Skip to main content
Glama
yandex-market-mcp

yandex-market-mcp

by SZhukovWork

yandex-market-mcp

English · Русский

An MCP server that gives LLM agents live, honestly-labelled data from Yandex Market: search with real pages, the site's sort orders and price windows; seller cards with the three prices kept apart; all sellers' offers of a product; reviews at the right level; buyers' questions; seller details with the legal entity.

Buyer side: reads the public storefront pages, no Yandex account needed. Looking for your seller cabinet (the official Partner API)? That is a different tool, e.g. dontsovcmc/mcp-server-yandex-market-seller.

Why another Yandex Market server

Market's pages are full of numbers that look like one thing and are another. Scrapers that take the big number on the page return data a buyer never pays. This server is built around not doing that:

Market trap

What this server does

The big green price on tiles, cards and in schema.org data is the price with the Yandex Pay card; the plain price is visible only in the «Детали цены» popup

price_rub = without the card (from the site's own price-details popup, cross-checked with the cart price), price_with_pay_card_rub = with the card, price_before_discount_rub = crossed-out. A missing plain price is null with a reason — the Pay price is never substituted

«Скидка 41%» is counted from the Pay-card price

discount_percent_vs_pay_price (the site's number) next to discount_percent_without_card

The search price filter and price sorting work on the Pay-card price

Every answer says so (price_filter.basis, sort_basis)

The rating on a card belongs to the seller's card, which can pool several different products (one seller's card pools seven Fiskars axes, 745 ratings)

rating_of_this_card with pools_other_products, checked against the SKUs of the reviews shown on the card; get_reviews(scope="variant") returns only this product's reviews

«Отзывы и оценки у всех продавцов» is a model group that merges different products (JBL Tune 520BT + 720BT + 770NC)

model_group_rating with an explicit scope; every model review says which product it is about

Page 1 of "popular" is almost entirely ads

sponsored on every tile, sponsored_on_page, optional filtering; the instructions steer depth to price sorting and windows

One product from several sellers = several tiles; model_id merges different products

Tiles deduplicated by offer id; same_sku_several_offers groups sellers of one SKU; the instructions say never to dedupe by model id

Promo codes and «−200 ₽ с доставкой по клику» look like price cuts

conditional_offers with threshold, code and end date — never subtracted; a promo that exists in the data but is not shown on the card is not offered

Cross-border offers, markdown («Уценка»), «Версия: для других стран», «Оригинал»

cross_border with the site's duty rule (order above 200 € or 31 kg), markdown with the seller's condition text, version_on_card, and «Оригинал» explained as "the seller provided documents"

Market picks the city from the IP; lr and yandex_gid are ignored, choosing an address needs a login

No fake city parameter: every answer echoes the region from Market's own page, and a loud note appears if it is not the expected one (VPN)

«6.9K оценок», «72K»

Numbers with approximate: true (exact counts are used where the page has them)

Every normal page contains an empty CaptchaService widget; real captchas and "empty frames" (a page with no data) do happen

Captchas are recognised by URL and SmartCaptcha markers only; empty frames and foreign pages are retried once, then reported as errors, never as data

Every response carries fetched_at (UTC) and city.

Related MCP server: wildberries-mcp

Tools

Tool

What it returns

search_products(query, page, sort, price_min, price_max, include_sponsored)

Page 1 = 8 tiles, later pages 16; sort popular (default) / price_asc / price_desc / rating; total_found, page_count, has_more, positions. Per item: offer / card / model / SKU ids, title, URL, three prices and discounts, seller and business_id, sponsored, rating of the seller's card with count and low_evidence, badges, signals («Уценка», «Из-за рубежа»), stock, delivery dates

get_product(product, include_specs, include_description, include_seller_legal)

One seller's card (product = card id or /card/ URL; specs on, description and legal entity off by default): three prices + conditional_offers + split flag; seller (rating, exact ratings count, orders, years on Market, status; legal entity on request); delivery options with dates and prices for the IP city; rating of the card with stars and the pooling check; «Все N предложений от X»; badges with their meaning; cross-border / markdown / version flags; stock; characteristics; description

get_offers(model_id, sku_id, sort)

All sellers' offers of one product as tiles (sort price_asc by default, also popular / price_desc / rating / delivery) and the labelled model-group rating

get_reviews(product, scope, sort, page)

10 per page; scope card (default) / variant / model; sort helpful (default) / newest / best / worst. Date (ISO; «3 января», «Вчера» resolved), stars, pros, cons, comment, votes, photo count, the product each review is about

get_questions(product, page)

10 per page; questions with the answers shown on the site, exact dates, by_seller

get_seller(business_id)

Rating, exact ratings count and star split, orders, years on Market, status; legal entity (name, INN, OGRN, address, cross-border flag)

compare_products(products)

Up to 10 cards side by side: three prices, card rating with the pooling flag, seller, fastest delivery, «все предложения от»

Author names, user ids and order numbers never appear in answers; names in sellers' greetings («Здравствуйте, Анна!», «Анна, добрый день!»), e-mails and phone numbers in texts are masked.

Requirements

Measured on 2026-09-25 (Linux, Python 3.13, a Russian home IP):

Python

≥ 3.10, with uv (or pip)

Browser

Not needed. Plain HTTP with a Chrome TLS fingerprint (curl_cffi) gets the same pages a browser does

Display

Not needed

Docker

Not needed

Disk

≈ 85 MB for the environment (curl_cffi 38 MB, the rest is the MCP SDK and pydantic)

Memory

Peak RSS of the server process 110–113 MB during a full run of all tools (two runs; pages are 1.3–2.6 MB of HTML)

Cold start

0.4–0.5 s until the MCP client sees the tools (0.7 s via uvx with a warm uv cache); no warm-up requests

Request time

A page answers in 0.6–1.2 s; requests are spaced 4–5 s apart, so a call takes ≈ 1 s when idle, ≈ 5 s back-to-back; get_product with the legal entity 14–16 s (3 requests); compare_products ≈ 5 s per card

Network

A Russian home or residential IP. Market maps the city from it; datacenter IPs abroad have been reported to get a captcha at once

Install

Claude Code:

claude mcp add yandex-market -- uvx --from git+https://github.com/SZhukovWork/yandex-market-mcp yandex-market-mcp

Any MCP client (claude_desktop_config.json, .mcp.json, …):

{
  "mcpServers": {
    "yandex-market": {
      "command": "uvx",
      "args": ["--from", "git+https://github.com/SZhukovWork/yandex-market-mcp", "yandex-market-mcp"]
    }
  }
}

From a checkout: uv venv && uv pip install -e . && .venv/bin/yandex-market-mcp.

Configuration (environment variables)

Variable

Default

Meaning

YM_EXPECTED_REGION

54 (Екатеринбург)

Region id you expect Market to assign to your IP (213 Москва, 2 Санкт-Петербург). If the page says otherwise, answers carry a WARNING note — usually a VPN. It does not change the city: nothing can, without logging in

YM_MIN_INTERVAL

4.0

Seconds between requests (never below 3). The IP is usually shared with your own browsing

YM_CAPTCHA_COOLDOWN

1800

After a captcha the server does not query the site for this many seconds, also across restarts

YM_RATE_LIMIT_COOLDOWN

600

The same pause after HTTP 403 / 429 persisted through one retry

YM_PROXY

—

Proxy URL, e.g. http://user:pass@host:3128 (the city then follows the proxy's IP)

YM_CACHE_DIR

~/.cache/yandex-market-mcp (honours XDG_CACHE_HOME)

Where the cookies (session.json, 0600; directory 0700) and the pause marker live

yandex-market-mcp status shows whether a pause is active; yandex-market-mcp unblock clears it (for example after you solved the captcha in your own browser).

What the numbers mean

  • price_rub — the price without the Yandex Pay card for an anonymous buyer in the reported city. Use it for comparisons and the landed price. price_with_pay_card_rub applies only when paying with the Pay card. price_before_discount_rub is the crossed-out «Обычная цена» and can be inflated (Fiskars X21 was seen at «79 567 → 33 915» while honest sellers ask about 9 000).

  • conditional_offers — promo codes and offers with conditions (minimum order, delivery mode, shop subscribers). They are listed, never subtracted.

  • rating_of_this_card — the seller's card; pools_other_products: true means the reviews shown on the card are partly about other products of the seller. model_group_rating — all sellers of a Market "model", which can merge different products. There is no separate rating of one variant on Market; its reviews are available with get_reviews(scope="variant"). low_evidence = fewer than 10 ratings.

  • Delivery — dates and prices for the IP city without an address, as the card shows them; «Доставка Маркета» options are often 0 ₽, sellers' couriers can cost more. A missing price means unknown.

  • stock_left — units the offer has according to the page.

  • all_offers.from_pay_card_price_rub — «Все N предложений от X»: X is the lowest price with the Pay card.

Limitations

  • City = the IP's city. Market ignores lr / yandex_gid; choosing an address requires a login. Prices and delivery for another city are not available. Whether prices depend on the city at all was not verified.

  • Search depth: at most 30 pages (≈ 470 items) per query, sort and price window. Page 1 has 8 tiles, later pages 16. With more results the answer carries depth_cap: split the price range into windows.

  • get_offers shows at most 16 offers per sort order. Market's server-rendered offers page ignores page (checked: page 2 returns page 1 again). Call it with other sorts to see more offers.

  • No price history — Market removed it in 2022 and the pages do not carry it.

  • Anonymous prices only. The site says «Войдите, и станет дешевле»: prices after login, personal discounts, split amounts, Plus points and cashback are not available (split is a yes/no flag; the raw isPersonalDiscount flag is passed as personal_discount_flag_raw, its meaning unconfirmed).

  • Search totals count loose matches and drift: the same query reported 2308 and, an hour later, 419 results; a nonsense query «finds» thousands. Check titles; do not treat total_found as a catalogue size.

  • Legal entity of a seller comes from the site's seller-info popup, which the page loads with a POST to /api/render-lazy — a path that robots.txt disallows. Only get_seller and get_product(include_seller_legal=true) make that request; everything else reads regular pages.

  • Customs duty — Market's rule for cross-border orders (duty above 200 € or 31 kg per order) is passed on; a fixed «Пошлина N ₽» is reported only when a tile shows one.

  • Unofficial: the server reads the state Market embeds in its pages. Market changes it without notice; parsers are isolated in parse.py and covered by tests on recorded pages. Implausible pages become errors.

  • Captcha: the server never solves or bypasses it. It stops and pauses (30 min by default).

Roadmap

  • Optional account mode (personal prices after login) and the cart — later.

  • Checkout, payment and address changes are out of scope.

Development

uv venv && uv pip install -e '.[dev]'
.venv/bin/pytest              # offline tests on recorded, anonymised pages
.venv/bin/pytest -m live -s   # every tool over MCP stdio against the live site (14 requests, ~1.5 min)

Please run the live test rarely: the IP is shared with your own browsing, and a captcha pauses the server for 30 minutes.

Disclaimer & credits

Not affiliated with Yandex. The server reads Market's internal page state, not an official API; use it for personal price research at a human request rate and respect Market's terms of use. Ideas for recognising real captchas (URL and SmartCaptcha markers, not the substring "captcha"), "empty frame" pages and retrying an empty redirect come from Vladimir-Human/ru-marketplace-mcp (MIT); no code was copied.

License: MIT.

Available Tools

7 tools
compare_productsA
Read-onlyIdempotent

Side-by-side rows for up to 10 seller cards: the three prices, rating of the card, seller, delivery.

One request per card, sequentially (about 5 s each). A card that fails gets an error row; a captcha or rate limit stops the whole comparison.

Inputs: products (required). Returns: object

get_offersA
Read-onlyIdempotent

All sellers' offers of one product (the site's «Все N предложений»), as tiles.

Market's server pages show the first 16 offers per sort and ignore page (checked 2026-09-25), so this returns at most 16; call again with another sort to see more (dedupe by offer_id). Also returns the model group's rating — labelled: it can merge different products. One request.

Inputs: sku_id (required), model_id (required), sort. Returns: object

get_productA
Read-onlyIdempotent

One seller's product card, live: the three labelled prices, promo conditions, delivery, seller.

Also: rating of this seller's card with stars and a check whether the card pools other products, «Все N предложений от X» (X = lowest Pay-card price; list them with get_offers), badges with their real meaning, cross-border / markdown / version flags, stock, characteristics and question count. One request (three with include_seller_legal).

Inputs: product (required), include_specs, include_description, include_seller_legal. Returns: object

get_questionsA
Read-onlyIdempotent

Buyers' questions about a card with the answers shown on the site; by_seller marks the seller's answers.

Dates are exact. Names of buyers are never returned; greetings with a name in answers are masked. One request.

Inputs: product (required), page. Returns: object

get_reviewsA
Read-onlyIdempotent

Buyer reviews with date, stars, pros, cons, comment, votes, photo count and the product each is about.

The header numbers (rating, counts, stars) are the site's for the chosen scope; for scope="variant" the site still shows the whole card's numbers (labelled). Items without text are ratings only. Author names and order numbers are never returned. One request.

Inputs: product (required), page, sort, scope. Returns: object

get_sellerA
Read-onlyIdempotent

A seller's storefront header (rating, ratings count, orders, years on Market, status) and legal entity.

The legal entity (name, INN, OGRN, address, cross-border flag) comes from the site's seller-info popup, loaded with a POST to Market's /api/ (robots.txt Disallow) — two requests.

Inputs: business_id (required). Returns: object

search_productsA
Read-onlyIdempotent

Search Yandex Market like the site: real pages, the site's sort orders and a price window.

Each item: offer/card/model/SKU ids, title, card URL, the three labelled prices (without the Pay card, with it, crossed-out), discounts, seller, sponsored flag, rating of this seller's card with its count, badges, cross-border / markdown flags, stock and delivery dates. One request per call.

Inputs: query (required), page, sort, price_max, +2 more. Returns: object

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    TDQS

    A4.2/5.0

    Scored across 7 tools

    Disambiguation5/5

    Each tool targets a distinct resource and action: search, single product card, all offers, comparison, reviews, questions, and seller info. Even the overlapping get_product and get_offers are clearly separated by scope (one seller vs. all sellers).

    Naming Consistency5/5

    All tool names follow a consistent verb_noun snake_case pattern: search_products, get_product, get_offers, compare_products, get_reviews, get_questions, get_seller. No mixed conventions or vague verbs.

    Tool Count5/5

    Seven tools is well-scoped for a marketplace research API. Each tool covers a distinct user need without redundancy or bloat.

    Completeness5/5

    The set covers the full product research lifecycle: discovery (search), deep dive (product, offers, compare), social proof (reviews, questions), and seller trust (seller info). No obvious dead ends or missing core operations for a read-only marketplace tool.

    Related MCP Connectors

    Related MCP Servers

    • A
      license
      A
      quality
      B
      maintenance
      Enables AI agents to run RU-first web searches through the Yandex index and extract web pages into clean reader-mode Markdown, bypassing anti-bot blocks.
      3
      36 npm
      MIT
    • A
      license
      A
      quality
      B
      maintenance
      Enables LLM agents to query live Wildberries marketplace data — product search with pages, sorting, price filters, per-article ratings and reviews, weekly price history, and seller legal details — with honest, sanity-checked answers and automatic anti-bot handling.
      5
      MIT
    • A
      license
      A
      quality
      C
      maintenance
      Enables LLM agents to retrieve live, accurately-labelled product data from Ozon's public storefront, including search with pagination and sorting, all price variants, delivery dates, seller legal details, variants, and SKU-specific ratings and reviews, all without an Ozon account.
      4
      MIT
    • A
      license
      A
      quality
      C
      maintenance
      Enables LLM agents to access live aliexpress.ru storefront data, including variant-specific ruble prices, order-accurate coupons, delivery quotes to Russian cities, seller info, and paginated buyer reviews with filters.
      4
      MIT