This MCP (Multi-platform Communication Protocol) server provides access to Naver Search APIs, allowing AI agents to search for various types of content on Naver.
- Search for blogs, news, books, images, shopping items, and more
- Multiple search categories with pagination support
- Structured text responses optimized for LLM consumption
- Check for adult content
- Convert keyboard input errors (errata)
- Python 3.12+
- Naver Developer API credentials
- You can obtain these credentials by signing up at the Naver Developers portal.
- And You can check my blog Naver Search API MCP Server, too.
- Clone the repository:
git clone https://github.com/jikime/py-mcp-naver-search.git
cd py-mcp-naver-search- uv installation
curl -LsSf https://astral.sh/uv/install.sh | sh- Create a virtual environment and install dependencies:
uv venv -p 3.12
source .venv/bin/activate
pip install -r requirements.txt- Create a
.envfile with your Naver API credentials:
cp env.example .env
vi .env
NAVER_CLIENT_ID=your_client_id_here
NAVER_CLIENT_SECRET=your_client_secret_here
- Build the Docker image:
docker build -t py-mcp-naver-search .- Run the container:
docker run py-mcp-naver-search- Run the server:
mcp run server.py- Run the MCP Inspector
mcp dev server.pyAdd the server configuration to your MCP settings file:
- To install automatically via Smithery:
npx -y @smithery/cli install @jikime/py-mcp-naver-search --client claude- To install manually
open
~/Library/Application Support/Claude/claude_desktop_config.json
Add this to the mcpServers object:
{
"mcpServers": {
"Google Toolbox": {
"command": "/path/to/bin/uv",
"args": [
"--directory",
"/path/to/py-mcp-naver-search",
"run",
"server.py"
]
}
}
}open ~/.cursor/mcp.json
Add this to the mcpServers object:
{
"mcpServers": {
"Google Toolbox": {
"command": "/path/to/bin/uv",
"args": [
"--directory",
"/path/to/py-mcp-naver-search",
"run",
"server.py"
]
}
}
}{
"mcpServers": {
"Google Toolbox": {
"command": "docker",
"args": [
"run",
"-i",
"--rm",
"py-mcp-naver-search"
]
}
}
}The repository includes a client script for testing:
# Basic search
uv run client.py blog "Python programming" display=5 page=1
# News search with sorting
uv run client.py news "AI" display=10 page=1 sort=date
# Image search with filtering
uv run client.py image "cat" display=10 filter=large
# Check for adult content
uv run client.py adult "your query"
# Errata correction
uv run client.py errata "spdlqj"The server supports the following search categories:
blog- Blog postsnews- News articlesbook- Booksadult- Adult content checkencyc- Encyclopedia entriescafe_article- Cafe articleskin- Knowledge iN Q&Alocal- Local business informationerrata- Keyboard input error correctionshop- Shopping itemsdoc- Academic papers and documentsimage- Imageswebkr- Web documents
search_blog(query: str, display: int = 10, page: int = 1, sort: str = "sim") -> str
Searches for blogs on Naver using the given keyword.
search_news(query: str, display: int = 10, page: int = 1, sort: str = "sim") -> str
Searches for news on Naver using the given keyword.
search_book(query: str, display: int = 10, page: int = 1, sort: str = "sim") -> str
Searches for book information on Naver using the given keyword.
check_adult_query(query: str) -> str
Determines if the input query is an adult search term.
search_encyclopedia(query: str, display: int = 10, page: int = 1, sort: str = "sim") -> str
Searches for encyclopedia information on Naver using the given keyword.
search_cafe_article(query: str, display: int = 10, page: int = 1, sort: str = "sim") -> str
Searches for cafe articles on Naver using the given keyword.
search_kin(query: str, display: int = 10, page: int = 1, sort: str = "sim") -> str
Searches for Knowledge iN Q&A on Naver using the given keyword.
search_local(query: str, display: int = 5, page: int = 1, sort: str = "random") -> str
Searches for local business information using the given keyword.
correct_errata(query: str) -> str
Converts Korean/English keyboard input errors.
search_shop(query: str, display: int = 10, page: int = 1, sort: str = "sim") -> str
Searches for shopping product information on Naver using the given keyword.
search_doc(query: str, display: int = 10, page: int = 1) -> str
Searches for academic papers, reports, etc. using the given keyword.
search_image(query: str, display: int = 10, page: int = 1, sort: str = "sim", filter: str = "all") -> str
Searches for images using the given keyword.
search_webkr(query: str, display: int = 10, page: int = 1) -> str
Searches for web documents using the given keyword.
GET naver://available-search-categories
Returns a list of Naver search categories available on this MCP server.
All tools return responses in structured text format, optimized for LLM processing:
Naver Blog search results (total 12,345 of 1~10):
### Result 1
Title(title): Sample Blog Post
Link(link): https://blog.example.com/post1
Description(description): This is a sample blog post about...
Blogger name(bloggername): John Doe
Blogger link(bloggerlink): https://blog.example.com
Post date(postdate): 20250429
### Result 2
...
This project is licensed under the MIT License - see the LICENSE file for details.