MCP server for Mercado Libre & Shopee affiliate tools — search products, generate links, analyze listings, create AI copy
Server has 6 tools with complete input schemas and descriptions. Naming follows verb_noun convention (search_, generate_, analyze_, trending_, commission_). However, descriptions lack specificity about when to use each tool vs. alternatives, parameter descriptions are minimal, and output schemas are entirely undocumented. No error handling guidance. Tools are read-only but lack explicit annotations. Missing details on API dependencies, rate limits, and failure modes.
Get a quality score (0-100) for any Mercado Libre product. Analyzes title, photos, description, attributes, price, and sales. Returns score breakdown and improvement suggestions.
Calculate expected affiliate earnings for a product based on clicks, conversion rate, and commission percentage.
Generate a tracked affiliate link for any Mercado Libre or Shopee product. Appends your affiliate tracking ID to the URL.
Generate AI-powered marketing copy for a product, optimized for specific channels (TikTok, Reels, WhatsApp, Telegram, Blog). Returns ready-to-post text with hashtags and CTA.
Search products on Mercado Libre or Shopee with affiliate commission estimates. Returns product list with title, price, image, commission rate, and estimated earnings.
Get trending products on Mercado Libre or Shopee by category. Returns top products ranked by sales velocity with commission estimates.
Output schemas completely undocumented. No specification of response structure, field types, or pagination. LLMs cannot plan downstream tool calls or extract required data.
Parameter descriptions are minimal or missing context. E.g., 'category' in search_products lacks explanation of format (MLB1051 example given but not documented as required format). 'campaign' in generate_affiliate_link marked optional but no guidance on format or use case.
No error handling or recovery guidance. Tools lack descriptions of failure modes (API unavailable, invalid product ID, rate limits). LLM has no guidance on retry strategy or fallback actions.
| Scored | Grade | Overall | Spec posture | Rubric |
|---|---|---|---|---|
| 2026-09-23 | D | 52 | 2026-07-28+ | v2 |
Tool descriptions do not explain when to use each tool vs. alternatives. E.g., search_products vs. trending_products distinction unclear. No guidance on prerequisites or dependencies.
No tool annotations (readOnlyHint, destructiveHint, idempotentHint). All tools are read-only but this is not declared in schema, forcing LLM to infer safety properties.