Wildberries MCP Server

Wildberries MCP Server

MCP server for Wildberries API that enables fetching product cards with multi-cabinet support, automatic pagination, and retry logic.

Category
访问服务器

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 cards
    • 0: cards without photos
    • 1: cards with photos only

Returns: JSON with product cards including IDs, names, sizes, characteristics, photos, and metadata.

Installation

  1. Clone the repository:

    git clone <repository-url>
    cd wb-mcp-server
    
  2. Install dependencies:

    pip install -e .
    
  3. Configure your API keys:

    cp config.example.yaml config.yaml
    

    Edit config.yaml and 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

  1. Go to Wildberries Seller Portal
  2. Navigate to SettingsAPI Access
  3. Create a new API key with required permissions:
    • Content API (read) - for product cards
  4. Copy the API key and add it to your config.yaml
  5. 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 orders
  • get_wb_sales - Fetch sales data
  • get_wb_warehouse_remains - Fetch warehouse stock
  • get_wb_prices - Fetch pricing information
  • get_wb_campaigns - Fetch advertising campaigns
  • get_wb_fullstats - Fetch advertising statistics
  • get_wb_finance - Fetch financial reports
  • get_wb_tariffs - Fetch tariff information

Security

  • Keep your config.yaml file secure and never commit it to version control
  • The .gitignore file is configured to exclude config.yaml by 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

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。

官方
精选
JavaScript
Playwright MCP Server

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。

官方
精选
TypeScript
Magic Component Platform (MCP)

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。

官方
精选
本地
TypeScript
Audiense Insights MCP Server

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。

官方
精选
本地
TypeScript
VeyraX

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。

官方
精选
本地
graphlit-mcp-server

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。

官方
精选
TypeScript
Kagi MCP Server

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。

官方
精选
Python
e2b-mcp-server

e2b-mcp-server

使用 MCP 通过 e2b 运行代码。

官方
精选
Neon MCP Server

Neon MCP Server

用于与 Neon 管理 API 和数据库交互的 MCP 服务器

官方
精选
Exa MCP Server

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。

官方
精选