Korean Patent MCP
Enables searching and analyzing Korean patents through the KIPRIS API using natural language. Supports patent search by applicant name, detailed patent information retrieval, and citation analysis.
README
๐ฐ๐ท Korean Patent MCP
ํ๊ตญ์ด ๋ฌธ์๋ ์๋์ ์์ต๋๋ค / Korean documentation below
MCP (Model Context Protocol) server for KIPRIS (Korean Intellectual Property Rights Information Service) API.
English Documentation
Overview
This MCP server enables AI assistants (Claude Desktop, Cursor, Windsurf, etc.) to search and analyze Korean patents through natural language queries. It connects to the official KIPRIS Plus Open API provided by the Korean Intellectual Property Office (KIPO).
Features
| Tool | Description |
|---|---|
kipris_search_patents |
Search patents by applicant name |
kipris_get_patent_detail |
Get detailed patent information by application number |
kipris_get_citing_patents |
Find patents that cite a specific patent |
Quick Start
# Install via Smithery (recommended)
npx -y @smithery/cli install korean-patent-mcp --client claude
# Or install via uv
uv pip install git+https://github.com/Tech-curator/korean-patent-mcp.git
Requirements
- Python 3.10+
- KIPRIS Plus Open API Key (Get your key here)
Configuration
Set the KIPRIS_API_KEY environment variable:
export KIPRIS_API_KEY="your_api_key_here"
Or add to your MCP client configuration:
{
"mcpServers": {
"korean-patent": {
"command": "uv",
"args": ["run", "korean-patent-mcp"],
"env": {
"KIPRIS_API_KEY": "your_api_key_here"
}
}
}
}
Example Queries
- "Search for Samsung Electronics' registered patents"
- "Get details for patent application number 1020200123456"
- "Find patents that cite application 1020180056789"
ํ๊ตญ์ด ๋ฌธ์
ํ๊ตญ ํนํ์ ๋ณด ๊ฒ์์๋น์ค(KIPRIS) API๋ฅผ ์ํ MCP(Model Context Protocol) ์๋ฒ์ ๋๋ค.
Claude Desktop, Cursor, Windsurf ๋๋ ๋ค๋ฅธ MCP ํด๋ผ์ด์ธํธ์ ์ฐ๋ํ์ฌ ์์ฐ์ด๋ก ํ๊ตญ ํนํ๋ฅผ ๊ฒ์ํ๊ณ ๋ถ์ํ ์ ์์ต๋๋ค.
โจ ๊ธฐ๋ฅ
Core Tools
| Tool | ์ค๋ช |
|---|---|
kipris_search_patents |
์ถ์์ธ๋ช ์ผ๋ก ํนํ ๊ฒ์ |
kipris_get_patent_detail |
์ถ์๋ฒํธ๋ก ํนํ ์์ธ ์ ๋ณด ์กฐํ |
kipris_get_citing_patents |
ํน์ ํนํ๋ฅผ ์ธ์ฉํ ํํ ํนํ ์กฐํ |
Extended Tools (ํฅํ ๊ตฌํ ์์ )
- [ ]
kipris_get_cpc_codes- CPC ๋ถ๋ฅ ์ฝ๋ ์กฐํ - [ ]
kipris_get_inventors- ๋ฐ๋ช ์ ์ ๋ณด ์กฐํ - [ ]
kipris_check_rejection- ๊ฑฐ์ ์ฌ๋ถ ํ์ธ - [ ]
kipris_analyze_rejection_reason- ๊ฑฐ์ ์ฌ์ ๋ถ์
๐ ์ค์น ๋ฐฉ๋ฒ
๋ฐฉ๋ฒ 1: Smithery๋ฅผ ํตํ ์ค์น (๊ถ์ฅ)
# Smithery CLI ์ค์น (์ฒ์ ํ ๋ฒ๋ง)
npm install -g @smithery/cli
# Korean Patent MCP ์๋ฒ ์ค์น
smithery install korean-patent-mcp --client claude
๋ฐฉ๋ฒ 2: uv๋ฅผ ์ฌ์ฉํ ๋ก์ปฌ ์ค์น
# ์ ์ฅ์ ํด๋ก
git clone https://github.com/khreat/korean-patent-mcp.git
cd korean-patent-mcp
# uv๋ก ์ค์น (๊ถ์ฅ)
uv pip install -e .
# ๋๋ pip์ผ๋ก ์ค์น
pip install -e .
์๊ตฌ์ฌํญ
- Python 3.10+
- KIPRIS Plus Open API ํค (๋ฐ๊ธ ์ฌ์ดํธ)
๐ง ์ค์
API ํค ์ค์
.env ํ์ผ์ ์์ฑํ๊ณ API ํค๋ฅผ ์ค์ ํฉ๋๋ค:
echo "KIPRIS_API_KEY=your_api_key_here" > .env
๋๋ ํ๊ฒฝ๋ณ์๋ก ์ค์ :
export KIPRIS_API_KEY="your_api_key_here"
๐ ํด๋ผ์ด์ธํธ ์ฐ๋
Claude Desktop
~/Library/Application Support/Claude/claude_desktop_config.json (macOS) ๋๋
%APPDATA%\Claude\claude_desktop_config.json (Windows) ํ์ผ์ ํธ์งํฉ๋๋ค:
{
"mcpServers": {
"korean-patent": {
"command": "uv",
"args": ["run", "korean-patent-mcp"],
"env": {
"KIPRIS_API_KEY": "your_api_key_here"
}
}
}
}
Cursor / Windsurf
MCP ์ค์ ์์ ๋ค์์ ์ถ๊ฐํฉ๋๋ค:
{
"korean-patent": {
"command": "uv",
"args": ["run", "korean-patent-mcp"],
"env": {
"KIPRIS_API_KEY": "your_api_key_here"
}
}
}
๐ ์ฌ์ฉ ์์
Claude Desktop์์ ๋ค์๊ณผ ๊ฐ์ด ์ง๋ฌธํ ์ ์์ต๋๋ค:
ํนํ ๊ฒ์
์ผ์ฑ์ ์๊ฐ ์ถ์ํ ํนํ ์ค ๋ฑ๋ก๋ ๊ฒ๋ค์ ๋ณด์ฌ์ค
์ถฉ๋ถ๋ํ๊ต ์ฐํํ๋ ฅ๋จ์ ์ต๊ทผ ํนํ๋ฅผ ๊ฒ์ํด์ค
ํนํ ์์ธ ์ ๋ณด
์ถ์๋ฒํธ 1020200123456์ ํนํ ์์ธ ์ ๋ณด๋ฅผ ์๋ ค์ค
์ธ์ฉ ํนํ ๋ถ์
์ถ์๋ฒํธ 1020180056789๋ฅผ ์ธ์ฉํ ํนํ๋ค์ ์ฐพ์์ค
๐งช ๊ฐ๋ฐ & ํ ์คํธ
MCP Inspector๋ก ํ ์คํธ
npx @modelcontextprotocol/inspector uv run korean-patent-mcp
Smithery Dev ๋ชจ๋
smithery dev
๐ ํ๋ก์ ํธ ๊ตฌ์กฐ
korean-patent-mcp/
โโโ pyproject.toml # ํจํค์ง ์ค์ (uv/pip ํธํ)
โโโ smithery.yaml # Smithery ๋ฐฐํฌ ์ค์
โโโ README.md
โโโ .env.example
โโโ src/
โโโ korean_patent_mcp/
โโโ __init__.py
โโโ server.py # MCP ์๋ฒ & Tool ์ ์
โโโ kipris_api.py # KIPRIS API ํด๋ผ์ด์ธํธ
๐ API ์๋ต ํ์
๋ชจ๋ Tool์ response_format ํ๋ผ๋ฏธํฐ๋ฅผ ์ง์ํฉ๋๋ค:
markdown(๊ธฐ๋ณธ๊ฐ): ์ฌ๋์ด ์ฝ๊ธฐ ์ข์ ํ์json: ํ๋ก๊ทธ๋๋ฐ ์ฒ๋ฆฌ์ ์ ํฉํ ๊ตฌ์กฐํ๋ ํ์
โ ๏ธ ์ฃผ์์ฌํญ
- KIPRIS API๋ ํธ์ถ ์ ํ์ด ์์ ์ ์์ต๋๋ค
- ๋๋ ๊ฒ์ ์ ํ์ด์ง๋ค์ด์ ์ ํ์ฉํ์ธ์
- API ํค๋ ์ ๋ ๊ณต๊ฐ ์ ์ฅ์์ ์ปค๋ฐํ์ง ๋ง์ธ์
๐ ๋ผ์ด์ ์ค
MIT License
๐ค ๊ธฐ์ฌ
๋ฒ๊ทธ ๋ฆฌํฌํธ, ๊ธฐ๋ฅ ์ ์, PR ๋ชจ๋ ํ์ํฉ๋๋ค!
๐ Contact
- Tech Curator: https://techcurator.kr
- DiME: https://www.dime.kr
- E-mail: jkh25@techcurator.kr / ceo@techcurator.kr
Made with โค๏ธ for Korean patent research
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
E2B
Using MCP to run code via e2b.