py-mcp-naver

py-mcp-naver avatar

by pfldy2850

Community Servers

python MCP NAVER

What is py-mcp-naver

Naver MCP Server

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.

Pre-requisite

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

Installation

from PyPi (Claude Desktop)

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>

from PyPi (Cursor)

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>

from source

# 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.

Features

This server provides the following tools for interacting with Naver OpenAPI:

  • Blog Search: Search blog posts on Naver.
  • News Search: Search news articles on Naver.
  • Book Search: Search books and advanced book information.
  • Adult Content Check: Check if a search term is adult content.
  • Encyclopedia Search: Search encyclopedia entries.
  • Cafe Article Search: Search articles in Naver cafes.
  • Q&A Search: Search questions and answers on Naver.
  • Local Search: Search local information.
  • Spelling Correction: Correct spelling errors in text.
  • Web Search: Search web pages.
  • Image Search: Search images with filters.
  • Shopping Search: Search shopping items with filters.
  • Document Search: Search documents.

Naver MCP Tools

The following tools are implemented in the server:

Blog Search

Search blog posts on Naver.

search_blog(query: str, display: int = 10, start: int = 1, sort: str = "sim")

News Search

Search news articles on Naver.

search_news(query: str, display: int = 10, start: int = 1, sort: str = "sim")

Book Search

Search books on Naver.

search_book(query: str, display: int = 10, start: int = 1, sort: str = "sim")

Advanced Book Search

Get detailed book information using title or ISBN.

get_book_adv(query: str = None, d_titl: str = None, d_isbn: str = None, ...)

Adult Content Check

Check if a search term is adult content.

adult_check(query: str)

Encyclopedia Search

Search encyclopedia entries on Naver.

search_encyc(query: str, display: int = 10, start: int = 1)

Cafe Article Search

Search articles in Naver cafes.

search_cafe_article(query: str, display: int = 10, start: int = 1, sort: str = "sim")

Q&A Search

Search questions and answers on Naver.

search_kin(query: str, display: int = 10, start: int = 1, sort: str = "sim")

Local Search

Search local information on Naver.

search_local(query: str, display: int = 10, start: int = 1, sort: str = "random")

Spelling Correction

Correct spelling errors in a given text.

fix_spelling(query: str)

Web Search

Search web pages on Naver.

search_webkr(query: str, display: int = 10, start: int = 1)

Image Search

Search images on Naver with filters.

search_image(query: str, display: int = 10, start: int = 1, sort: str = "sim", filter: str = "all")

Shopping Search

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)

Document Search

Search documents on Naver.

search_doc(query: str, display: int = 10, start: int = 1)

License

This project is open source software licensed as MIT.

Leave a Comment

Comments section will be available soon. Stay tuned!

Frequently Asked Questions

What is MCP?

MCP (Model Context Protocol) is an open protocol that standardizes how applications provide context to LLMs. Think of MCP like a USB-C port for AI applications, providing a standardized way to connect AI models to different data sources and tools.

What are MCP Servers?

MCP Servers are lightweight programs that expose specific capabilities through the standardized Model Context Protocol. They act as bridges between LLMs like Claude and various data sources or services, allowing secure access to files, databases, APIs, and other resources.

How do MCP Servers work?

MCP Servers follow a client-server architecture where a host application (like Claude Desktop) connects to multiple servers. Each server provides specific functionality through standardized endpoints and protocols, enabling Claude to access data and perform actions through the standardized protocol.

Are MCP Servers secure?

Yes, MCP Servers are designed with security in mind. They run locally with explicit configuration and permissions, require user approval for actions, and include built-in security features to prevent unauthorized access and ensure data privacy.