DataGoKr Public

Search 109k Korean public datasets from data.go.kr by topic or column name (bge-m3 hybrid search over titles, descriptions and 1.5M column fields).

CommunityOnlineNo sign-inGlobalFreeRead-only

What it can do

  • Search: 필요한 공공데이터를 자연어로 찾을 때 사용합니다. Search Korean public datasets by topic. 반환: id 식별자, title 제목, org_nm 기관, dtype 유형, access_kind 접근방법, page_url 출처, rank 순위, matched_fields 관련 컬럼, last_probe_ok 최근 확인
  • Show: 검색 후 데이터셋의 구조와 사용법을 확인할 때 사용합니다. Inspect a dataset before use. 반환: id/title/org_nm 식별 정보, category 분류, dtype/access_kind 접근방법, page_url 출처, portal_updated 갱신일, columns 최대 50개 컬럼, operations 기능 요
  • Record: 로컬 클라이언트의 조회·신청·다운로드에 필요한 메타데이터만 반환합니다. Return allowlisted metadata for client-side fetch, apply and download. 반환 / Returns: id/title/list_title/org_nm, dtype/access_kind, page_url/external_ur

What data it sees

Do you need an account

No: the server works without sign-in

Search 109k Korean public datasets from data.go.kr by topic or column name (bge-m3 hybrid search over titles, descriptions and 1.5M column fields). Read-only: search, show, record, fields, get_preview, download_url. BYOK for previews. Rate limited per IP. Source and local package: https://github.com/twlaude/datagokr.

How to connect

How to connect DataGoKr Public to Claude

The server address to paste into Claude settings:

https://datagokr-public--zlans28.run.tools

  1. Open Claude (claude.ai or the desktop app).
  2. Go to Settings → Connectors.
  3. Click Add custom connector.
  4. Paste the server address copied below into Remote MCP server URL and click Add.
  5. In a chat, click + → Connectors and switch the new connector on.

Custom connectors are available on Free, Pro, Max, Team and Enterprise plans (Free is limited to one). On Team and Enterprise an organization Owner adds the connector first under Organization settings → Connectors.

Authorization

After you click Add, a sign-in window for the service opens. Sign in with your own account and approve access. Claude never sees your password.

How to connect DataGoKr Public to ChatGPT

The server address to paste into ChatGPT settings:

https://datagokr-public--zlans28.run.tools

  1. Open ChatGPT in a browser (chatgpt.com). A Plus, Pro, Business, Enterprise or Edu plan is required.
  2. Turn on developer mode once: Settings → Apps → Advanced settings → Developer mode.
  3. Open Settings → Connectors and click Create.
  4. Fill in the form: Name (anything), Description (one line about what the service does), MCP server URL (copy it below).
  5. Under Authentication choose OAuth if the service requires sign-in, otherwise None. Click Create.
  6. In a new chat open + → Apps/Connectors and enable the connector.

OpenAI has renamed this section before (Connectors → Apps/Plugins). If the label differs, search settings for "developer mode". On Business/Enterprise workspaces an admin must allow custom connectors first.

Authorization

On first use ChatGPT opens the service's sign-in window. Sign in and approve access.

How to connect DataGoKr Public to Cursor

The server address to paste into Cursor settings:

https://datagokr-public--zlans28.run.tools

Fastest: click Open in Cursor below and confirm the prompt.

Manually:

  1. In Cursor open Settings → Cursor Settings → MCP and click Add new global MCP server.
  2. Paste the JSON copied below into ~/.cursor/mcp.json (per project: .cursor/mcp.json in the repo root).
  3. Save the file. The server appears in the MCP list; authorize it there if asked.

Authorization

If the service needs sign-in, an authorize button appears next to the server in the MCP list.

Server tool list (6)

Raw names from tools/list. Only developers need these.

search필요한 공공데이터를 자연어로 찾을 때 사용합니다. Search Korean public datasets by topic. 반환: id 식별자, title 제목, org_nm 기관, dtype 유형, access_kind 접근방법, page_url 출처, rank 순위, matched_fields 관련 컬럼, last_probe_ok 최근 확인 결과. Returns ranked metadata, not dataset contents. 예시 / Examples: '전국 주차장', '서울 병원 위치'. 찾는 컬럼 이름이 정해져 있으면(예: 위도·경도·수온) search 대신 fields를 쓰세요. If you already know the column names you need, use `fields` instead of `search`.
show검색 후 데이터셋의 구조와 사용법을 확인할 때 사용합니다. Inspect a dataset before use. 반환: id/title/org_nm 식별 정보, category 분류, dtype/access_kind 접근방법, page_url 출처, portal_updated 갱신일, columns 최대 50개 컬럼, operations 기능 요약, examples 요청 예시, note 생략 안내. Examples / 예시: '15028200 컬럼 보여줘', '15000001 API 사용법 알려줘'.
record로컬 클라이언트의 조회·신청·다운로드에 필요한 메타데이터만 반환합니다. Return allowlisted metadata for client-side fetch, apply and download. 반환 / Returns: id/title/list_title/org_nm, dtype/access_kind, page_url/external_url, parent_id, versions/version_keys, examples (request templates), std_meta, api_sample. 원본 raw와 내부 상태는 제외하며 서버에서 신청하거나 저장하지 않습니다. Raw catalog records and internal state are never returned; no application or download is performed.
fields컬럼 조건이 있으면 search 말고 이 툴입니다. Use this, not `search`, when the query names columns. 반환: id 식별자, title 제목, org_nm 기관, dtype/access_kind 접근방법, page_url 원문, rank 순위, matched_fields 일치 컬럼, last_probe_ok 확인 결과. n은 최대 20입니다. names에 적은 컬럼을 '모두' 가진 데이터셋만 돌려주며, search보다 느립니다(수십 초). Slower than `search` (tens of seconds) but far more precise for column-shaped questions. 예시 / Examples: '위도와 경도가 있는 데이터', '시군구명과 주차구획수가 있는 자료'.
get_preview다운로드 전에 첫 행을 확인하거나 접근방법을 알고 싶을 때 사용합니다. Preview first rows. 반환: access_kind 접근방법, data.columns/rows 최대 50컬럼/20행, total 전체 건수, source_note 출처 또는 url/parent_id/request_templates/message 접근 안내. PORTAL_FILE requires the caller's X-DataGoKr-Key header; keys are never returned. 예시 / Examples: '15028200 처음 5행 보여줘', '15000001 미리보기 방법 알려줘'.
download_url전체 자료를 사용자 컴퓨터에서 저장하고 싶을 때 사용합니다. Obtain client-side download instructions. 반환: access_kind 접근방법, url 또는 post_url/get_url 원본 주소, params 요청값, version_keys 파일 버전, message 실행 절차, page_url 포털 출처. 서버는 파일을 저장하지 않습니다. 예시 / Examples: '15028200 전체 JSON 받는 법', '15000001 원본 파일 다운로드 주소'.