Product Big Data Service

This MCP service provides enterprise keyword search, product search, enterprise products, overseas store products, brand, and e-commerce channel query capabilities, helping users with product selection, competitor research, product qualification verification, and channel analysis.

Main Features

• 🏢 Enterprise abbreviation and keyword search

• 🔍 Retail product and overseas online store search

• 🧾 Enterprise retail product and e-commerce product queries

• 🌍 Overseas store product catalog queries

• 🏷️ Beauty industry enterprise brand and product efficacy analysis

• 🛒 Domestic and global online store channel analysis

Related MCP server: Enterprise Operation Insight MCP Server

Service Design Notes

• The service provides 6 Tools based on actual usage targets, rather than laying out tools by upstream API count.

• When users only provide an enterprise abbreviation, first use goods_enterprise_search to obtain the full enterprise name or stable ID.

• Enterprise products and overseas store products are provided as separate Tools to avoid the same parameter expressing different objects in different sources.

• goods_enterprise_products can select retail or e-commerce products, but a single call only accesses one Product ID.

• Enterprise retail products have a maximum of 10 items per page; other paginated queries have a maximum of 50 items per page.

• The business outer layer of paginated results is uniformly total and resultList.

• Store best-seller, monthly sales, and cumulative sales capabilities that depended on third-party products have been removed; price or sales trend Tools are no longer registered.

• On success, Tools return the business data extracted by the HandaaS Integrator Gateway.

Environment Requirements

• Python 3.10+

• Dependencies: python-dotenv, requests, mcp

Local Quick Start

1. Enter the Project Directory

cd goods-mcp-server

2. Create a Virtual Environment and Install Dependencies

python3 -m venv mcp_env
source mcp_env/bin/activate
pip install -r requirements.txt

3. Configure Environment Variables

cp .env.example .env

Edit .env:

INTEGRATOR_ID=your_integrator_id
SECRET_ID=your_secret_id
SECRET_KEY=your_secret_key
HANDAAS_REQUEST_TIMEOUT=30

HANDAAS_REQUEST_TIMEOUT is optional, in seconds, with a default value of 30.

4. Start the Service

python server/mcp_server.py streamable-http

The default service address is http://localhost:8000/mcp.

You can also use:

./start_mcp_server.sh streamable-http

Supports three startup methods: stdio, sse, and streamable-http.

5. Cursor / Cherry Studio Configuration

{
  "mcpServers": {
    "goods-mcp-server": {
      "type": "streamableHttp",
      "url": "http://127.0.0.1:8000/mcp"
    }
  }
}

STDIO Installation and Deployment

Replace {workdir} with the absolute project path:

{
  "mcpServers": {
    "goods-mcp-server": {
      "command": "{workdir}/mcp_env/bin/python",
      "args": [
        "{workdir}/server/mcp_server.py",
        "stdio"
      ]
    }
  }
}

INTEGRATOR_ID, SECRET_ID, and SECRET_KEY need to be obtained after registering at HandaaS and activating the integrator. Real credentials should only be stored in the local .env or deployment secrets.

Available Tools and Product IDs

1. goods_enterprise_search

Function: Search candidate enterprises by enterprise abbreviation, brand, product, or other keywords.

Main Parameters:

• matchKeyword (required): Enterprise abbreviation or related keyword.

• pageIndex (optional): Page number, starting from 1.

• pageSize (optional): Default 10, maximum 50.

Returns: Candidate enterprises total/resultList. After confirming an enterprise, preferably pass the full enterprise name, enterprise ID, or unified social credit code to the enterprise product, brand, and channel Tools.

2. goods_search

Function: Search retail products or overseas online stores for product selection, product discovery, and cross-border channel filtering.

Main Parameters:

• matchKeyword (optional): Product name, online store name, or product keyword.

• source (optional): retail retail products; overseas overseas online stores. Default retail.

• pageIndex (optional): Page number, starting from 1.

• pageSize (optional): Maximum 50; retail search default 10, overseas search default 50.

• eshopSource, eshopCategories, eshopSalesLevel (optional): Only used for overseas online store search.

• operationStatus, hasAssociateEnterprise (optional): Overseas online store status and associated enterprise filtering.

Returns: total and resultList.

3. goods_enterprise_products

Function: Query retail or e-commerce products by enterprise, suitable for product qualification verification, enterprise product inventory, and competitor research.

Main Parameters:

• matchKeyword (required): Enterprise name, enterprise ID, registration number, or unified social credit code.

• productType (optional): retail enterprise retail products; ecommerce enterprise e-commerce products. Default retail.

• keywordType (optional): name, nameId, regNumber, or socialCreditCode.

• pageIndex (optional): Page number, starting from 1.

• pageSize (optional): Retail products maximum 10, default 10; e-commerce products maximum 50, default 50.

Retail Product Return Fields:

• Product name, product barcode, listing date

• Enterprise name, enterprise ID

• Brand name, GPC category

E-commerce Product Return Fields:

• Product name, image link, price, product source

4. goods_overseas_store_products

Function: Query the store product catalog by overseas online store ID.

Main Parameters:

• storeId (required): The online store _id returned by goods_search(source=overseas).

• pageIndex, pageSize (optional): MCP local pagination, pageSize maximum 50.

Returns: Product quantity, reviews, BSR, category, product name, and link information, uniformly formatted as total/resultList.

5. goods_brand

Function: Query beauty industry enterprise brand details or brand product efficacy overview.

Main Parameters:

• matchKeyword (required): Enterprise identifier.

• view (optional): brand_detail brand details; product_overview product efficacy overview.

• keywordType (optional): Enterprise identifier type.

6. goods_channel

Function: Query the enterprise's domestic e-commerce store list or global domestic and overseas online store details.

Main Parameters:

• matchKeyword (required): Enterprise identifier.

• source (optional): domestic_store domestic e-commerce stores; global_store domestic and overseas online stores.

• keywordType (optional): Enterprise identifier type.

• pageIndex, pageSize (optional): Only used for domestic stores, pageSize maximum 50.

Usage Scenarios

1. Enterprise Identification: Use abbreviations, brand, or product keywords to find candidate enterprises and stable identifiers.

2. Product Discovery: Discover retail products by product keyword, or filter overseas online stores by product and platform.

3. Enterprise Product Inventory: Query an enterprise's retail product barcodes, brands, GPC categories, and e-commerce product prices.

4. Product Qualification Verification: Use enterprise identifiers to locate the product entity and verify product name, barcode, and listing information.

5. Cross-border Competitor Research: Enter a specific store's product catalog from overseas online store search, analyzing categories and BSR.

6. Brand Analysis: Understand beauty industry enterprise brands, main products, and product efficacy layout.

7. Channel Analysis: Compare an enterprise's domestic e-commerce stores and domestic/overseas online store layout.

Usage Notes

1. Single Data Source Call: A single call only accesses one Product ID selected by source, productType, or view.

2. Pagination Limits: Enterprise retail products have a maximum pageSize of 10; other paginated Tools have a maximum of 50.

3. Abbreviation Handling: If an enterprise abbreviation cannot be queried directly, first call goods_enterprise_search.

4. Identifier Priority: After confirming a candidate, preferably use the enterprise ID or unified social credit code.

5. Overseas Store ID: storeId must come from overseas online store search results; enterprise names cannot be used as a substitute.

6. Empty Results: total=0, resultList=[] are valid business results.

7. Capability Boundary: This service no longer provides store best-seller, monthly sales, cumulative sales, or sales trend queries.

Example Questions

goods_enterprise_search

1. Which enterprises correspond to "Xiaomi"?

2. Help me find the exact enterprise name and enterprise ID for "Gree".

goods_search

1. Help me find coffee products in the retail market, show 10 first.

2. Search Amazon overseas online stores selling coffee.

goods_enterprise_products

1. Query the retail product names, barcodes, and brands of Xiaomi Technology Co., Ltd.

2. View the product names, prices, and sources published by a certain enterprise on e-commerce platforms.

goods_overseas_store_products

1. View this overseas online store's product catalog and BSR.

2. List the products and review counts of a specified overseas store by page.

goods_brand

1. Query the brand details of Shanghai Jahwa United Co., Ltd.

2. Analyze the brand product efficacy overview of L'Oréal (China) Co., Ltd.

goods_channel

1. What domestic e-commerce stores does Gree Electric Appliances Inc. of Zhuhai have?

2. What domestic and overseas online store channels does Beijing JD Century Trading Co., Ltd. have?

Testing and Verification

python -m py_compile server/mcp_server.py
python -m unittest discover -s tests -v

Unit tests use Mock HTTP responses and do not call real HandaaS product APIs.