Connect your LLM to Amazon's product catalog and display real-time results directly in chat. Easily browse, compare, and buy products — all inside your AI agent, chatbot, or tool.
Single tool with minimal schema definition, no parameter descriptions, and vague overall purpose. The tool 'search_for_products' has a basic structure but critically lacks parameter documentation and output schema specification. Code shows server is named 'firecrawl-mcp' but this is actually a product scraper, indicating confusion. No input validation, no error handling guidance, and no structured output documentation.
Search for products by query and return results with images
Parameter 'query' has no description. LLM cannot infer whether to pass product names, categories, SKUs, or free-form search text.
No output schema documented. Response structure is completely unknown, LLM cannot extract product IDs, images, or prices for downstream use.
Tool description 'Search for products by query and return results with images' is generic and under-specified. Does not explain: (1) Which product catalog? (2) What fields are returned? (3) Are results paginated? (4) What is the rate limit?
No error handling guidance. If a search fails or returns no results, the LLM has no recovery path.
Inferred effective spec: <=2025-11-25.
| Scored | Grade | Overall | Spec posture | Rubric |
|---|---|---|---|---|
| 2026-09-22 | F | 34 | <=2025-11-25 | v2 |
| 2026-03-09 | F | 0 | - | v1 |
No pagination support declared. If results can be large, LLM cannot request limit/offset parameters.
Server name mismatch: package.json and code identify server as 'firecrawl-mcp' version 1.7.0, but repo is 'Ecomm-MCP' for product scraping. This confusion will mislead users and cause integration issues.
PRODUCTS_TOOL object initialized empty ({}), the actual tool definition is hardcoded in the ListToolsRequest handler, not constructed properly. Tool properties are not visible in static analysis.