Wildberries MCP Server
MCP server for Wildberries API that enables fetching product cards with multi-cabinet support, automatic pagination, and retry logic.
README
Wildberries MCP Server
MCP (Model Context Protocol) server for Wildberries API that provides tools to interact with Wildberries marketplace data.
Features
- Multi-cabinet support: Configure multiple Wildberries cabinets (accounts) with separate API keys
- Automatic pagination: Handles pagination automatically to retrieve all data
- Retry logic: Built-in retry mechanism with exponential backoff for transient failures
- Rate limiting: Respects Wildberries API rate limits with automatic retry
Currently Available Tools
get_wb_cards
Get product cards (карточки товаров) from Wildberries.
Parameters:
cabinet_name(optional): Name of the cabinet to fetch cards from. If not specified, fetches from all enabled cabinets.with_photo(optional): Filter cards by photo presence-1(default): all cards0: cards without photos1: cards with photos only
Returns: JSON with product cards including IDs, names, sizes, characteristics, photos, and metadata.
Installation
-
Clone the repository:
git clone <repository-url> cd wb-mcp-server -
Install dependencies:
pip install -e . -
Configure your API keys:
cp config.example.yaml config.yamlEdit
config.yamland add your Wildberries API keys:cabinets: wb_cabinet1: api_key: "your-api-key-here" enabled: true wb_cabinet2: api_key: "another-api-key" enabled: true
Getting Wildberries API Keys
- Go to Wildberries Seller Portal
- Navigate to Settings → API Access
- Create a new API key with required permissions:
- Content API (read) - for product cards
- Copy the API key and add it to your
config.yaml - Keep your API keys secure - never commit them to git
Usage
Running the Server
python -m wb_mcp_server.server
Using with Claude Desktop
Add to your Claude Desktop configuration (~/Library/Application Support/Claude/claude_desktop_config.json on macOS):
{
"mcpServers": {
"wildberries": {
"command": "python",
"args": ["-m", "wb_mcp_server.server"],
"cwd": "/path/to/wb-mcp-server"
}
}
}
Example Tool Calls
Get all cards from all cabinets:
{
"name": "get_wb_cards"
}
Get cards from specific cabinet:
{
"name": "get_wb_cards",
"arguments": {
"cabinet_name": "wb_cabinet1"
}
}
Get only cards with photos:
{
"name": "get_wb_cards",
"arguments": {
"with_photo": 1
}
}
Project Structure
wb-mcp-server/
├── src/wb_mcp_server/
│ ├── __init__.py
│ ├── config.py # Configuration loader
│ ├── base_client.py # HTTP client with retry logic
│ ├── wb_api.py # Wildberries API client
│ └── server.py # MCP server implementation
├── config.example.yaml # Example configuration
├── config.yaml # Your configuration (gitignored)
├── pyproject.toml # Project dependencies
└── README.md
Development
Install with dev dependencies:
pip install -e ".[dev]"
Run tests:
pytest
Code formatting:
ruff check .
ruff format .
Roadmap
The following tools are planned for future releases:
get_wb_orders- Fetch ordersget_wb_sales- Fetch sales dataget_wb_warehouse_remains- Fetch warehouse stockget_wb_prices- Fetch pricing informationget_wb_campaigns- Fetch advertising campaignsget_wb_fullstats- Fetch advertising statisticsget_wb_finance- Fetch financial reportsget_wb_tariffs- Fetch tariff information
Security
- Keep your
config.yamlfile secure and never commit it to version control - The
.gitignorefile is configured to excludeconfig.yamlby default - API keys are passed in Authorization headers and not logged
License
MIT
Contributing
Contributions are welcome! Please feel free to submit a Pull Request.
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。