Wraps the Naver OpenAPI to bring Korean search capabilities directly into Claude. You can search blogs, news, books, shopping items, and local businesses, plus get spelling corrections and adult content filtering. Requires Naver developer credentials but handles the API authentication for you. Reach for this when you need to pull Korean content or validate Korean text without switching between Claude and a browser. Each tool maps to specific Naver endpoints like blog search, news search, and their local business directory, making it straightforward to integrate Korean web data into your workflows.
A server implementation for Naver OpenAPI using the Model Context Protocol (MCP). This project provides tools to interact with various Naver services, such as searching blogs, news, books, and more.
To use the Naver MCP server, you need to apply for access to the Naver Open API. You can apply for Open API access at the link below:
https://developers.naver.com/apps/#/register=datalab
Install it to Claude Desktop with (uv):
uv pip install mcp-naver
uv run python -m mcp-naver.hosts.claude_desktop \
-e NAVER_CLIENT_ID=<YOUR NAVER CLIENT ID> \
-e NAVER_CLIENT_SECRET=<YOUR NAVER CLIENT SECRET>
Install it to Claude Desktop with:
pip install mcp-naver
python -m mcp-naver.hosts.claude_desktop \
-e NAVER_CLIENT_ID=<YOUR NAVER CLIENT ID> \
-e NAVER_CLIENT_SECRET=<YOUR NAVER CLIENT SECRET>
Install it to Cursor with (uv):
uv pip install mcp-naver
uv run python -m mcp-naver.hosts.cursor \
-e NAVER_CLIENT_ID=<YOUR NAVER CLIENT ID> \
-e NAVER_CLIENT_SECRET=<YOUR NAVER CLIENT SECRET>
# Clone the repository
git clone https://github.com/pfldy2850/py-mcp-naver.git
# Navigate into the project directory
cd py-mcp-naver
# Synchronize dependencies
uv sync --dev --all-extras
Run it with:
# Start the server (Using FastMCP CLI)
fastmcp install mcp_naver/server.py -e NAVER_CLIENT_ID=<YOUR NAVER CLIENT ID> -e NAVER_CLIENT_SECRET=<YOUR NAVER CLIENT SECRET>
The tool sets up everything you need to create an MCP server integrated with Naver OpenAPI.
This server provides the following tools for interacting with Naver OpenAPI:
The following tools are implemented in the server:
Search blog posts on Naver.
search_blog(query: str, display: int = 10, start: int = 1, sort: str = "sim")
Search news articles on Naver.
search_news(query: str, display: int = 10, start: int = 1, sort: str = "sim")
Search books on Naver.
search_book(query: str, display: int = 10, start: int = 1, sort: str = "sim")
Get detailed book information using title or ISBN.
get_book_adv(query: str = None, d_titl: str = None, d_isbn: str = None, ...)
Check if a search term is adult content.
adult_check(query: str)
Search encyclopedia entries on Naver.
search_encyc(query: str, display: int = 10, start: int = 1)
Search articles in Naver cafes.
search_cafe_article(query: str, display: int = 10, start: int = 1, sort: str = "sim")
Search questions and answers on Naver.
search_kin(query: str, display: int = 10, start: int = 1, sort: str = "sim")
Search local information on Naver.
search_local(query: str, display: int = 10, start: int = 1, sort: str = "random")
Correct spelling errors in a given text.
fix_spelling(query: str)
Search web pages on Naver.
search_webkr(query: str, display: int = 10, start: int = 1)
Search images on Naver with filters.
search_image(query: str, display: int = 10, start: int = 1, sort: str = "sim", filter: str = "all")
Search shopping items on Naver with filters.
search_shop(query: str, display: int = 10, start: int = 1, sort: str = "sim", filter: str = None, exclude: str = None)
Search documents on Naver.
search_doc(query: str, display: int = 10, start: int = 1)
This project is open source software licensed as MIT.