Trademark

You can run and integrate the Trademark MCP Server to query and analyze trademark data. This MCP server provides end-to-end access to fuzzy enterprise searches, trademark information, and statistical profiles, enabling you to perform queries, monitor trademark activity, and analyze brand assets from a single, consistent interface.

How to use

Use an MCP client to connect to the Trademark MCP Server. You have two primary connection methods: a remote HTTP endpoint and a local stdio (hosted) server. The HTTP method lets your client query a remote MCP endpoint directly. The stdio method runs the local server process and exposes an MCP API that your client can call through standard input/output channels. To perform common tasks, start by choosing the connection method that best fits your environment, then use your client’s built-in MCP features to search for enterprise data, search trademarks, view company trademark profiles, and run statistics analyses.

How to install

Prerequisites: you need Python 3.10 or newer and a functioning shell. You will install dependencies, configure environment variables, and start the MCP server.

# 1. Clone the project repository
git clone https://github.com/handaas/trademark-mcp-server
cd trademark-mcp-server

# 2. Create and activate a virtual environment, then install dependencies
python -m venv mcp_env && source mcp_env/bin/activate
pip install -r requirements.txt

# 3. Configure environment variables
cp .env.example .env
# Edit .env to set your credentials:
# INTEGRATOR_ID=your_integrator_id
# SECRET_ID=your_secret_id
# SECRET_KEY=your_secret_key

# 4. Start the local MCP server using the streamable-http channel
python server/mcp_server.py streamable-http

The server will start and listen at http://localhost:8000. You can also run in stdio or streamable-http modes depending on your deployment needs.

Configuration and runtime options

Connection configurations let you choose between a remote HTTP MCP endpoint and a local stdio-based MCP server. The following examples show how to configure these options for integration with your MCP client or Cursor/Cherry Studio setup.

{
  "mcpServers": {
    "trademark_mcp": {
      "type": "http",
      "url": "https://mcp.handaas.com/trademark/trademark_bigdata?token={token}",
      "args": []
    }
  }
}

{
  "mcpServers": {
    "trademark_mcp": {
      "type": "stdio",
      "command": "uv",
      "args": ["run", "mcp", "run", "{workdir}/server/mcp_server.py"],
      "env": [
        {"name": "PATH", "value": "{workdir}/mcp_env/bin:$PATH"},
        {"name": "PYTHONPATH", "value": "{workdir}/mcp_env"},
        {"name": "INTEGRATOR_ID", "value": "YOUR_INTEGRATOR_ID"},
        {"name": "SECRET_ID", "value": "YOUR_SECRET_ID"},
        {"name": "SECRET_KEY", "value": "YOUR_SECRET_KEY"}
      ]
    }
  }
}

Using official remote service

If you want to use the official remote MCP service, configure your client to point to the remote endpoint and include your authentication token in the URL. This lets you leverage the hosted MCP server for trademark data without running a local instance.

{
  "mcpServers": {
    "trademark_mcp-server":{
      "type": "http",
      "url": "https://mcp.handaas.com/trademark/trademark_bigdata?token={token}"
    }
  }
}

Environment and security notes

Keep your integrator credentials secure. Do not expose your INTEGRATOR_ID, SECRET_ID, SECRET_KEY, or access tokens in client configurations or public repositories. Use environment isolation for production deployments and rotate credentials per your security policy.

Available tools and endpoints

This server exposes several tools that enable data retrieval and analysis across trademark and enterprise data. The key tools are:

• trademark_bigdata_fuzzy_search — fuzzy search for enterprise keywords to locate related corporate entities
• trademark_bigdata_trademark_search — search for trademark information by name, application, applicant, or agent and filter by status
• trademark_bigdata_trademark_profile — obtain high-level statistics on a company’s related trademarks
• trademark_bigdata_trademark_stats — analyze trademark application and registration trends, statuses, and categories for a company

Troubleshooting and notes

If the server fails to start, verify that Python 3.10+ is installed, the virtual environment is active, and dependencies are installed. Ensure that environment variables are correctly set and that the selected MCP connection (http or stdio) matches your deployment method.

Available tools

trademark_bigdata_fuzzy_search

Fuzzy search for enterprise keywords to retrieve related enterprise information.

trademark_bigdata_trademark_search

Trademark information search by name, application number, applicant, or agent with optional status filtering.

trademark_bigdata_trademark_profile

Enterprise trademark profile statistics including total count and category breakdown.

trademark_bigdata_trademark_stats

Statistical analysis of trademark applications, registrations, and categories for an enterprise.