Patent Downloader MCP Server

@Edison-A-N

代码仓库

基本信息

分类

其他

传输方式

stdio

作者

Edison-A-N

提交者

Nan Zhang

关于 Patent Downloader MCP Server

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

#patent-downloader#python-sdk#google-patents

Patent Downloader MCP Server 配置

使用下面的配置,将此服务器添加到你的 MCP 客户端。

{
  "mcpServers": {
    "patent_downloader": {
      "command": "uvx",
      "args": [
        "--from",
        "git+https://github.com/Edison-A-N/patent_downloader@0.1.0",
        "--with",
        "patent_downloader[mcp]",
        "patent-downloader",
        "mcp-server"
      ],
      "env": {
        "OUTPUT_DIR": "/Users/nan.zhang/Downloads/patents"
      }
    }
  }
}

Patent Downloader MCP Server 工具

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

概览

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

常见问题

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`.

其他分类下的更多 MCP 服务器

PickFu MCP

PickFu MCP is a Model Context Protocol (MCP) server that connects AI assistants, developers, marketers, product managers, and AI agents to PickFu's consumer research platform. It enables users to create surveys, conduct

Glasswarp

See and control a real Windows PC you own — from any MCP client, locally or remotely. Observe (UIA + screenshots), click/type/drag/scroll, launch apps, owner Live View. BYOH: your machine, your key.

MCP Toolbox for Databases

googleapis

MCP Toolbox for Databases is an open source MCP server for databases.

15.9K

Awesome Mlops

visenger

A curated list of references for MLOps

14.0K

Screenpipe

screenpipe

YC (S26) | Open Computer History | Continuously record your company computer work, map your workflows, help you find work worth automating, and power your agents' context

22.0K