Naver Search MCP Server
Provides tools to search Naver services (web, news, blog, etc.) and analyze search trends using Naver DataLab, with all required MCP protocol methods implemented for compatibility with Cursor and Claude Desktop.
README
Naver Search MCP Server (Fixed Version)
This is a fixed version of the original @isnow890/naver-search-mcp package.
What was fixed?
The original package was missing required MCP protocol methods (prompts/list and resources/list), causing "Method not found" errors in MCP clients like Cursor and Claude Desktop.
Changes made:
- ✅ Added missing MCP protocol handlers for
prompts/listandresources/listmethods - ✅ Added
promptsandresourcescapabilities to server configuration - ✅ Improved compatibility with all MCP clients (Cursor, Claude Desktop, etc.)
- ✅ Fixed "Method not found" errors
Original Source
- Original package: @isnow890/naver-search-mcp
- Original author: isnow890
- Original license: MIT
Installation
Quick Install via NPX
npx @d429/naver-search-mcp-fixed
Manual Installation
npm install @d429/naver-search-mcp-fixed
Environment Variables
# Windows
set NAVER_CLIENT_ID=your_client_id
set NAVER_CLIENT_SECRET=your_client_secret
# Linux/Mac
export NAVER_CLIENT_ID=your_client_id
export NAVER_CLIENT_SECRET=your_client_secret
Cursor Configuration
Add to ~/.cursor/mcp.json:
{
"mcpServers": {
"naver-search": {
"command": "npx",
"args": ["-y", "@d429/naver-search-mcp-fixed"],
"env": {
"NAVER_CLIENT_ID": "your_client_id",
"NAVER_CLIENT_SECRET": "your_client_secret"
}
}
}
}
Claude Desktop Configuration
Add to claude_desktop_config.json:
{
"mcpServers": {
"naver-search": {
"command": "npx",
"args": ["-y", "@d429/naver-search-mcp-fixed"],
"env": {
"NAVER_CLIENT_ID": "your_client_id",
"NAVER_CLIENT_SECRET": "your_client_secret"
}
}
}
}
Available Tools
Search Tools:
- search_webkr: Search Naver web documents
- search_news: Search Naver news
- search_blog: Search Naver blogs
- search_cafearticle: Search Naver cafe articles
- search_shop: Search Naver shopping
- search_image: Search Naver images
- search_kin: Search Naver KnowledgeiN
- search_book: Search Naver books
- search_encyc: Search Naver encyclopedia
- search_academic: Search Naver academic papers
- search_local: Search Naver local places
DataLab Tools:
- datalab_search: Analyze search term trends
- datalab_shopping_category: Analyze shopping category trends
- datalab_shopping_by_device: Analyze shopping trends by device
- datalab_shopping_by_gender: Analyze shopping trends by gender
- datalab_shopping_by_age: Analyze shopping trends by age group
- datalab_shopping_keywords: Analyze shopping keyword trends
- datalab_shopping_keyword_by_device: Analyze shopping keyword trends by device
- datalab_shopping_keyword_by_gender: Analyze shopping keyword trends by gender
- datalab_shopping_keyword_by_age: Analyze shopping keyword trends by age group
Prerequisites
- Naver Developers API Key (Client ID and Secret)
- Node.js 18 or higher
- NPM 8 or higher
Getting API Keys
- Visit Naver Developers
- Click "Register Application"
- Enter application name and select ALL of the following APIs:
- Search (for blog, news, book search, etc.)
- DataLab (Search Trends)
- DataLab (Shopping Insight)
- Set the obtained Client ID and Client Secret as environment variables
Build
npm install
npm run build
License
MIT License - Same as original package
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。