MCP.so
Sign In
P

Patent Downloader

@Edison-A-N

About Patent Downloader

A Python SDK for downloading patents from Google Patents with Model Context Protocol (MCP) support.

Basic information

Category

Other

Transports

stdio

Publisher

Edison-A-N

Submitted by

Nan Zhang

Config

Add this server to your MCP-compatible client using the configuration below.

{
  "mcpServers": {
    "patent_downloader": {
      "command": "uvx",
      "args": [
        "--from",
        "git+https://github.com/Edison-A-N/[email protected]",
        "--with",
        "patent_downloader[mcp]",
        "patent-downloader",
        "mcp-server"
      ],
      "env": {
        "OUTPUT_DIR": "/Users/nan.zhang/Downloads/patents"
      }
    }
  }
}

Tools

3

Download a single patent PDF from Google Patents. Args: patent_number: The patent number to download (e.g., 'WO2013078254A1') output_dir: Directory to save the PDF file Returns: Success or error message

Download multiple patent PDFs from Google Patents. Args: patent_numbers: List of patent numbers to download output_dir: Directory to save the PDF files Returns: Summary of download results

Get detailed information about a patent. Args: patent_number: The patent number to get information for Returns: Formatted patent information

Overview

What is Patent Downloader?

Patent Downloader is a Python SDK for downloading patent PDFs from Google Patents, with built-in support for the Model Context Protocol (MCP). It is designed for developers who need to programmatically retrieve patent documents and integrate patent downloading into AI-powered tools or workflows.

How to use Patent Downloader?

Install the package via pip or uv (recommended). Use the command-line interface to download patents, e.g., patent-downloader download WO2013078254A1. To start the MCP server, run patent-downloader mcp-server or use uvx patent-downloader mcp-server without installation. Set the default output directory with the OUTPUT_DIR environment variable.

Key features of Patent Downloader

  • Download patent PDFs from Google Patents
  • Simple and clean Python API with type hints
  • MCP server support for AI assistant integration
  • Command-line interface for quick downloads
  • Comprehensive error handling

Use cases of Patent Downloader

  • Download a single patent by its number
  • Batch-download multiple patents at once
  • Retrieve patent metadata (title, inventors, abstract)
  • Integrate patent downloading into an AI agent via MCP
  • Automate patent research and analysis pipelines

FAQ from Patent Downloader

Do I need to install the full package to run the MCP server?

No. You can run the MCP server directly using uvx patent-downloader mcp-server without installing the package.

How do I set a custom download directory?

Use the --output-dir option in the CLI, or set the OUTPUT_DIR environment variable before starting the MCP server. The default is ./downloads.

What patent numbers are supported?

Any patent number that works with Google Patents (e.g., WO2013078254A1, US20130123448A1).

Does Patent Downloader require authentication or API keys?

The README does not mention any authentication requirements; no API keys or credentials are needed.

What transport does the MCP server use?

The MCP server uses stdio transport. Start it with patent-downloader mcp-server or via uvx.

Comments

More Other MCP servers