Korea Local Data MCP Server (Naver Map, Kakao Map)

An MCP server that gives AI agents live Korean local business data: search places on Naver Map and Kakao Map, and read Naver Place visitor reviews. Connect it to Claude, ChatGPT, Cursor or any MCP client and ask in plain language:

• "Find the top 20 cafes in Seongsu on Naver Map and summarize what reviewers say about the top 3."
• "List dermatology clinics near Gangnam Station with phone numbers."
• "Compare the Naver and Kakao ratings of restaurants in Euljiro."

Google Maps coverage of South Korea is thin. Naver Map and Kakao Map are what people in Korea actually use, so this is where the complete listings, ratings and reviews are.

No Naver or Kakao login or API key is needed. You only need an Apify account.

Tools

Tool	Input	Returns
search_naver_places	query (Korean keyword such as 성수 카페), maxPlaces 1–100 (default 20)	Places in Naver's ranking order: name, category, address, phone, coordinates, rating (visitorReviewScore), visitor and blog review counts, booking flag, amenities, Naver Map URL
get_naver_place_reviews	place (Naver place id or Naver Map URL), maxReviews 1–100 (default 20)	The place's average rating and review count, plus the newest visitor reviews: rating, text, visit date, written date, keyword tags with English codes, ordered menu item, owner reply
search_kakao_places	query, maxPlaces 1–100 (default 15)	Places from Kakao Map with exactly the same fields as the Naver tool (homepage is filled on Kakao only)

Every result also has status (completed, partial or budgetLimited), a message that explains anything unusual, reportedTotal (how many the site says exist) and returnedCount. Every field is always present; a value the site does not show is null. Numbers are numbers.

Reviewer names, profile pictures and user IDs are never requested or returned.

Korean keywords that combine an area and a category work best: 강남 맛집 (Gangnam restaurants), 홍대 미용실 (Hongdae hair salons), 부산 해운대 호텔 (Haeundae hotels). Agents usually translate an English request into such a keyword on their own.

Connect

The MCP endpoint (Streamable HTTP) is:

https://magenta-courser--korea-local-data-mcp.apify.actor/mcp

Authenticate with your Apify API token as a Bearer token.

Claude Code

$claude mcp add --transport http korea-local-data https://magenta-courser--korea-local-data-mcp.apify.actor/mcp --header "Authorization: Bearer YOUR_APIFY_TOKEN"

Any client that takes a JSON config

{
  "mcpServers": {
    "korea-local-data": {
      "type": "http",
      "url": "https://magenta-courser--korea-local-data-mcp.apify.actor/mcp",
      "headers": { "Authorization": "Bearer YOUR_APIFY_TOKEN" }
    }
  }
}

Example result

search_naver_places with {"query": "성수 카페", "maxPlaces": 1}:

{
  "source": "naver",
  "query": "성수 카페",
  "status": "completed",
  "message": null,
  "reportedTotal": 2346,
  "returnedCount": 1,
  "places": [
    {
      "source": "naver",
      "query": "성수 카페",
      "rank": 1,
      "id": "1922651675",
      "name": "노틀던",
      "category": "카페,디저트",
      "businessType": "cafe",
      "roadAddress": "서울숲2길 11 1층",
      "address": "서울특별시 성동구 성수동1가 685-501 1층",
      "district": "서울 성동구 성수동1가",
      "phone": null,
      "latitude": 37.5473614,
      "longitude": 127.0400154,
      "visitorReviewScore": 4.97,
      "visitorReviewCount": 1160,
      "blogCafeReviewCount": 1463,
      "hasBooking": true,
      "amenities": ["포장", "예약", "단체 이용 가능", "간편결제", "제로페이"],
      "homepage": null,
      "url": "https://map.naver.com/p/entry/place/1922651675",
      "scrapedAt": "2026-10-02T17:35:22.080Z"
    }
  ]
}

One row of get_naver_place_reviews (reviews[]), next to the top-level placeName, placeRating and placeReviewCount:

{
  "source": "naver",
  "placeId": "1922651675",
  "placeName": "노틀던",
  "reviewId": "6abf33448f9dd532461b9928",
  "rating": 5,
  "text": "디저트도 예쁘고 맛있어요!! 다른메뉴도 먹으러 또오고싶어요",
  "visitedAt": "2026-10-02T04:23:12.000Z",
  "createdAt": "2026-10-02T04:29:56.000Z",
  "visitCount": 1,
  "verificationType": "receipt",
  "menuItem": "노틀던 누아",
  "keywords": ["커피가 맛있어요", "디저트가 맛있어요", "아늑해요", "음악이 좋아요"],
  "keywordCodes": ["coffee_good", "dessert_good", "cozy", "music_good"],
  "hasOwnerReply": false,
  "ownerReply": null,
  "url": "https://map.naver.com/p/entry/place/1922651675?placePath=/review",
  "scrapedAt": "2026-10-02T17:35:26.980Z"
}

The place field names are the same as in the batch Actors listed below, so data from both can be merged.

Pricing

Pay per event:

• tool-call: one per tool call that returns at least one item.
• place: one per place returned by search_naver_places or search_kakao_places.
• review: one per review returned by get_naver_place_reviews.

What you are not charged for:

• A tool call that fails (the site blocked the request, a wrong place id, invalid arguments) or returns nothing.
• Connecting, initialize and tools/list.
• Items you did not receive. If the run's spending limit cannot pay for everything you asked for, the result is cut to what was charged, status is budgetLimited and message says so. If only part of the pages could be read, you get and pay for that part (status: "partial").

As with any Actor in Standby mode, the small container that serves your requests runs in your Apify account. It uses 256 MB and stops 60 seconds after your last request; in our tests one session cost about $0.001 of platform usage for a single call and about $0.002 for ten calls.

Run it without an MCP client

You can also press Start (or call the Actor through the Apify API) to make one tool call. The items go to the run's dataset and a short summary to the key-value store record RUN_SUMMARY.

Input	Meaning
tool	search_naver_places (default), get_naver_place_reviews or search_kakao_places
query	Search keyword for the two search tools, e.g. 성수 카페
place	Naver place id or Naver Map URL for get_naver_place_reviews
maxItems	1–100 places or reviews

Need bulk data instead?

This server is built for quick agent lookups (up to 100 items per call, answers in a few seconds). For large exports, scheduled monitoring, opening hours, menus, photos and full review histories, use the batch Actors. They cost less per item:

• Naver Place Search Scraper
• Naver Place Reviews Scraper
• Kakao Map Place Search Scraper

Notes

• Names, categories, addresses and review text are returned in Korean, as shown on Naver and Kakao.
• Naver and Kakao place IDs are separate systems. To decide that two rows are the same business, compare phone, address and coordinates.
• Ratings on Naver and Kakao come from different reviewers and are not directly comparable. A place nobody has rated has visitorReviewScore: null.
• The first request after a pause takes 2-4 seconds longer while the server starts.
• Naver and Kakao sometimes reject requests. The server retries up to 4 times with a new proxy IP and gives up after about 45 seconds with a clear error; that call is free.
• Short naver.me links are not supported as input; use the full Naver Map URL or the numeric id.
• This server reads publicly visible listing and review content only and does not log in to any account.