Korean Data MCP Server

Local setup required. This server has to be cloned and prepared on your machine before you register it in Claude Code.
1

Set the server up locally

Run this once to clone and prepare the server before adding it to Claude Code.

Run in terminal
pip install korean-data-mcp
2

Register it in Claude Code

After the local setup is done, run this command to point Claude Code at the built server.

Run in terminal
claude mcp add -e "APIFY_TOKEN=${APIFY_TOKEN}" korean-data-mcp -- node "<FULL_PATH_TO_KOREAN_DATA_MCP>/dist/index.js"

Replace <FULL_PATH_TO_KOREAN_DATA_MCP>/dist/index.js with the actual folder you prepared in step 1.

Required:APIFY_TOKEN
README.md

Real-time Korean web data for AI assistants powered by Apify actors.

πŸ‡°πŸ‡· Korean Data MCP

Real-time Korean web data for AI assistants β€” powered by Apify actors.

A Model Context Protocol (MCP) server that gives Claude, Cursor, and other AI tools direct access to live Korean web data β€” including Naver reviews, Melon music charts, Daangn/Bunjang marketplace listings, Korean news, and Musinsa fashion rankings.


πŸ›  Available Tools

Tool Description
get_naver_place_reviews Fetch reviews for any Naver Place (restaurant, cafe, shop, etc.)
get_melon_chart Real-time / daily / weekly Korean music chart (μ‹€μ‹œκ°„ 차트)
search_daangn Search Daangn Market (λ‹Ήκ·Όλ§ˆμΌ“) C2C listings
search_bunjang Search Bunjang (번개μž₯ν„°) marketplace
search_naver_news Search Naver News articles by keyword
search_naver_places Search Naver Map places by keyword + location
get_musinsa_ranking Musinsa fashion ranking by category

πŸš€ Quick Start

1. Get an Apify API Token

Sign up at apify.com (free tier: $5/month credit included).
Copy your token from console.apify.com/account/integrations.

2. Install

pip install korean-data-mcp

Or with uv (recommended):

uv add korean-data-mcp

3. Set Environment Variable

export APIFY_TOKEN="your_apify_token_here"

4. Run the MCP Server

korean-data-mcp

βš™οΈ Claude Desktop Configuration

Add to ~/Library/Application Support/Claude/claude_desktop_config.json:

{
  "mcpServers": {
    "korean-data": {
      "command": "korean-data-mcp",
      "env": {
        "APIFY_TOKEN": "your_apify_token_here"
      }
    }
  }
}

Or with uvx (no install needed):

{
  "mcpServers": {
    "korean-data": {
      "command": "uvx",
      "args": ["korean-data-mcp"],
      "env": {
        "APIFY_TOKEN": "your_apify_token_here"
      }
    }
  }
}

πŸ’¬ Usage Examples

Once connected to Claude Desktop or another MCP client:

"What are the top 10 songs on Melon chart right now?"

"Find cafes near Hongdae on Naver Map and show their reviews."

"Search Daangn for iPhone 15 Pro listings in Seoul."

"What are the trending news stories on Naver today about 인곡지λŠ₯?"

"Show me the Musinsa top 50 outer clothing items."

πŸ”§ Cursor / VS Code Configuration

Add to .cursor/mcp.json or .vscode/mcp.json:

{
  "servers": {
    "korean-data": {
      "type": "stdio",
      "command": "korean-data-mcp",
      "env": {
        "APIFY_TOKEN": "your_apify_token_here"
      }
    }
  }
}

πŸ“Š Data Sources

All data is fetched live via Apify actors:

Actor Apify Store
Naver Place Reviews oxygenated_quagmire/naver-place-reviews
Melon Chart oxygenated_quagmire/melon-chart-scraper
Daangn Market oxygenated_quagmire/daangn-market-scraper
Bunjang Market oxygenated_quagmire/bunjang-market-scraper
Naver News oxygenated_quagmire/naver-news-scraper
Naver Place Search oxygenated_quagmire/naver-place-search
Musinsa Ranking oxygenated_quagmire/musinsa-ranking-scraper

πŸ’° Pricing

  • Apify Free Tier: $5/month credit β€” enough for ~1,000–5,000 tool calls
  • Actor runs are billed per 1,000 items returned ($0.50/1K items)
  • No additional cost for this MCP server itself

πŸ— Development

git clone https://github.com/leadbrain/korean-data-mcp
cd korean-data-mcp
pip install -e ".[dev]"
export APIFY_TOKEN="your_token"
python -m korean_data_mcp.server

πŸ“„ License

MIT License β€” see LICENSE


🀝 Contributing

Issues and PRs welcome at github.com/leadbrain/korean-data-mcp


Built on FastMCP Β· Data from Apify

Tools (7)

get_naver_place_reviewsFetch reviews for any Naver Place (restaurant, cafe, shop, etc.)
get_melon_chartReal-time / daily / weekly Korean music chart (μ‹€μ‹œκ°„ 차트)
search_daangnSearch Daangn Market (λ‹Ήκ·Όλ§ˆμΌ“) C2C listings
search_bunjangSearch Bunjang (번개μž₯ν„°) marketplace
search_naver_newsSearch Naver News articles by keyword
search_naver_placesSearch Naver Map places by keyword + location
get_musinsa_rankingMusinsa fashion ranking by category

Environment Variables

APIFY_TOKENrequiredYour Apify API token for accessing web scraping actors

Configuration

claude_desktop_config.json
{"mcpServers": {"korean-data": {"command": "korean-data-mcp", "env": {"APIFY_TOKEN": "your_apify_token_here"}}}}

Try it

β†’What are the top 10 songs on the Melon chart right now?
β†’Find cafes near Hongdae on Naver Map and show their reviews.
β†’Search Daangn for iPhone 15 Pro listings in Seoul.
β†’What are the trending news stories on Naver today about AI?
β†’Show me the Musinsa top 50 outer clothing items.

Frequently Asked Questions

What are the key features of Korean Data MCP?

Real-time access to Naver Place reviews and location search. Live retrieval of Korean music charts from Melon. Marketplace search capabilities for Daangn and Bunjang. Keyword-based news aggregation from Naver News. Fashion trend tracking via Musinsa rankings.

What can I use Korean Data MCP for?

Market research for consumer trends in South Korea. Automated monitoring of second-hand marketplace listings. Content creation for Korean pop culture and fashion blogs. Local business analysis using Naver Map data.

How do I install Korean Data MCP?

Install Korean Data MCP by running: pip install korean-data-mcp

What MCP clients work with Korean Data MCP?

Korean Data MCP works with any MCP-compatible client including Claude Desktop, Claude Code, Cursor, and other editors with MCP support.

Turn this server into reusable context

Keep Korean Data MCP docs, env vars, and workflow notes in Conare so your agent carries them across sessions.

Need the old visual installer? Open Conare IDE.
Open Conare