MCP server that audits Shopify e-commerce stores by crawling live pages and analyzing store performance, SEO, and configuration
Single tool 'audit_store' has a basic description (89 chars) but critically lacks input parameter descriptions. The schema defines a 'url' parameter with only a type string and minimal description ('The store URL to audit (e.g., https://your-store.com)'). No output schema is documented anywhere in the codebase. The tool name is reasonable (verb_noun form) but the overall definition is sparse. No error handling guidance, no pagination, no structured output specification. The client examples show HTTP transport but the server implementation is not visible in the provided source, making it impossible to verify actual tool registration, error handling, or response structure.
Audits a Shopify store by crawling the live page and analyzing store performance, SEO, and configuration
No output schema documented. LLMs cannot plan downstream actions or extract structured data from audit results.
Parameter 'url' lacks actionable description. Should specify format (must start with https://), length constraints, and what constitutes a valid Shopify store URL.
No error handling guidance. Tool description mentions 10-20s crawl time but does not document timeout behavior, network failure recovery, or what errors the LLM should expect.
Server implementation not visible in source. Tool registration, actual response structure, and error handling cannot be verified.
No tool annotations (readOnlyHint, destructiveHint, idempotentHint). Tool is marked READ_ONLY in metadata but this is not reflected in the schema or description.
| Scored | Grade | Overall | Spec posture | Rubric |
|---|---|---|---|---|
| 2026-09-23 | D | 50 | 2026-07-28+ | v2 |