Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@io.github.dontsovcmc/ozon-seller show my recent orders with status delivered"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
MCP-сервер, CLI-утилита и библиотека Pydantic-моделей для Ozon Seller API.
MCP-сервер — интеграция с Claude Code, Claude Desktop и другими MCP-клиентами
CLI-утилита — работа с API из терминала, скрипты и автоматизация
Pydantic-модели — типизированные модели API для использования в своих Python-программах
Все данные остаются на вашем компьютере — ключи API никуда не передаются.
Related MCP server: Ozon MCP Server
Сервер использует паттерн search + execute — вместо 111 отдельных инструментов предоставляет 3:
Инструмент | Описание |
| Поиск действий по описанию на естественном языке |
| Выполнение действия по ID |
| Выполнение действия со скачиванием файла |
LLM: ozon_search("отменить отправление fbs")
→ [{"id": "fbs-posting-cancel", "params_schema": {"posting_number": "str", ...}, ...}]
LLM: ozon_execute("fbs-posting-cancel", '{"posting_number": "12345678-0001-1", "cancel_reason_id": 352}')
→ {"result": true}Домен | Кол-во | Описание |
21 | Товары: создание, обновление, цены, остатки, атрибуты | |
17 | FBS-отправления: списки, отмены, этикетки, акты | |
9 | FBO: отправления, поставки, склады | |
4 | Категории и атрибуты товаров | |
4 | Финансы: транзакции, итоги, движение средств | |
3 | Аналитика: данные, остатки, оборачиваемость | |
2 | Склады и способы доставки | |
8 | Возвраты FBO/FBS/rFBS | |
6 | Чаты с покупателями | |
6 | Акции и промо | |
4 | Ценовые стратегии | |
3 | Рейтинг и качество продавца | |
4 | Отчёты | |
4 | Отзывы покупателей | |
3 | Вопросы покупателей | |
4 | Заявки на отмену | |
6 | Сертификаты | |
2 | Штрихкоды | |
1 | Бренды |
Войдите в Ozon Seller
Перейдите в Настройки → API-ключи
Создайте ключ (Admin)
Скопируйте Client-Id и Api-Key
Способ 1: через uvx (не требует установки пакета)
Требуется uv — если не установлен:
curl -LsSf https://astral.sh/uv/install.sh | sh
claude mcp add ozon-seller \
-e OZON_CLIENT_ID=ваш_client_id \
-e OZON_API_KEY=ваш_api_key \
-- uvx mcp-server-ozon-sellerСпособ 2: через pip
pip install mcp-server-ozon-seller
claude mcp add ozon-seller \
-e OZON_CLIENT_ID=ваш_client_id \
-e OZON_API_KEY=ваш_api_key \
-- mcp-server-ozon-sellerДля удаления:
claude mcp remove ozon-sellerДобавьте в конфигурационный файл:
Клиент | ОС | Путь к файлу |
Claude Code | все |
|
Claude Desktop | macOS |
|
Claude Desktop | Windows |
|
Claude Desktop | Linux |
|
Через uvx:
{
"mcpServers": {
"ozon-seller": {
"command": "uvx",
"args": ["mcp-server-ozon-seller"],
"env": {
"OZON_CLIENT_ID": "ваш_client_id",
"OZON_API_KEY": "ваш_api_key"
}
}
}
}Через pip (после pip install mcp-server-ozon-seller):
{
"mcpServers": {
"ozon-seller": {
"command": "mcp-server-ozon-seller",
"env": {
"OZON_CLIENT_ID": "ваш_client_id",
"OZON_API_KEY": "ваш_api_key"
}
}
}
}Подключает сервер только на время одной сессии Claude, не сохраняя в настройки. Токен хранится в отдельном .env.mcp файле, а не в конфиге Claude.
Из JSON-строки:
claude --mcp-config '{"ozon-seller":{"command":"bash","args":["-c","source ~/.env.mcp && exec uvx mcp-server-ozon-seller"]}}'Из файла:
claude --mcp-config ~/mcp-servers.jsonПример ~/mcp-servers.json:
{
"ozon-seller": {
"command": "bash",
"args": ["-c", "source ~/.env.mcp && exec uvx mcp-server-ozon-seller"]
}
}Пример ~/.env.mcp:
OZON_CLIENT_ID=ваш_client_id
OZON_API_KEY=ваш_api_keyПопросите Claude: «покажи мои товары на Ozon» — он вызовет ozon_search, затем ozon_execute.
«покажи мои товары на Ozon» → ozon_search("products list") → ozon_execute("product-list")
«отмени FBS отправление 12345678-0001-1» → ozon_execute("fbs-posting-cancel", ...)
«скачай акт приёмки №42» → ozon_execute_file("fbs-act-pdf", ...)
«какие FBS заказы ещё не собраны?» → ozon_execute("fbs-postings-list", ...)
«покажи финансовые транзакции за апрель» → ozon_execute("finance-transactions", ...)
pip install mcp-server-ozon-sellerПеременные окружения OZON_CLIENT_ID и OZON_API_KEY должны быть установлены:
export OZON_CLIENT_ID=ваш_client_id
export OZON_API_KEY=ваш_api_keyИли через файл:
ozon-seller-cli --env /path/to/.env <command>Формат файла — KEY=VALUE, по одной переменной на строку, #-комментарии.
Без аргументов запускается MCP-сервер, с командой — CLI. Все команды выводят JSON.
# Версия
ozon-seller-cli --version
# Справка
ozon-seller-cli --help
ozon-seller-cli <command> --help# Товары
ozon-seller-cli product-list --limit 10
ozon-seller-cli product-info --offer-id SKU-001
ozon-seller-cli product-stocks-info
# FBS-отправления
ozon-seller-cli fbs-list
ozon-seller-cli fbs-cancel-reasons
ozon-seller-cli fbs-label 12345678-0001-1
# FBO
ozon-seller-cli fbo-list
ozon-seller-cli fbo-supply-list
# Финансы и аналитика
ozon-seller-cli finance-transactions '{"date": {"from": "2026-04-01", "to": "2026-04-25"}}'
ozon-seller-cli analytics-stock
# Возвраты
ozon-seller-cli returns-fbs
ozon-seller-cli returns-fbo
# Другое
ozon-seller-cli warehouses
ozon-seller-cli categories
ozon-seller-cli rating
ozon-seller-cli reviews
ozon-seller-cli brandsПакет содержит типизированные Pydantic-модели всех объектов API. Модели можно использовать в своих Python-программах для валидации данных и автодополнения в IDE.
pip install mcp-server-ozon-sellerfrom mcp_server_ozon_seller.models import FbsPostingsListParams
# Валидация данных
params = FbsPostingsListParams.model_validate({
"filter_dict": {"status": "awaiting_packaging"},
"limit": 50,
})
print(params.model_dump_json())
# Создание объекта
params = FbsPostingsListParams(limit=10)
print(params.limit) # type-safe доступ к полямВсе модели используют extra="allow" для forward compatibility — неизвестные поля API не вызывают ошибок.
Полный список моделей: models.py
Переменная | Обязательная | По умолчанию | Описание |
| да | — | Client-Id из личного кабинета Ozon Seller |
| да | — | Api-Key из личного кабинета Ozon Seller |
| нет |
| Таймаут HTTP-запросов к API (секунды) |
| нет |
| Таймаут скачивания файлов (секунды) |
Получить ключи: Ozon Seller → Настройки → API-ключи.
pip install -e ".[test]"
ruff check src/ tests/
pytest tests/ -vMIT
Execute an Ozon Seller API action by ID.
Use ozon_search first to find the action ID and its parameter schema.
Args: action: action ID from ozon_search results (e.g. "product-list") params_json: JSON object with action parameters matching the schema
| Name | Required | Description | Default |
|---|---|---|---|
| action | Yes | ||
| params_json | No | {} |
| Name | Required | Description |
|---|---|---|
| result | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations indicate non-read-only; description confirms it executes an action, implying mutation, but lacks details on side effects or rate limits.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Concise, front-loaded with purpose, and uses only four sentences including a structured Args list.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Covers essential usage and parameters; output schema exists so no need for return details, though the description could clarify params_json is a string.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
With 0% schema coverage, description fully explains both parameters: action is an ID from ozon_search with example, params_json is a JSON object matching the schema.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool executes an Ozon Seller API action by ID, and distinguishes it from siblings by advising to use ozon_search first.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Explicitly instructs to use ozon_search before executing, providing clear usage context, though it does not mention ozon_execute_file or when not to use.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Execute an Ozon Seller API action that downloads a file.
Args: action: action ID for download actions file_path: local file path to save the downloaded file params_json: JSON object with action parameters
| Name | Required | Description | Default |
|---|---|---|---|
| action | Yes | ||
| file_path | Yes | ||
| params_json | No | {} |
| Name | Required | Description |
|---|---|---|
| result | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The annotations indicate readOnlyHint=false, suggesting the tool may have side effects, yet the description only mentions downloading a file (a read operation). This creates a contradiction. The description does not disclose any behavioral traits such as auth requirements, rate limits, or side effects. Therefore, it is misleading and scores low.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is concise, with one sentence for purpose and a bullet-like list for arguments. It is front-loaded and easy to read. Every sentence contributes value.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
The description explains the tool's primary function and parameters, but lacks information on usage context, side effects, and differentiation from siblings. With a simple schema and output schema present, the description is adequate but not comprehensive.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The description adds some meaning to parameters beyond the schema titles: it explains 'action' is an action ID, 'file_path' is a local path to save, and 'params_json' is a JSON object. However, it does not specify what actions are valid or the structure of params_json. Given that schema description coverage is 0%, the description partially compensates but remains vague.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool executes an Ozon Seller API action that results in downloading a file. The verb 'execute' and resource 'action' are specific. However, it does not differentiate from sibling tool 'ozon_execute' which likely also executes actions but without file download. This lack of distinction prevents perfect clarity.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides no guidance on when to use this tool versus alternatives. There is no mention of prerequisites, context, or conditions. The sibling tools are not referenced.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Find available Ozon Seller API actions by intent.
Args: query: natural language description of what you want to do domain: optional filter (products, fbs, fbo, categories, finance, analytics, warehouses, returns, chats, promos, strategies, rating, reports, reviews, questions, cancellations, certificates, barcodes, brands) limit: max results (default 10)
| Name | Required | Description | Default |
|---|---|---|---|
| limit | No | ||
| query | Yes | ||
| domain | No |
| Name | Required | Description |
|---|---|---|
| result | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations declare readOnlyHint true, and the description adds behavioral context (searches by intent, parameter constraints). It does not contradict annotations and provides additional detail like domain filter options.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is concise with a clear purpose statement followed by a structured Args section. Every sentence adds value, no redundant content.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
The description covers the tool's purpose and all parameters. An output schema exists, so return value explanation is not required. It might lack details on error handling or empty results, but is sufficient for the tool's complexity.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The description adds significant meaning beyond the schema: query is natural language, domain is an optional filter with a list of valid values, limit sets max results with default. This compensates for the 0% schema description coverage.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool's purpose: 'Find available Ozon Seller API actions by intent.' It specifies a verb (Find) and resource (available actions), and distinguishes itself from sibling tools that execute actions.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description lists parameters with explanations (query as natural language, domain filter with allowed values, limit with default). While it does not explicitly state when to use or avoid this tool, the sibling names strongly imply this is for discovery versus execution.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections. Dates show when Glama detected each change.
v0.3.1ozon_executeozon_execute_fileozon_searchEach tool has a distinct purpose: ozon_search discovers actions, ozon_execute executes general API calls, and ozon_execute_file handles file downloads. No overlap in core functionality.
All tools follow the consistent pattern of 'ozon_' prefix with a verb_noun structure (search, execute, execute_file). No mixing of conventions.
Only 3 tools, but they are designed as a meta-interface to a large API. The minimal set is appropriate for the gateway pattern, though it may feel thin for complex workflows.
The meta-approach covers the entire Ozon Seller API via search and execute, with a dedicated tool for file downloads. Minor gap: no direct tools for common operations, but the discovery mechanism mitigates this.
Unclaimed servers have limited discoverability.
If you are the server author, to access and configure the admin panel.
Hosted Amazon Seller and Vendor MCP server for Claude, ChatGPT, Cursor, Codex, Gemini, Copilot.
Hosted Amazon Seller Central and Amazon Ads MCP server for Claude, ChatGPT, Cursor, and agents.
MCP server for Gainium — manage trading bots, deals, and balances via AI assistants
The Mercado Pago MCP Server implements the Model Context Protocol to provide AI agents and LLMs with access to Mercado Pago's APIs and tools within compatible development environments. It acts as an intermediary that translates Mercado Pago resources into executable functions (tools) that AI applications can invoke to perform actions and automate flows. The server simplifies integration, enables using documentation to implement or improve code, and optimizes operations through natural language interactions without manual implementations.
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/dontsovcmc/mcp-server-ozon-seller'
If you have feedback or need assistance with the MCP directory API, please join our Discord server
