Estore

You can query and analyze Chinese e-commerce data through a dedicated MCP server that collects enterprise information, shop and product profiles, and cross-platform store insights. This MCP server lets you search by keywords, view global online store profiles, analyze ecommerce products, and inspect store information to support market research, competitive analysis, and investment decisions.

How to use

You will interact with the MCP server through an MCP client. Start by connecting to the local or remote MCP endpoint, then perform focused queries to retrieve: 1) fuzzy enterprise searches, 2) global online store profiles, 3) ecommerce product profiles, and 4) ecommerce store information. Use these capabilities to understand a company’s ecommerce footprint, product distribution, and store performance across platforms.

How to install

Prerequisites: Python 3.10 or newer is required. Ensure you have a working Python development environment and network access.

Step 1: Clone the MCP server repository and navigate into it.

Step 2: Create and activate a virtual environment, then install dependencies.

Step 3: Copy the environment template and configure your credentials in a .env file.

Step 4: Start the MCP server using the streamable-http method. The service will be available at http://localhost:8000.

Step 5: If you are integrating with Cursor / Cherry Studio, use one of the MCP configuration examples shown below to connect the server.

Configuration and usage notes

Environment variables you configure to run the server include integrator credentials needed for authentication.

Two common MCP connection methods are available: 1) streamable HTTP to point to a remote MCP endpoint, and 2) STDIO to run a local Python-based MCP process and stream results. Use the method that fits your orchestration tooling.

If you plan to use the official remote service, set the MCP config to point to the remote URL and ensure you have valid credentials and tokens.

Examples of MCP connection configurations

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

{
  "mcpServers": {
    "estore-mcp-server":{
      "type": "streamableHttp",
      "url": "https://mcp.handaas.com/estore/estore_bigdata?token={token}"
    }
  }
}

{
  "mcpServers": {
    "estore-mcp-server": {
      "command": "uv",
      "args": ["run", "mcp", "run", "{workdir}/server/mcp_server.py"],
      "env": {
        "PATH": "{workdir}/mcp_env/bin:$PATH",
        "PYTHONPATH": "{workdir}/mcp_env",
        "INTEGRATOR_ID": "your_integrator_id",
        "SECRET_ID": "your_secret_id",
        "SECRET_KEY": "your_secret_key"
      }
    }
  }
}

Notes and best practices

• You may need the full enterprise name for certain queries; if a call requires the enterprise full name, first use a fuzzy search to obtain it.

• Data timeliness varies by source; pay attention to data timestamps for trend analysis.

• Domestic and international store data may have different structures; plan your queries accordingly.

Troubleshooting

If the MCP server fails to start, verify that Python 3.10+ is active, the virtual environment is activated, dependencies are installed, and the environment variables are correctly set in the .env file.

If you cannot reach http://localhost:8000, check that the streamable-http start command completed successfully and that there are no port conflicts.

Available tools

estore_bigdata_fuzzy_search

Fuzzy search for enterprise keywords across names, brands, products, and roles to retrieve matching enterprises.

estore_bigdata_global_online_store_profile

Query global online store profiles for a company, including domestic and international store counts, product counts, and platforms.

estore_bigdata_ecommerce_product_profile

Analyze ecommerce product profiles to reveal brand information, ratings, founding time, categories, and core products.

estore_bigdata_ecommerce_store_info

Fetch detailed information about stores associated with an enterprise, including store counts, products, brands, platforms, and overview.