Skip to main content
Glama
SZhukovWork

wildberries-mcp

by SZhukovWork

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
WB_DESTNoWB delivery-region id. By default WB's own IP-based detection is used.auto
WB_PROXYNoProxy URL for both HTTP and the browser, e.g. http://user:pass@host:3128
WB_ACCOUNTNoSet to '1' to enable account mode (cart, wallet price).
WB_HEADLESSNo0 shows the browser window while minting the token (debugging).1
WB_CACHE_DIRNoWhere the anti-bot session is kept.~/.cache/wildberries-mcp
WB_MIN_INTERVALNoSeconds between storefront API calls. Default is 3.0.3.0

Instructions

Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.

This server publishes no instructions, or was last inspected before Glama recorded them.

Capabilities

Features and capabilities supported by this server

Protocol revision2025-11-25

CapabilityDetails
tools
{
  "listChanged": false
}
prompts
{
  "listChanged": false
}
resources
{
  "subscribe": false,
  "listChanged": false
}
experimental
{}

Tools

Functions exposed to the LLM to take actions

NameDescription
search_productsA

Search Wildberries like the site does: real pages, sorting and a price window.

Each item has the live price (and pre-discount price), per-article rating and review count, stock, seller with its rating, WB's delivery estimate in hours for the region, and the product-group id. Fields without data are omitted (no rating = no reviews yet); in_stock_qty 0 means sold out. total_found is how many products WB matched; has_more tells whether another page exists. Search prices come from the result feed — confirm finalists with get_product.

get_productA

Full, live product card for one article.

Returns the current price (per size), stock, delivery estimate, seller with its legal entity, the article's own rating with star distribution next to the merged group rating, seller-filled characteristics, description, package contents, a weekly price-history summary and — optionally — the other articles merged into the same product group with their live prices.

get_price_historyA

Weekly average prices WB keeps for an article, next to the live price.

Each point is WB's average price for one week (stamped with a date); weeks without data are absent. The last point is not the current price — use current_price_rub. With 0–1 points no trend can be claimed.

get_reviewsA

Buyer reviews with date, stars, text, pros, cons, bought variant and seller reply.

Also returns the star split of this article's ratings found in the review feed and the merged group's rating, so it is clear which one a headline number refers to. The feed lists reviews that have text and may hold fewer ratings than the card counts — the card rating (get_product) is the one shown on the site.

compare_productsA

Live side-by-side offers for up to 50 articles in one request.

Per article: price, pre-discount price, discount, per-article rating and reviews, stock, seller and rating, delivery estimate. Articles WB has no offer for (removed or sold out in this region) are listed with a reason.

Prompts

Interactive templates invoked by user choice

NameDescription

No prompts

Resources

Contextual data attached and managed by the client

NameDescription

No resources

TDQS

A4.4/5.0

Scored across 5 tools

Disambiguation4/5

Each tool has a clear primary purpose (fetch one product, search, history, reviews, compare), but get_product and compare_products overlap for a single article, and get_reviews vs get_product both surface rating info. Descriptions clarify the differences, so ambiguity is low but not zero.

Naming Consistency5/5

All tools follow a consistent verb_noun pattern: get_product, search_products, get_price_history, get_reviews, compare_products. The verbs (get, search, compare) and nouns are clear and uniform.

Tool Count5/5

5 tools is well-scoped for a read-only product data server. Each tool addresses a distinct need—single product detail, search, price history, reviews, and multi-product comparison—without unnecessary duplication or bloat.

Completeness5/5

For a marketplace data retrieval server, the tool set covers the core workflows: finding products, deep-diving a product, checking price trends, reading reviews, and comparing offers. No obvious gaps for the stated purpose; it's read-only so CRUD operations are not expected.

Maintenance

ActivityMaintained
ResponsivenessNo issues