korean-keyword-mcp

korean-keyword-mcp

Enables Korean keyword niche analysis using Naver SearchAd API data for CPC, competition, and search volume, with tools for expansion, scoring, and trend discovery.

Category
访问服务器

README

korean-keyword-mcp

MCP server for Korean keyword niche analysis. The only MCP server that exposes Naver SearchAd API data (CPC competition, click rates) for keyword research.

Why This Exists

Feature korean-keyword-mcp Other Naver MCP servers
SearchAd API (CPC, competition index) YES NO
Niche scoring (0-100, A-F grade) YES NO
Blog competition deep analysis YES Basic search only
Keyword expansion + scoring YES NO
Batch comparison analysis YES NO
Trending keyword discovery YES NO

Tools (7)

Tool Description
keyword_expand Expand seed keyword → 50+ related keywords with Quick Score + top N Full Score
niche_score Single keyword full niche analysis (0-100 score + A-F grade)
search_volume Naver SearchAd monthly search volume (PC/mobile split, competition index)
trend Naver DataLab 12-month search trend (monthly relative values 0-100)
blog_competition Blog competition analysis (total results + top 10 posts)
batch_analyze Batch niche analysis for up to 10 keywords with sorted comparison
trending_discover Discover rising-trend keywords from seed keyword's related keywords

Scoring Algorithm

Full Niche Score (100 points)

Component Weight Source
Volume 20 SearchAd API — sweet spot: 1K-30K searches
Competition 30 Blog total results + blogger diversity
Freshness 15 Average post age (older = less competition)
Trend 20 12-month linear regression slope
Efficiency 15 Search volume / blog post ratio

Grades: A (75+), B (60+), C (45+), D (30+), F (<30)

Setup

1. Get Naver API Keys

You need two sets of API credentials:

Naver SearchAd API (for search volume, CPC, competition):

  1. Go to Naver SearchAd
  2. Create an account → Tools → API License
  3. Note your Customer ID, API Key, and Secret Key

Naver Developer API (for DataLab trends, blog search):

  1. Go to Naver Developers
  2. Register application → Select "Search" and "DataLab" APIs
  3. Note your Client ID and Client Secret

2. Configure Claude Desktop

Add to your Claude Desktop config (claude_desktop_config.json):

{
  "mcpServers": {
    "korean-keyword": {
      "command": "npx",
      "args": ["-y", "korean-keyword-mcp"],
      "env": {
        "NAVER_SEARCHAD_CUSTOMER_ID": "your-customer-id",
        "NAVER_SEARCHAD_API_KEY": "your-api-key",
        "NAVER_SEARCHAD_SECRET_KEY": "your-secret-key",
        "NAVER_CLIENT_ID": "your-client-id",
        "NAVER_CLIENT_SECRET": "your-client-secret"
      }
    }
  }
}

3. Verify

Restart Claude Desktop. You should see "korean-keyword" in the MCP servers list with 7 tools available.

Example Usage

Once connected, you can ask Claude:

  • "Analyze the niche potential of '캠핑의자'" → uses niche_score
  • "Find niche keywords related to '다이어트'" → uses keyword_expand
  • "Compare these keywords: 캠핑의자, 캠핑테이블, 캠핑조명" → uses batch_analyze
  • "What keywords related to '캠핑' are trending up?" → uses trending_discover
  • "How much search volume does '에어프라이어' get?" → uses search_volume

Environment Variables

Variable Required Description
NAVER_SEARCHAD_CUSTOMER_ID Yes SearchAd API customer ID
NAVER_SEARCHAD_API_KEY Yes SearchAd API key
NAVER_SEARCHAD_SECRET_KEY Yes SearchAd API secret
NAVER_CLIENT_ID Yes Naver Developer client ID
NAVER_CLIENT_SECRET Yes Naver Developer client secret

License

MIT

推荐服务器

Baidu Map

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。

官方
精选
JavaScript
Playwright MCP Server

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。

官方
精选
TypeScript
Magic Component Platform (MCP)

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。

官方
精选
本地
TypeScript
Audiense Insights MCP Server

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。

官方
精选
本地
TypeScript
VeyraX

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。

官方
精选
本地
graphlit-mcp-server

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。

官方
精选
TypeScript
Kagi MCP Server

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。

官方
精选
Python
e2b-mcp-server

e2b-mcp-server

使用 MCP 通过 e2b 运行代码。

官方
精选
Neon MCP Server

Neon MCP Server

用于与 Neon 管理 API 和数据库交互的 MCP 服务器

官方
精选
Exa MCP Server

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。

官方
精选