MCP App Store
by KeenEthics
PandaFind icon

PandaFind MCP Server for ChatGPT

By 17labs.ai

Overview

AliExpress is full of niche products, messy titles, specific variants, and listings that are hard to find unless you know the right marketplace wording. PandaFind lets you describe what you want in plain language, then helps your assistant search AliExpress directly and compare the results with more context. Use PandaFind to: - Search AliExpress without knowing the perfect keywords - Find niche products, specific variants, and cheaper alternatives - Compare similar listings before you buy - Check whether a product from another marketplace is just an AliExpress item with a markup - Decide whether lower price, faster shipping, easier returns, or seller trust matters most

How to connect

  1. ChatGPT: Open the PandaFind listing in the ChatGPT app directory and choose Connect. ChatGPT listing PandaFind exposes 5 tools here.

Tools

get_product_description_batch

ChatGPT
Returns what the seller wrote about one to five AliExpress products: the item specifics (brand, material, size, model, compatible models and similar attributes), the package size and weight, and the seller's description text, in the target language. Answers questions such as what a product is made of, how big it is, what it fits or what is in the box. Does not return prices, shipping or variants. Figures that exist only in the listing images are not included. A product that cannot be sold to the destination or is no longer listed is reported as such.

get_product_details_batch

ChatGPT
Use this tool if the user is asking about a specific AliExpress product, or if, after calling search_products or search_products_batch, you need shipping, SKU, rating, or delivery details for one or more shortlisted products. Returns one row per SKU: this is the only tool that reads the SKUs a listing sells, each with the properties that separate it from the others and its own price, shipping and rating. Do not use for first-pass discovery. Pass only product IDs; do not pass previous URLs, search_result_id, or pandafind_result_id. Reuse the same zero-based intent_index and turn_index as the search when details happen in the same user-visible assistant turn. Increment intent_index when the semantic shopping goal changes; humidifier followed by something to dry clothes quickly is a new intent. Do not provide model_name, model_mode, or any assistant self-reported runtime/model field. Pass the full shortlist in one call; do not call this tool once per product. AliExpress returns at most 20 SKUs per product. Set ship_to_country from the delivery destination you can determine; a destination is not a language, so never read it off how the user writes. Ask the user only if you genuinely cannot determine one, then retry with it set. Individual failures are returned per item and do not fail the whole batch. Returned item URLs are PandaFind redirect URLs when tracking is enabled.

resolve_product_cards

ChatGPT
Widget-only. Loads product cards that show_product_cards could not draw from cache: product references from the product detail endpoint in one call, SKU references from the SKU detail endpoint.

search_products

ChatGPT
Find candidate AliExpress products from one compact marketplace query. Use short marketplace phrasing, not the users full sentence. For cheapest or price-comparison tasks, make multiple tool calls with different compact queries when variants, exact-model titles, or noisy SEO could hide the real cheapest option. When several query branches are independent, prefer issuing them in parallel or in the same assistant turn if your client supports multi-call tool use; do not wait for one branch before launching another unless the next query depends on observed results. Do not rely only on an exact model-name search when looking for the cheapest matching listing: also try one compact characteristic-led query built from the product head plus key specs so you can catch cheaper listings whose titles emphasize features instead of the canonical model name. Unless the user explicitly asks for a different presentation, every mentioned product must include a bold clickable markdown title plus the visible price immediately after it in parentheses, formatted like **[Product Title](URL)** (24.50 EUR). Do not mention a product without its link when a URL is available, and do not omit the visible price when one is available. After calling this tool, rank results by target-variant relevance first and visible price second, explain any partial matches, and explicitly flag trap listings such as mixed-capacity variants, lower-capacity defaults, without-battery listings, case-only listings, or battery-not-included listings.

show_product_cards

ChatGPT
Display products you found with PandaFind as visual cards. Use this whenever you recommend, shortlist or compare products from a PandaFind search, including when you also compare them with products from other sources: call it before writing the comparison, then discuss them by name. Pass only references in products, in the order you want them; the server keeps everything else from the search, so there is nothing to repeat. To show a specific SKU or its shipping, call get_product_details_batch first and pass {product_id, sku_ids} with the SKUs you picked. Show a curated handful of the best matches rather than everything you looked at.

Capabilities

Interactive

Similar Apps

Listed on MCP App Store

Listed on MCP App Store

Add this badge to your site or README. It links to this page.

HTML

<a href="https://mcp-app-store.keenethics-labs.com/app/pandafind"><img src="https://mcp-app-store.keenethics-labs.com/badges/listed-on-mcp-app-store.svg" alt="Listed on MCP App Store" width="220" height="44"></a>

Markdown

[![Listed on MCP App Store](https://mcp-app-store.keenethics-labs.com/badges/listed-on-mcp-app-store.svg)](https://mcp-app-store.keenethics-labs.com/app/pandafind)