape hatch mitigates but does not close this gap.

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 its owning action, so the schema carries most of the load. The description adds the meta-behavior of help:true and tells the agent to pass action-specific arguments, but does not clarify ambiguous pairs like q versus query or explain which arguments are ignored per action.

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?

The description names the resource (site themes and templates) and enumerates four distinct operations with specific verbs: list custom themes, semantic search the marketplace, list public templates, and create a new site from a template. The parenthetical 'the dedicated "use this template" API' separates create_site_from_template from a generic create_site sibling without the agent needing to inspect 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 Guidelines3/5

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

Within the tool, each action is described well enough to choose between reading a theme list, semantically searching, or creating a site from a template. However, it gives no guidance on when to use this tool at all versus siblings such as create_site, clone, or build_page, and no exclusions or prerequisites for the mutating action.

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