MPSTATS Ozon Product Search

This skill searches Ozon (Russia) products in the MPSTATS analytics database by Russian keyword, SKU list, brand name, or seller name. It is the entry point for Ozon product discovery and competitor lookup — downstream drill-downs (brand/category/seller/detail/trend) typically start from the IDs returned here.

Core Concepts

MPSTATS Ozon coverage: Ozon is Russia's largest general-category marketplace. MPSTATS indexes Ozon product listings and sales history. Per the official outputSchema, this endpoint returns the full Ozon product card (identity + sales, price, stock, rating, turnover, lost-profit, revenue-share, etc. — 39 fields total), shared with the brand / category / seller drill-down endpoints. In practice the endpoint's primary use is discovery — resolving a keyword / SKU / brand / seller into products — and runtime may leave metric fields sparse depending on coverage and the startDate/endDate window.

Language requirement: Keywords, brand names, and seller names must be in Russian (Cyrillic) — or the Latin-script form actually used on the Ozon storefront (e.g., adidas). If the user supplies an English or Chinese keyword, translate it to Russian first and note the translation.

At-least-one input rule: The input schema marks all four filters as optional, but the tool's business rule requires at least one of keyword / productIds / brandNames / sellerNames to be supplied. The four can be combined to narrow results.

Parameters

At least one of keyword / productIds / brandNames / sellerNames must be supplied.

API Usage

This tool calls the LinkFox tool gateway API. See references/api.md for calling conventions, request parameters, response structure, and error codes. You can also execute scripts/mpstats_ozon_product_search.py directly for ad-hoc queries.

Usage Examples

1. Keyword search — sneakers in Russian

{"keyword": "кроссовки", "pageSize": 50}

2. SKU batch reverse lookup

{"productIds": [1786874757, 151623766, 142257239]}

3. Brand-scoped discovery

{"brandNames": ["adidas", "Xiaomi"], "keyword": "наушники"}

4. Seller-scoped discovery

{"sellerNames": ["ООО Ромашка"], "pageSize": 100}

5. Dated window for period-specific search

{"keyword": "футболка", "startDate": "2025-02-01", "endDate": "2025-02-28"}

How to Chain with Other Ozon Skills

1. Keyword → drill-down: Search → pick productId → call mpstats-ozon-product-detail (batch metrics) or mpstats-ozon-product-trend (single-SKU time-series).
2. Brand discovery → brand drill-down: Use this skill to confirm the exact brand display name, then call mpstats-ozon-brand-products for full sales / stock / rating metrics.
3. Seller scouting → seller drill-down: Confirm the seller via this skill, read the sellerId from the result, then call mpstats-ozon-seller-products for the seller's full SKU map.

Display Rules

1. Lead with identity columns — productId, title, brand, sellerName should headline the table since this endpoint is primarily a discovery step. Add price / monthlySalesUnits / rating only when those fields are actually populated in the response.
2. Russian titles — preserve the original Russian title; optionally offer an English or Chinese translation on user request.
3. Pagination — when total exceeds the page size, tell the user the total count and suggest the next page or a narrower keyword.
4. Do not extrapolate on null metrics — a missing monthlySalesUnits here is not "zero sales"; if the user wants hard numbers, route to mpstats-ozon-product-detail (single SKU or batch card) or the *-products drill-down endpoints.
5. Error handling — when code / errcode is non-200, explain the reason from msg / errmsg and suggest adjusting inputs (supply at least one of the four filters, use Russian, narrow date range).

Important Limitations

• At least one filter required — empty payloads are rejected by the tool's business rule even though required is empty in inputSchema.
• Russian / Latin only — non-Russian keywords generally return empty results.
• Date range — endDate cannot be today or a future date; data is T-1.
• Result cap per page — pageSize max is 100; paginate for larger sets.
• Metric-field sparsity — the schema declares a full product card, but this endpoint often returns only identity fields. Treat price / sales / rating here as best-effort, not contractual.

User Expression & Scenario Quick Reference

Applicable — Ozon product discovery / identity resolution:

Not applicable — Needs beyond discovery:

• Reliable per-SKU sales / revenue / stock / rating metrics → use mpstats-ozon-product-detail (batch card) or the *-products drill-down skills.
• Time-series trend for a single SKU → use mpstats-ozon-product-trend.
• Wildberries or other non-Ozon Russian marketplaces → not covered here.
• Category-tree navigation / Russian category path lookup → use mpstats-ozon-category-products with a known path.

Boundary judgment: If the user wants to find or identify Ozon products, start here. If they already have an ID or a dimension (brand / category / seller) and want metrics under it, go to the corresponding drill-down skill directly.

Feedback:

Auto-detect and report feedback via the Feedback API when any of the following apply:

1. The functionality or purpose described in this skill does not match actual behavior
2. The skill's results do not match the user's intent
3. The user expresses dissatisfaction or praise about this skill
4. Anything you believe could be improved

Call the feedback API as specified in references/api.md. Do not interrupt the user's flow.

For more high-quality, professional cross-border e-commerce skills, set LinkFox Skills.