marketplaces-mcp-ru
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| WB_API_KEY | No | API ключ для Wildberries Seller API (берётся из настроек доступа к API в кабинете WB) | |
| OZON_API_KEY | No | API ключ для Ozon Seller API (берётся из настроек API-ключей в кабинете Ozon) | |
| OZON_CLIENT_ID | No | Client ID для Ozon Seller API (берётся из настроек API-ключей в кабинете Ozon) |
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
| Capability | Details |
|---|---|
| tools | {
"listChanged": false
} |
| prompts | {
"listChanged": false
} |
| resources | {
"subscribe": false,
"listChanged": false
} |
| experimental | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| wb_check_authA | Check whether the required credentials are present in the environment. Does NOT reveal secret values — only reports which variables are set. Returns JSON: {"ready": bool, "missing": [str], "required": [str]}. |
| wb_list_sectionsA | List API sections and how many catalog endpoints each contains. |
| wb_get_sectionA | List all endpoints in one section. Args: section: section name (see wb_list_sections), e.g. "statistics". Returns JSON list of {operation_id, method, path, safety, summary}. |
| wb_search_methodsA | Search the endpoint catalog by keyword (works in Russian and English). Args: query: free text, e.g. "остатки", "stocks", "update price". limit: max results (1-50). Returns JSON list of matching endpoints (best first). |
| wb_mapA | The big picture: business entities this API covers and the go-to methods for each. Call with no args to see the whole map ("you are here"); pass entity="reviews" (or stocks/prices/orders/…) to list every method of one entity. Use this before guessing — it orients you fast. |
| wb_describe_methodA | Return the full catalog record for one endpoint: method, host, path, scope, safety level, pagination style, rate limit, params and doc URL. |
| wb_call_methodA | Execute one READ endpoint from the catalog by operation_id. Target API: https://dev.wildberries.ru/en/openapi/api-information. Reads only: nothing here changes data, so it runs without confirmation. To change data use wb_write_method, to delete use wb_delete_method. Args: operation_id: id from the catalog (see wb_search_methods). path_values: values for {placeholders} in the path. query: query-string parameters. body: JSON request body (a few read endpoints take one). Returns JSON: {"ok": true, "status", "data"} or the error envelope. |
| wb_write_methodA | Execute one WRITE endpoint from the catalog: create or update data. Target API: https://dev.wildberries.ru/en/openapi/api-information. Requires confirm_write=true; nothing is sent without it. Irreversible operations live in wb_delete_method, reads in wb_call_method. Args: operation_id: id from the catalog (see wb_search_methods). path_values: values for {placeholders} in the path. query: query-string parameters. body: JSON request body. confirm_write: must be true. Returns JSON: {"ok": true, "status", "data"} or the error envelope. |
| wb_delete_methodA | Execute one DESTRUCTIVE endpoint: deletes or irreversibly changes data. Target API: https://dev.wildberries.ru/en/openapi/api-information. Both confirm_write=true and i_understand_this_modifies_data=true are required; nothing is sent without both. Args: operation_id: id from the catalog (see wb_search_methods). path_values: values for {placeholders} in the path. query: query-string parameters. body: JSON request body. confirm_write: must be true. i_understand_this_modifies_data: must be true. Returns JSON: {"ok": true, "status", "data"} or the error envelope. |
| wb_get_rawA | Read ANY endpoint by path, including ones missing from the catalog. Target API: https://dev.wildberries.ru/en/openapi/api-information. Safe verbs only (GET, HEAD, OPTIONS). To change data use wb_write_raw, to delete use wb_delete_raw. Args: path: full path beginning with '/', e.g. "/ping". method: safe verb, GET by default. host: host override; defaults to the service's default host. query: query-string parameters. body: JSON request body (rare on reads; some APIs want one). Returns JSON: {"ok": true, "status", "data"} or the error envelope. |
| wb_write_rawA | Create or update data at ANY path, including paths not in the catalog. Target API: https://dev.wildberries.ru/en/openapi/api-information. POST, PUT and PATCH only; requires confirm_write=true. Args: method: POST, PUT or PATCH. path: full path beginning with '/'. host: host override; defaults to the service's default host. query: query-string parameters. body: JSON request body. confirm_write: must be true. Returns JSON: {"ok": true, "status", "data"} or the error envelope. |
| wb_delete_rawA | Delete data at ANY path, including paths not in the catalog. Target API: https://dev.wildberries.ru/en/openapi/api-information. DELETE only. Both confirm_write=true and i_understand_this_modifies_data=true are required. Args: path: full path beginning with '/'. method: DELETE. host: host override; defaults to the service's default host. query: query-string parameters. body: JSON request body. confirm_write: must be true. i_understand_this_modifies_data: must be true. Returns JSON: {"ok": true, "status", "data"} or the error envelope. |
| wb_fetch_allA | Auto-paginate a read endpoint and return every row in one response. Handles offset, last_id, cursor (Ozon v4/v5), page and WB lastChangeDate styles. The array path is taken from the catalog automatically. Args: operation_id: a read endpoint from the catalog. query / body / path_values: base parameters (cursor fields are managed). items_path: override the array path (default: the endpoint's own). limit: page size to request. max_items: hard cap to protect context (default 10000). Returns JSON: {"ok", "items", "total_fetched", "pages_fetched", "truncated"}. |
| wb_list_cabinetsA | List configured cabinets for this marketplace and which one is active. Returns JSON: {"active": str|null, "cabinets": [names], "fields_needed": [...]}. Secret values are never returned. |
| wb_add_cabinetA | Add or update a cabinet (a named set of API credentials), from chat. ⚠️ This puts the key into the chat transcript — requires i_understand_key_goes_to_chat=true. The terminal-free safe alternative is the installer (install.py / double-click), where the key never enters chat. Args: credentials: dict with the required fields for this service ({fields}). For Ozon: {{"client_id": "...", "api_key": "..."}}; for WB: {{"token": "..."}}. name: optional label. If omitted, the cabinet is named after the real shop name fetched from the marketplace (falls back to "main"). i_understand_key_goes_to_chat: must be true to proceed. Saved to ~/.marketplace-mcp/cabinets.json (local, chmod 600), never echoed. |
| wb_set_keyA | Change / rotate the API key from chat (e.g. the old one expired or leaked). ⚠️ The key goes into the chat transcript — requires i_understand_key_goes_to_chat=true. The safe, terminal-free alternative is the installer, where the key never enters chat. Use a scoped key and rotate it in the seller cabinet if it was exposed. Args: credentials: dict with the required fields ({fields}). cabinet: which cabinet to update. Default: the active one (so "my key expired" just works). If there is none, the cabinet is named from the marketplace's shop name, else "main". i_understand_key_goes_to_chat: must be true to proceed. On success the key is validated against the marketplace and the shop name is reported. Saved locally (chmod 600), never echoed back. |
| wb_use_cabinetA | Switch the active cabinet. Subsequent API calls use its credentials. Args: name: the cabinet to activate (see wb_list_cabinets). |
| wb_remove_cabinetA | Delete a stored cabinet. If it was active, another becomes active. Args: name: the cabinet to remove. |
| wb_list_workflowsA | List ready-made analytical workflows (recipes) for this marketplace. Returns JSON: [{name, category, when_to_use}]. Use {svc}_get_workflow to fetch the full step-by-step plan for one. |
| wb_get_workflowA | Return the full plan for one workflow: ordered steps (each naming a catalog operation_id and why), interpretation guidance, and common mistakes to avoid. Args: name: workflow name (see {svc}_list_workflows). |
| wb_get_salesA | Get Wildberries sales and returns since a date (Statistics API, 1 req/min). Args: date_from: RFC3339 date/time in MSK, e.g. "2026-06-01" or "2026-06-01T00:00:00". flag: 0 = rows changed since date_from (incremental); 1 = rows dated on date_from. Returns JSON: {"ok": true, "status", "data": [ sale rows ]} or error envelope. Each row includes saleID, srid, nmId, totalPrice, forPay, lastChangeDate. |
| wb_get_stocksA | Get the current Wildberries stock snapshot (Statistics API, 1 req/min). Stocks have no history — this is a point-in-time snapshot. Use an early date_from to get the full current set. Args: date_from: RFC3339 date; default "2020-01-01" returns everything in stock now. Returns JSON: {"ok": true, "data": [ stock rows ]} with quantity, warehouseName, nmId. |
| wb_get_new_ordersA | Get new FBS assembly orders awaiting processing (Marketplace API). Returns JSON: {"ok": true, "data": {"orders": [...]}} — each order has id, rid, article, skus, createdAt, warehouseId. |
| wb_get_pricesA | Get current prices and discounts for products (Discounts-Prices API). Args: limit: page size (<=1000). offset: pagination offset. filter_nm_id: optional single nmID to filter by. Returns JSON: {"ok": true, "data": {"listGoods": [{nmID, sizes, discount, ...}]}}. |
| wb_set_priceA | Set price and discount for ONE product (Discounts-Prices API). WRITE. Requires confirm_write=true (this changes your live price). A new price 3x below the old one lands the product in WB price quarantine. Args: nm_id: product nmID. price: new base price in rubles (integer). discount: discount percent (0-99). confirm_write: must be true to actually send the change. Returns JSON: {"ok": true, "data": {"id": uploadID}} — poll wb_prices_history_tasks. |
| ozon_check_authA | Check whether the required credentials are present in the environment. Does NOT reveal secret values — only reports which variables are set. Returns JSON: {"ready": bool, "missing": [str], "required": [str]}. |
| ozon_list_sectionsA | List API sections and how many catalog endpoints each contains. |
| ozon_get_sectionA | List all endpoints in one section. Args: section: section name (see ozon_list_sections), e.g. "statistics". Returns JSON list of {operation_id, method, path, safety, summary}. |
| ozon_search_methodsA | Search the endpoint catalog by keyword (works in Russian and English). Args: query: free text, e.g. "остатки", "stocks", "update price". limit: max results (1-50). Returns JSON list of matching endpoints (best first). |
| ozon_mapA | The big picture: business entities this API covers and the go-to methods for each. Call with no args to see the whole map ("you are here"); pass entity="reviews" (or stocks/prices/orders/…) to list every method of one entity. Use this before guessing — it orients you fast. |
| ozon_describe_methodA | Return the full catalog record for one endpoint: method, host, path, scope, safety level, pagination style, rate limit, params and doc URL. |
| ozon_call_methodA | Execute one READ endpoint from the catalog by operation_id. Target API: https://docs.ozon.ru/api/seller/. Reads only: nothing here changes data, so it runs without confirmation. To change data use ozon_write_method, to delete use ozon_delete_method. Args: operation_id: id from the catalog (see ozon_search_methods). path_values: values for {placeholders} in the path. query: query-string parameters. body: JSON request body (a few read endpoints take one). Returns JSON: {"ok": true, "status", "data"} or the error envelope. |
| ozon_write_methodA | Execute one WRITE endpoint from the catalog: create or update data. Target API: https://docs.ozon.ru/api/seller/. Requires confirm_write=true; nothing is sent without it. Irreversible operations live in ozon_delete_method, reads in ozon_call_method. Args: operation_id: id from the catalog (see ozon_search_methods). path_values: values for {placeholders} in the path. query: query-string parameters. body: JSON request body. confirm_write: must be true. Returns JSON: {"ok": true, "status", "data"} or the error envelope. |
| ozon_delete_methodA | Execute one DESTRUCTIVE endpoint: deletes or irreversibly changes data. Target API: https://docs.ozon.ru/api/seller/. Both confirm_write=true and i_understand_this_modifies_data=true are required; nothing is sent without both. Args: operation_id: id from the catalog (see ozon_search_methods). path_values: values for {placeholders} in the path. query: query-string parameters. body: JSON request body. confirm_write: must be true. i_understand_this_modifies_data: must be true. Returns JSON: {"ok": true, "status", "data"} or the error envelope. |
| ozon_get_rawA | Read ANY endpoint by path, including ones missing from the catalog. Target API: https://docs.ozon.ru/api/seller/. Safe verbs only (GET, HEAD, OPTIONS). To change data use ozon_write_raw, to delete use ozon_delete_raw. Args: path: full path beginning with '/', e.g. "/v1/actions". method: safe verb, GET by default. host: host override; defaults to the service's default host. query: query-string parameters. body: JSON request body (rare on reads; some APIs want one). Returns JSON: {"ok": true, "status", "data"} or the error envelope. |
| ozon_write_rawA | Create or update data at ANY path, including paths not in the catalog. Target API: https://docs.ozon.ru/api/seller/. POST, PUT and PATCH only; requires confirm_write=true. Args: method: POST, PUT or PATCH. path: full path beginning with '/'. host: host override; defaults to the service's default host. query: query-string parameters. body: JSON request body. confirm_write: must be true. Returns JSON: {"ok": true, "status", "data"} or the error envelope. |
| ozon_delete_rawA | Delete data at ANY path, including paths not in the catalog. Target API: https://docs.ozon.ru/api/seller/. DELETE only. Both confirm_write=true and i_understand_this_modifies_data=true are required. Args: path: full path beginning with '/'. method: DELETE. host: host override; defaults to the service's default host. query: query-string parameters. body: JSON request body. confirm_write: must be true. i_understand_this_modifies_data: must be true. Returns JSON: {"ok": true, "status", "data"} or the error envelope. |
| ozon_fetch_allA | Auto-paginate a read endpoint and return every row in one response. Handles offset, last_id, cursor (Ozon v4/v5), page and WB lastChangeDate styles. The array path is taken from the catalog automatically. Args: operation_id: a read endpoint from the catalog. query / body / path_values: base parameters (cursor fields are managed). items_path: override the array path (default: the endpoint's own). limit: page size to request. max_items: hard cap to protect context (default 10000). Returns JSON: {"ok", "items", "total_fetched", "pages_fetched", "truncated"}. |
| ozon_list_cabinetsA | List configured cabinets for this marketplace and which one is active. Returns JSON: {"active": str|null, "cabinets": [names], "fields_needed": [...]}. Secret values are never returned. |
| ozon_add_cabinetA | Add or update a cabinet (a named set of API credentials), from chat. ⚠️ This puts the key into the chat transcript — requires i_understand_key_goes_to_chat=true. The terminal-free safe alternative is the installer (install.py / double-click), where the key never enters chat. Args: credentials: dict with the required fields for this service ({fields}). For Ozon: {{"client_id": "...", "api_key": "..."}}; for WB: {{"token": "..."}}. name: optional label. If omitted, the cabinet is named after the real shop name fetched from the marketplace (falls back to "main"). i_understand_key_goes_to_chat: must be true to proceed. Saved to ~/.marketplace-mcp/cabinets.json (local, chmod 600), never echoed. |
| ozon_set_keyA | Change / rotate the API key from chat (e.g. the old one expired or leaked). ⚠️ The key goes into the chat transcript — requires i_understand_key_goes_to_chat=true. The safe, terminal-free alternative is the installer, where the key never enters chat. Use a scoped key and rotate it in the seller cabinet if it was exposed. Args: credentials: dict with the required fields ({fields}). cabinet: which cabinet to update. Default: the active one (so "my key expired" just works). If there is none, the cabinet is named from the marketplace's shop name, else "main". i_understand_key_goes_to_chat: must be true to proceed. On success the key is validated against the marketplace and the shop name is reported. Saved locally (chmod 600), never echoed back. |
| ozon_use_cabinetA | Switch the active cabinet. Subsequent API calls use its credentials. Args: name: the cabinet to activate (see ozon_list_cabinets). |
| ozon_remove_cabinetA | Delete a stored cabinet. If it was active, another becomes active. Args: name: the cabinet to remove. |
| ozon_list_workflowsA | List ready-made analytical workflows (recipes) for this marketplace. Returns JSON: [{name, category, when_to_use}]. Use {svc}_get_workflow to fetch the full step-by-step plan for one. |
| ozon_get_workflowA | Return the full plan for one workflow: ordered steps (each naming a catalog operation_id and why), interpretation guidance, and common mistakes to avoid. Args: name: workflow name (see {svc}_list_workflows). |
| ozon_get_productsA | List Ozon products (one page). Args: visibility: ALL | VISIBLE | INVISIBLE | ARCHIVED | IN_SALE ... limit: page size (<=1000). last_id: cursor from a previous page (empty for first page). Returns JSON: {"ok": true, "data": {"result": {"items": [...], "last_id": "..."}}}. For every product across pages use ozon_fetch_all with ozon_product_list. |
| ozon_get_stocksA | Get available + reserved stock per product (v4/product/info/stocks). Args: visibility: product visibility filter (default ALL). limit: page size (<=1000). last_id: cursor for pagination. Returns JSON with stock per product (present, reserved) per warehouse type. |
| ozon_get_pricesA | Get prices, commissions and price indexes per product (v5/product/info/prices). Args: visibility: product visibility filter (default ALL). limit: page size (<=1000). cursor: pagination cursor from a previous response. Returns JSON with price, marketing_seller_price, min_price, commissions, price_indexes. |
| ozon_get_fbs_unfulfilledA | List new/unprocessed FBS shipments awaiting assembly. Args: cutoff_from: ISO datetime lower bound, e.g. "2026-06-01T00:00:00Z". cutoff_to: ISO datetime upper bound. limit: page size. offset: pagination offset. Returns JSON: {"ok": true, "data": {"result": {"postings": [...]}}}. |
| ozon_set_priceA | Set the price for ONE product by offer_id (v1/product/import/prices). WRITE. Requires confirm_write=true. Ozon limits price updates to ~10/product/hour. Prices are strings. old_price="0" clears the strikethrough old price. Args: offer_id: seller's article (offer_id). price: new price as a string, e.g. "1499". old_price: pre-discount price as string, or "0" to clear. min_price: minimum price as string, or "0". currency_code: default "RUB". confirm_write: must be true to send. Returns JSON: {"ok": true, "data": {"result": [{"offer_id", "updated", "errors"}]}}. |
| ozon_perf_check_authA | Check whether the required credentials are present in the environment. Does NOT reveal secret values — only reports which variables are set. Returns JSON: {"ready": bool, "missing": [str], "required": [str]}. |
| ozon_perf_list_sectionsA | List API sections and how many catalog endpoints each contains. |
| ozon_perf_get_sectionA | List all endpoints in one section. Args: section: section name (see ozon_perf_list_sections), e.g. "statistics". Returns JSON list of {operation_id, method, path, safety, summary}. |
| ozon_perf_search_methodsA | Search the endpoint catalog by keyword (works in Russian and English). Args: query: free text, e.g. "остатки", "stocks", "update price". limit: max results (1-50). Returns JSON list of matching endpoints (best first). |
| ozon_perf_mapA | The big picture: business entities this API covers and the go-to methods for each. Call with no args to see the whole map ("you are here"); pass entity="reviews" (or stocks/prices/orders/…) to list every method of one entity. Use this before guessing — it orients you fast. |
| ozon_perf_describe_methodA | Return the full catalog record for one endpoint: method, host, path, scope, safety level, pagination style, rate limit, params and doc URL. |
| ozon_perf_call_methodA | Execute one READ endpoint from the catalog by operation_id. Target API: https://docs.ozon.ru/api/performance/. Reads only: nothing here changes data, so it runs without confirmation. To change data use ozon_perf_write_method, to delete use ozon_perf_delete_method. Args: operation_id: id from the catalog (see ozon_perf_search_methods). path_values: values for {placeholders} in the path. query: query-string parameters. body: JSON request body (a few read endpoints take one). Returns JSON: {"ok": true, "status", "data"} or the error envelope. |
| ozon_perf_write_methodA | Execute one WRITE endpoint from the catalog: create or update data. Target API: https://docs.ozon.ru/api/performance/. Requires confirm_write=true; nothing is sent without it. Irreversible operations live in ozon_perf_delete_method, reads in ozon_perf_call_method. Args: operation_id: id from the catalog (see ozon_perf_search_methods). path_values: values for {placeholders} in the path. query: query-string parameters. body: JSON request body. confirm_write: must be true. Returns JSON: {"ok": true, "status", "data"} or the error envelope. |
| ozon_perf_delete_methodA | Execute one DESTRUCTIVE endpoint: deletes or irreversibly changes data. Target API: https://docs.ozon.ru/api/performance/. Both confirm_write=true and i_understand_this_modifies_data=true are required; nothing is sent without both. Args: operation_id: id from the catalog (see ozon_perf_search_methods). path_values: values for {placeholders} in the path. query: query-string parameters. body: JSON request body. confirm_write: must be true. i_understand_this_modifies_data: must be true. Returns JSON: {"ok": true, "status", "data"} or the error envelope. |
| ozon_perf_get_rawA | Read ANY endpoint by path, including ones missing from the catalog. Target API: https://docs.ozon.ru/api/performance/. Safe verbs only (GET, HEAD, OPTIONS). To change data use ozon_perf_write_raw, to delete use ozon_perf_delete_raw. Args: path: full path beginning with '/', e.g. "/api/client/campaign". method: safe verb, GET by default. host: host override; defaults to the service's default host. query: query-string parameters. body: JSON request body (rare on reads; some APIs want one). Returns JSON: {"ok": true, "status", "data"} or the error envelope. |
| ozon_perf_write_rawA | Create or update data at ANY path, including paths not in the catalog. Target API: https://docs.ozon.ru/api/performance/. POST, PUT and PATCH only; requires confirm_write=true. Args: method: POST, PUT or PATCH. path: full path beginning with '/'. host: host override; defaults to the service's default host. query: query-string parameters. body: JSON request body. confirm_write: must be true. Returns JSON: {"ok": true, "status", "data"} or the error envelope. |
| ozon_perf_delete_rawA | Delete data at ANY path, including paths not in the catalog. Target API: https://docs.ozon.ru/api/performance/. DELETE only. Both confirm_write=true and i_understand_this_modifies_data=true are required. Args: path: full path beginning with '/'. method: DELETE. host: host override; defaults to the service's default host. query: query-string parameters. body: JSON request body. confirm_write: must be true. i_understand_this_modifies_data: must be true. Returns JSON: {"ok": true, "status", "data"} or the error envelope. |
| ozon_perf_fetch_allA | Auto-paginate a read endpoint and return every row in one response. Handles offset, last_id, cursor (Ozon v4/v5), page and WB lastChangeDate styles. The array path is taken from the catalog automatically. Args: operation_id: a read endpoint from the catalog. query / body / path_values: base parameters (cursor fields are managed). items_path: override the array path (default: the endpoint's own). limit: page size to request. max_items: hard cap to protect context (default 10000). Returns JSON: {"ok", "items", "total_fetched", "pages_fetched", "truncated"}. |
| ozon_perf_list_cabinetsA | List configured cabinets for this marketplace and which one is active. Returns JSON: {"active": str|null, "cabinets": [names], "fields_needed": [...]}. Secret values are never returned. |
| ozon_perf_add_cabinetA | Add or update a cabinet (a named set of API credentials), from chat. ⚠️ This puts the key into the chat transcript — requires i_understand_key_goes_to_chat=true. The terminal-free safe alternative is the installer (install.py / double-click), where the key never enters chat. Args: credentials: dict with the required fields for this service ({fields}). For Ozon: {{"client_id": "...", "api_key": "..."}}; for WB: {{"token": "..."}}. name: optional label. If omitted, the cabinet is named after the real shop name fetched from the marketplace (falls back to "main"). i_understand_key_goes_to_chat: must be true to proceed. Saved to ~/.marketplace-mcp/cabinets.json (local, chmod 600), never echoed. |
| ozon_perf_set_keyA | Change / rotate the API key from chat (e.g. the old one expired or leaked). ⚠️ The key goes into the chat transcript — requires i_understand_key_goes_to_chat=true. The safe, terminal-free alternative is the installer, where the key never enters chat. Use a scoped key and rotate it in the seller cabinet if it was exposed. Args: credentials: dict with the required fields ({fields}). cabinet: which cabinet to update. Default: the active one (so "my key expired" just works). If there is none, the cabinet is named from the marketplace's shop name, else "main". i_understand_key_goes_to_chat: must be true to proceed. On success the key is validated against the marketplace and the shop name is reported. Saved locally (chmod 600), never echoed back. |
| ozon_perf_use_cabinetA | Switch the active cabinet. Subsequent API calls use its credentials. Args: name: the cabinet to activate (see ozon_perf_list_cabinets). |
| ozon_perf_remove_cabinetA | Delete a stored cabinet. If it was active, another becomes active. Args: name: the cabinet to remove. |
| ozon_perf_list_workflowsA | List ready-made analytical workflows (recipes) for this marketplace. Returns JSON: [{name, category, when_to_use}]. Use {svc}_get_workflow to fetch the full step-by-step plan for one. |
| ozon_perf_get_workflowA | Return the full plan for one workflow: ordered steps (each naming a catalog operation_id and why), interpretation guidance, and common mistakes to avoid. Args: name: workflow name (see {svc}_list_workflows). |
| ym_check_authA | Check whether the required credentials are present in the environment. Does NOT reveal secret values — only reports which variables are set. Returns JSON: {"ready": bool, "missing": [str], "required": [str]}. |
| ym_list_sectionsA | List API sections and how many catalog endpoints each contains. |
| ym_get_sectionA | List all endpoints in one section. Args: section: section name (see ym_list_sections), e.g. "statistics". Returns JSON list of {operation_id, method, path, safety, summary}. |
| ym_search_methodsA | Search the endpoint catalog by keyword (works in Russian and English). Args: query: free text, e.g. "остатки", "stocks", "update price". limit: max results (1-50). Returns JSON list of matching endpoints (best first). |
| ym_mapA | The big picture: business entities this API covers and the go-to methods for each. Call with no args to see the whole map ("you are here"); pass entity="reviews" (or stocks/prices/orders/…) to list every method of one entity. Use this before guessing — it orients you fast. |
| ym_describe_methodA | Return the full catalog record for one endpoint: method, host, path, scope, safety level, pagination style, rate limit, params and doc URL. |
| ym_call_methodA | Execute one READ endpoint from the catalog by operation_id. Target API: https://yandex.ru/dev/market/partner-api/doc/ru/. Reads only: nothing here changes data, so it runs without confirmation. To change data use ym_write_method, to delete use ym_delete_method. Args: operation_id: id from the catalog (see ym_search_methods). path_values: values for {placeholders} in the path. query: query-string parameters. body: JSON request body (a few read endpoints take one). Returns JSON: {"ok": true, "status", "data"} or the error envelope. |
| ym_write_methodA | Execute one WRITE endpoint from the catalog: create or update data. Target API: https://yandex.ru/dev/market/partner-api/doc/ru/. Requires confirm_write=true; nothing is sent without it. Irreversible operations live in ym_delete_method, reads in ym_call_method. Args: operation_id: id from the catalog (see ym_search_methods). path_values: values for {placeholders} in the path. query: query-string parameters. body: JSON request body. confirm_write: must be true. Returns JSON: {"ok": true, "status", "data"} or the error envelope. |
| ym_delete_methodA | Execute one DESTRUCTIVE endpoint: deletes or irreversibly changes data. Target API: https://yandex.ru/dev/market/partner-api/doc/ru/. Both confirm_write=true and i_understand_this_modifies_data=true are required; nothing is sent without both. Args: operation_id: id from the catalog (see ym_search_methods). path_values: values for {placeholders} in the path. query: query-string parameters. body: JSON request body. confirm_write: must be true. i_understand_this_modifies_data: must be true. Returns JSON: {"ok": true, "status", "data"} or the error envelope. |
| ym_get_rawA | Read ANY endpoint by path, including ones missing from the catalog. Target API: https://yandex.ru/dev/market/partner-api/doc/ru/. Safe verbs only (GET, HEAD, OPTIONS). To change data use ym_write_raw, to delete use ym_delete_raw. Args: path: full path beginning with '/', e.g. "/v2/regions". method: safe verb, GET by default. host: host override; defaults to the service's default host. query: query-string parameters. body: JSON request body (rare on reads; some APIs want one). Returns JSON: {"ok": true, "status", "data"} or the error envelope. |
| ym_write_rawA | Create or update data at ANY path, including paths not in the catalog. Target API: https://yandex.ru/dev/market/partner-api/doc/ru/. POST, PUT and PATCH only; requires confirm_write=true. Args: method: POST, PUT or PATCH. path: full path beginning with '/'. host: host override; defaults to the service's default host. query: query-string parameters. body: JSON request body. confirm_write: must be true. Returns JSON: {"ok": true, "status", "data"} or the error envelope. |
| ym_delete_rawA | Delete data at ANY path, including paths not in the catalog. Target API: https://yandex.ru/dev/market/partner-api/doc/ru/. DELETE only. Both confirm_write=true and i_understand_this_modifies_data=true are required. Args: path: full path beginning with '/'. method: DELETE. host: host override; defaults to the service's default host. query: query-string parameters. body: JSON request body. confirm_write: must be true. i_understand_this_modifies_data: must be true. Returns JSON: {"ok": true, "status", "data"} or the error envelope. |
| ym_fetch_allA | Auto-paginate a read endpoint and return every row in one response. Handles offset, last_id, cursor (Ozon v4/v5), page and WB lastChangeDate styles. The array path is taken from the catalog automatically. Args: operation_id: a read endpoint from the catalog. query / body / path_values: base parameters (cursor fields are managed). items_path: override the array path (default: the endpoint's own). limit: page size to request. max_items: hard cap to protect context (default 10000). Returns JSON: {"ok", "items", "total_fetched", "pages_fetched", "truncated"}. |
| ym_list_cabinetsA | List configured cabinets for this marketplace and which one is active. Returns JSON: {"active": str|null, "cabinets": [names], "fields_needed": [...]}. Secret values are never returned. |
| ym_add_cabinetA | Add or update a cabinet (a named set of API credentials), from chat. ⚠️ This puts the key into the chat transcript — requires i_understand_key_goes_to_chat=true. The terminal-free safe alternative is the installer (install.py / double-click), where the key never enters chat. Args: credentials: dict with the required fields for this service ({fields}). For Ozon: {{"client_id": "...", "api_key": "..."}}; for WB: {{"token": "..."}}. name: optional label. If omitted, the cabinet is named after the real shop name fetched from the marketplace (falls back to "main"). i_understand_key_goes_to_chat: must be true to proceed. Saved to ~/.marketplace-mcp/cabinets.json (local, chmod 600), never echoed. |
| ym_set_keyA | Change / rotate the API key from chat (e.g. the old one expired or leaked). ⚠️ The key goes into the chat transcript — requires i_understand_key_goes_to_chat=true. The safe, terminal-free alternative is the installer, where the key never enters chat. Use a scoped key and rotate it in the seller cabinet if it was exposed. Args: credentials: dict with the required fields ({fields}). cabinet: which cabinet to update. Default: the active one (so "my key expired" just works). If there is none, the cabinet is named from the marketplace's shop name, else "main". i_understand_key_goes_to_chat: must be true to proceed. On success the key is validated against the marketplace and the shop name is reported. Saved locally (chmod 600), never echoed back. |
| ym_use_cabinetA | Switch the active cabinet. Subsequent API calls use its credentials. Args: name: the cabinet to activate (see ym_list_cabinets). |
| ym_remove_cabinetA | Delete a stored cabinet. If it was active, another becomes active. Args: name: the cabinet to remove. |
| ym_list_workflowsA | List ready-made analytical workflows (recipes) for this marketplace. Returns JSON: [{name, category, when_to_use}]. Use {svc}_get_workflow to fetch the full step-by-step plan for one. |
| ym_get_workflowA | Return the full plan for one workflow: ordered steps (each naming a catalog operation_id and why), interpretation guidance, and common mistakes to avoid. Args: name: workflow name (see {svc}_list_workflows). |
| ym_get_campaignsA | List the seller's shops (кампании) with their campaignId and businessId. Call this first: nearly every other Yandex Market method needs a campaignId (магазин) or businessId (кабинет продавца). Both are in the response: campaigns[].id and campaigns[].business.id. Args: page_token: pageToken from a previous page (empty for the first page). limit: page size (<=100). Returns JSON: {"ok": true, "data": {"campaigns": [...], "paging": {...}}}. |
| ym_get_ordersA | List orders of one shop (GET /v2/campaigns/{campaignId}/orders). Args: campaign_id: shop id from ym_get_campaigns. status: filter, e.g. PROCESSING | DELIVERY | PICKUP | DELIVERED | CANCELLED | UNPAID (comma-separated allowed). Empty = all. from_date: order creation date lower bound, DD-MM-YYYY (Yandex format). to_date: upper bound, DD-MM-YYYY. page_token: pageToken from a previous page. limit: page size (<=50). Returns JSON: {"ok": true, "data": {"orders": [...], "paging": {...}}}. For every order across pages use ym_fetch_all with ym_get_orders. |
| ym_get_offersA | List the seller's offers (товары) with their Market card mapping (POST /v2/businesses/{businessId}/offer-mappings). Args: business_id: cabinet id (campaigns[].business.id). offer_ids: comma-separated offerId (SKU) filter; empty = all. page_token: pageToken from a previous page. limit: page size (<=200). Returns JSON: {"ok": true, "data": {"result": {"offerMappings": [...], "paging": {...}}}}. |
| ym_get_stocksA | Stock per offer per warehouse for one shop, with optional turnover (POST /v2/campaigns/{campaignId}/offers/stocks). Args: campaign_id: shop id. offer_ids: comma-separated offerId filter; empty = all. with_turnover: also return turnover (оборачиваемость) per offer. page_token: pageToken from a previous page. limit: page size (<=200). Returns JSON: {"ok": true, "data": {"result": {"warehouses": [{"warehouseId", "offers": [...]}]}}}. |
| ym_get_pricesA | Base prices set for all shops of the cabinet (POST /v2/businesses/{businessId}/offer-prices). Args: business_id: cabinet id. offer_ids: comma-separated offerId filter; empty = all. page_token: pageToken from a previous page. limit: page size (<=200). Returns JSON with result.offers[].price {value, currencyId, discountBase, updatedAt}. |
| ym_set_priceA | Set the base price of ONE offer for all shops of the cabinet (POST /v2/businesses/{businessId}/offer-prices/updates). WRITE. Requires confirm_write=true. discount_base is the strikethrough price (must be higher than price); 0 = no discount shown. Args: business_id: cabinet id. offer_id: seller's SKU (offerId). price: new price, e.g. 1499. discount_base: pre-discount price, or 0 to clear. currency: RUR (default) — Yandex uses "RUR", not "RUB". confirm_write: must be true to send. Returns JSON: {"ok": true, "data": {"status": "OK"}} on success. |
| avito_check_authA | Check whether the required credentials are present in the environment. Does NOT reveal secret values — only reports which variables are set. Returns JSON: {"ready": bool, "missing": [str], "required": [str]}. |
| avito_list_sectionsA | List API sections and how many catalog endpoints each contains. |
| avito_get_sectionA | List all endpoints in one section. Args: section: section name (see avito_list_sections), e.g. "statistics". Returns JSON list of {operation_id, method, path, safety, summary}. |
| avito_search_methodsA | Search the endpoint catalog by keyword (works in Russian and English). Args: query: free text, e.g. "остатки", "stocks", "update price". limit: max results (1-50). Returns JSON list of matching endpoints (best first). |
| avito_mapA | The big picture: business entities this API covers and the go-to methods for each. Call with no args to see the whole map ("you are here"); pass entity="reviews" (or stocks/prices/orders/…) to list every method of one entity. Use this before guessing — it orients you fast. |
| avito_describe_methodA | Return the full catalog record for one endpoint: method, host, path, scope, safety level, pagination style, rate limit, params and doc URL. |
| avito_call_methodA | Execute one READ endpoint from the catalog by operation_id. Target API: https://developers.avito.ru/api-catalog. Reads only: nothing here changes data, so it runs without confirmation. To change data use avito_write_method, to delete use avito_delete_method. Args: operation_id: id from the catalog (see avito_search_methods). path_values: values for {placeholders} in the path. query: query-string parameters. body: JSON request body (a few read endpoints take one). Returns JSON: {"ok": true, "status", "data"} or the error envelope. |
| avito_write_methodA | Execute one WRITE endpoint from the catalog: create or update data. Target API: https://developers.avito.ru/api-catalog. Requires confirm_write=true; nothing is sent without it. Irreversible operations live in avito_delete_method, reads in avito_call_method. Args: operation_id: id from the catalog (see avito_search_methods). path_values: values for {placeholders} in the path. query: query-string parameters. body: JSON request body. confirm_write: must be true. Returns JSON: {"ok": true, "status", "data"} or the error envelope. |
| avito_delete_methodA | Execute one DESTRUCTIVE endpoint: deletes or irreversibly changes data. Target API: https://developers.avito.ru/api-catalog. Both confirm_write=true and i_understand_this_modifies_data=true are required; nothing is sent without both. Args: operation_id: id from the catalog (see avito_search_methods). path_values: values for {placeholders} in the path. query: query-string parameters. body: JSON request body. confirm_write: must be true. i_understand_this_modifies_data: must be true. Returns JSON: {"ok": true, "status", "data"} or the error envelope. |
| avito_get_rawA | Read ANY endpoint by path, including ones missing from the catalog. Target API: https://developers.avito.ru/api-catalog. Safe verbs only (GET, HEAD, OPTIONS). To change data use avito_write_raw, to delete use avito_delete_raw. Args: path: full path beginning with '/', e.g. "/core/v1/items". method: safe verb, GET by default. host: host override; defaults to the service's default host. query: query-string parameters. body: JSON request body (rare on reads; some APIs want one). Returns JSON: {"ok": true, "status", "data"} or the error envelope. |
| avito_write_rawA | Create or update data at ANY path, including paths not in the catalog. Target API: https://developers.avito.ru/api-catalog. POST, PUT and PATCH only; requires confirm_write=true. Args: method: POST, PUT or PATCH. path: full path beginning with '/'. host: host override; defaults to the service's default host. query: query-string parameters. body: JSON request body. confirm_write: must be true. Returns JSON: {"ok": true, "status", "data"} or the error envelope. |
| avito_delete_rawA | Delete data at ANY path, including paths not in the catalog. Target API: https://developers.avito.ru/api-catalog. DELETE only. Both confirm_write=true and i_understand_this_modifies_data=true are required. Args: path: full path beginning with '/'. method: DELETE. host: host override; defaults to the service's default host. query: query-string parameters. body: JSON request body. confirm_write: must be true. i_understand_this_modifies_data: must be true. Returns JSON: {"ok": true, "status", "data"} or the error envelope. |
| avito_fetch_allA | Auto-paginate a read endpoint and return every row in one response. Handles offset, last_id, cursor (Ozon v4/v5), page and WB lastChangeDate styles. The array path is taken from the catalog automatically. Args: operation_id: a read endpoint from the catalog. query / body / path_values: base parameters (cursor fields are managed). items_path: override the array path (default: the endpoint's own). limit: page size to request. max_items: hard cap to protect context (default 10000). Returns JSON: {"ok", "items", "total_fetched", "pages_fetched", "truncated"}. |
| avito_list_cabinetsA | List configured cabinets for this marketplace and which one is active. Returns JSON: {"active": str|null, "cabinets": [names], "fields_needed": [...]}. Secret values are never returned. |
| avito_add_cabinetA | Add or update a cabinet (a named set of API credentials), from chat. ⚠️ This puts the key into the chat transcript — requires i_understand_key_goes_to_chat=true. The terminal-free safe alternative is the installer (install.py / double-click), where the key never enters chat. Args: credentials: dict with the required fields for this service ({fields}). For Ozon: {{"client_id": "...", "api_key": "..."}}; for WB: {{"token": "..."}}. name: optional label. If omitted, the cabinet is named after the real shop name fetched from the marketplace (falls back to "main"). i_understand_key_goes_to_chat: must be true to proceed. Saved to ~/.marketplace-mcp/cabinets.json (local, chmod 600), never echoed. |
| avito_set_keyA | Change / rotate the API key from chat (e.g. the old one expired or leaked). ⚠️ The key goes into the chat transcript — requires i_understand_key_goes_to_chat=true. The safe, terminal-free alternative is the installer, where the key never enters chat. Use a scoped key and rotate it in the seller cabinet if it was exposed. Args: credentials: dict with the required fields ({fields}). cabinet: which cabinet to update. Default: the active one (so "my key expired" just works). If there is none, the cabinet is named from the marketplace's shop name, else "main". i_understand_key_goes_to_chat: must be true to proceed. On success the key is validated against the marketplace and the shop name is reported. Saved locally (chmod 600), never echoed back. |
| avito_use_cabinetA | Switch the active cabinet. Subsequent API calls use its credentials. Args: name: the cabinet to activate (see avito_list_cabinets). |
| avito_remove_cabinetA | Delete a stored cabinet. If it was active, another becomes active. Args: name: the cabinet to remove. |
| avito_list_workflowsA | List ready-made analytical workflows (recipes) for this marketplace. Returns JSON: [{name, category, when_to_use}]. Use {svc}_get_workflow to fetch the full step-by-step plan for one. |
| avito_get_workflowA | Return the full plan for one workflow: ordered steps (each naming a catalog operation_id and why), interpretation guidance, and common mistakes to avoid. Args: name: workflow name (see {svc}_list_workflows). |
| avito_whoamiA | Authorized Avito account: id (needed as user_id in many methods), name, email, phone, profile_url. Also the cheapest way to verify the credentials. Returns JSON: {"ok": true, "data": {"id": ..., "name": ..., ...}}. |
| avito_get_itemsA | List the seller's listings (объявления): status, category, url (GET /core/v1/items). Max 25 requests/min. Args: status: active | removed | old | blocked | rejected (comma-separated ok). category: Avito category id filter, 0 = all. updated_from: YYYY-MM-DD lower bound on the listing update date. page: 1-based page number. per_page: page size (<100). Returns JSON: {"ok": true, "data": {"meta": {...}, "resources": [...]}}. For all pages use avito_fetch_all with avito_get_items_info. |
| avito_get_ordersA | Orders placed with Авито Доставка (GET /order-management/1/orders). Business (B2C) sellers only. Args: statuses: comma-separated filter: on_confirmation, ready_to_ship, in_transit, canceled, delivered, on_return, in_dispute, closed. date_from: unix timestamp — only orders created after it. page: 1-based page number. limit: page size (<=20). Returns JSON: {"ok": true, "data": {"orders": [...], "hasMore": bool}}. Each order has availableActions (confirm / reject / setTrackNumber …) and schedules (deadlines such as confirmTill, shipTill). |
| avito_get_stocksA | Stock per listing (POST /stock-management/1/info): quantity, is_unlimited, is_out_of_stock. Up to 500 ids per call. Args: item_ids: comma-separated Avito listing ids. Returns JSON: {"ok": true, "data": {"stocks": [{"item_id", "quantity", ...}]}}. |
| avito_get_item_statsA | Views / contacts / favorites per listing per period (POST /stats/v1/accounts/{user_id}/items). Up to 200 ids, 270 days deep. Args: item_ids: comma-separated listing ids. date_from: YYYY-MM-DD (inclusive). date_to: YYYY-MM-DD (inclusive). period_grouping: day | week | month. Returns JSON with result.items[].stats[] {date, uniqViews, uniqContacts, uniqFavorites}. |
| avito_get_reviewsA | Published reviews on the seller with score, text, deal stage and the seller's answer (GET /ratings/v1/reviews). Use avito_get_ratings_info_v1 via avito_call_method for the aggregate rating. Args: offset: pagination offset. limit: page size (<=50). Returns JSON: {"ok": true, "data": {"total": n, "reviews": [...]}}. |
| avito_get_chatsA | Buyer chats (GET /messenger/v2/accounts/{user_id}/chats). Requires the Messenger API to be enabled on the seller's Avito plan. Args: unread_only: only chats with unread messages. item_ids: comma-separated listing ids to filter chats by. limit: page size (<=100). offset: pagination offset (<=1000). Returns JSON: {"ok": true, "data": {"chats": [{"id", "context", "last_message", "users"}]}}. |
| avito_get_balanceA | Wallet balance: real money and bonuses (GET /core/v1/accounts/{user_id}/balance/). Returns JSON: {"ok": true, "data": {"real": ..., "bonus": ...}}. |
| avito_update_priceA | Set the price of ONE listing (POST /core/v1/items/{item_id}/update_price). WRITE. Requires confirm_write=true. Goods, spare parts, cars, real estate only; max 150 requests/min. Args: item_id: Avito listing id. price: new price in roubles (integer). confirm_write: must be true to send. Returns JSON: {"ok": true, "data": {"result": {"success": true}}}. |
| avito_update_stockA | Set the available quantity of ONE listing (PUT /stock-management/1/stocks). WRITE. Requires confirm_write=true. quantity 0 hides the "buy with delivery" button. Args: item_id: Avito listing id. quantity: units available (0..999999). confirm_write: must be true to send. Returns JSON: {"ok": true, "data": {"stocks": [{"item_id", "success", "errors"}]}}. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 126 tools
The five marketplace prefixes (wb_, ozon_, ozon_perf_, ym_, avito_) cleanly separate otherwise identical tool families. Within a service, call_method, get_raw, and fetch_all are distinguishable by catalog-id vs raw-path vs auto-pagination, though convenience wrappers like wb_set_price and wb_write_method could briefly cause hesitation.
Tools overwhelmingly follow a {marketplace}_{verb}_{noun} snake_case pattern, including the nested ozon_perf_ family. Minor deviations like avito_whoami and standalone convenience wrappers (wb_get_sales, ozon_get_products) break the strict verb_noun rhythm, but the overall scheme is predictable.
126 tools is far beyond the recommended range and matches the rubric's extreme mismatch threshold. The five-marketplace scope explains some repetition, but the resulting surface still overwhelms agent context and makes tool selection disproportionately expensive.
Each marketplace receives a full lifecycle: auth and cabinet management, endpoint discovery, generic read/write/delete with raw fallbacks, auto-pagination, and convenience wrappers for core entities like prices, stocks, orders, and products. Common seller workflows have no obvious dead ends.