# datagokr — 한국 공공데이터 검색 (Korean public data search) (remote · datagokr.dev)

Search Korea's public data portal (data.go.kr): find datasets, schema, preview rows, download steps

- Trust score: 70/100 (medium)
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-09-28

## Components

- remote · `datagokr.dev`: 70/100 (this document), [markdown](https://verifymcp.io/servers/dev-datagokr-datagokr/datagokr.md), [page](https://verifymcp.io/servers/dev-datagokr-datagokr/datagokr)

## Channel facts

- Endpoint: `https://datagokr.dev/mcp`
- Transports: `streamable-http`
- Auth: `none`
- Version: `0.1.1`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically against the live server, and we only credit what we can confirm. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-09-28.

- **Endpoint Security**: 83/100
  - The endpoint's TLS certificate is valid, in date, and uses a strong key.
  - No authorisation is required to call this server. Every tool declares its destructiveHint and none is destructive, so open access doesn't expose one.
  - HTTPS is enforced; there's no plaintext access path.
  - The HSTS (Strict-Transport-Security) header is present.
  - DNSSEC is configured correctly; the domain's records validate against the full chain to the root.
- **Transport & Reachability**: 100/100
  - Verified streamable-http transport via a live MCP handshake.
- **Schema Quality & AI Usability**: 60/100
  - AI-judged instruction clarity (good).
  - Context-footprint check failed: tool/resource definitions use about 1529 tokens (~254/item across 6 items; 6 tools + 0 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 0/100
  - Stability not yet verified: not enough scan history yet (needs a 30-day window).
- **Tool Coverage**: 71/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 0% of tool parameters carry a description.
  - Structured output schemas are declared (100% of tools); any adoption earns full credit.
- **Tool Safety**: 100/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - We read all 6 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 7 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 100/100
  - Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.

**Unverified: 1 category.** A category scored 0 because we could not verify it: authentication we do not have, an unreachable endpoint, or not enough scan history. We only credit what we can confirm.

## Install

### How do I install the datagokr — 한국 공공데이터 검색 (Korean public data search) MCP server?

datagokr — 한국 공공데이터 검색 (Korean public data search) is a hosted endpoint at https://datagokr.dev/mcp, so there is nothing to install locally. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

### Claude

```bash
claude mcp add --transport http dev-datagokr-datagokr 'https://datagokr.dev/mcp'
```

### Cursor

```json
{
  "mcpServers": {
    "dev-datagokr-datagokr": {
      "url": "https://datagokr.dev/mcp"
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "dev-datagokr-datagokr": {
      "type": "http",
      "url": "https://datagokr.dev/mcp"
    }
  }
}
```

### Codex

```toml
[mcp_servers.dev-datagokr-datagokr]
url = "https://datagokr.dev/mcp"
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "dev-datagokr-datagokr": {
      "type": "remote",
      "url": "https://datagokr.dev/mcp",
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add dev-datagokr-datagokr --url 'https://datagokr.dev/mcp' --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  dev-datagokr-datagokr:
    url: "https://datagokr.dev/mcp"
```

### Netclaw

```json
{
  "McpServers": {
    "dev-datagokr-datagokr": {
      "Transport": "http",
      "Url": "https://datagokr.dev/mcp"
    }
  }
}
```

### Vellum

```bash
assistant mcp add dev-datagokr-datagokr -t streamable-http -u 'https://datagokr.dev/mcp'
```

### Other

```json
{
  "mcpServers": {
    "dev-datagokr-datagokr": {
      "type": "http",
      "url": "https://datagokr.dev/mcp"
    }
  }
}
```

The mcpServers block is a cross-client convention. Remote transports vary, so check your client's docs.

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-09-28 (score 70)

First indexed and scored.

## MCP tools (6)

### `search` (~368 tokens)

공공데이터 검색 (Search datasets)

주제로 공공데이터를 찾습니다. "전국 주차장", "재난문자 API", "서울 병원 위치"처럼 뭘 찾는지 한 줄로 주세요.
Search Korean public datasets by topic. Give a one-line description of what you need.

\- 주제+컬럼 조건('서울 병원 중 위도·경도 있는 것')은 이 툴에 `fields=['위도','경도']`를 같이 주세요.
  주제 없이 컬럼만 조건이면 `fields` 툴. / Topic + required columns: pass `fields=[...]` here.
  Columns only, no topic: use the `fields` tool.
\- 지역과 API/파일 의도는 질문에서 알아서 뽑지만, dtype(API/FILE)·org(기관)를 주면 더 정확합니다.
\- 비슷한 데이터셋은 주제별로 접어서 줍니다(group=True). 접힌 것은 group_ids의 id를 show로 펼치세요. n은 최대 20.

반환: results[{id, title, org_nm, dtype, access_kind, page_url, desc_short, top_columns, group_count, group_ids,
access_note(접근방식 한 줄 안내)}],
summary(잘라내기 전 후보 분포), expanded_terms(적용된 동의어), region_gap/region_fallback(지역 자료가 없을 때
전국·타지역 안내), scope_warning(범위 밖 질문 안내). 다음 단계: 마음에 드는 id를 show로 확인.

Input parameters:

- `dtype`
- `fields`
- `group` (boolean)
- `n` (integer)
- `org`
- `query` (string, required)

### `show` (~187 tokens)

데이터셋 상세 (Dataset details)

검색에서 고른 데이터셋의 구조와 접근 방법을 봅니다. Inspect a dataset's schema and access methods.
반환: id, title, org_nm, category, dtype, access_kind, page_url, portal_updated, columns(최대 50),
operations, operation_names, examples, n_versions, version_keys(최신 3개), note,
truncated(잘린 항목과 전체 개수), more(후속 조회법). 응답은 약 20KB 이내로 잘림.
operations가 많은 API는 show(id, operation='기능명 또는 operation_seq')로 한 기능만 전체 보기.
Responses are trimmed to about 20KB; select an operation by name or sequence for its full fields.
쓸 만하면 get_preview로 실제 첫 행을 확인하세요.

Input parameters:

- `dataset_id` (string, required)
- `operation`

### `record` (~133 tokens)

원본 메타데이터 (Raw metadata)

(로컬 datagokr 패키지 전용) 조회·신청·다운로드에 필요한 원본 메타데이터를 돌려줍니다. 일반 사용에서는 show를 쓰세요.
Allowlisted raw metadata for the local datagokr client; prefer `show` for normal use.
반환: id/title/list_title/org_nm, dtype/access_kind, page_url/external_url, parent_id, versions/version_keys,
examples(요청 템플릿), std_meta, api_sample. 내부 상태는 제외하고, 서버에서 신청하거나 저장하지 않습니다.

Input parameters:

- `dataset_id` (string, required)

### `fields` (~164 tokens)

컬럼으로 찾기 (Find by columns)

주제 없이 컬럼만 조건일 때(query는 빈 문자열로 고정됨). 주제가 있으면 search(query, fields=...)를 쓰세요.
Find datasets with ALL given columns and no topic; for a topic use search(query, fields=...).
names에 적은 컬럼을 전부 가진 데이터셋만 나옵니다(필드명 역색인). dtype/org로 좁힐 수 있고 n은 최대 20.
반환: id, title, org_nm, dtype, access_kind, page_url, rank, matched_fields(일치한 컬럼), last_probe_ok.

Input parameters:

- `dtype`
- `group` (boolean)
- `n` (integer)
- `names` (array, required)
- `org`

### `get_preview` (~252 tokens)

첫 행 미리보기 (Preview rows)

실제 첫 행 보기. STD_FILE·PORTAL_FILE(첨부 있으면)은 키 없이 첫 행을 줍니다.
PORTAL_FILE 첨부 미리보기가 불가한 파일만 X-DataGoKr-Key 헤더 필요(키는 절대 반환·저장 안 함).
OPEN_API→request_templates, LINK→url, STD 하위행→parent_id.
Preview standard data and portal attachments without a key; only unavailable attachments need
X-DataGoKr-Key. Keys are never returned or stored. API/link/subset responses give access guidance.
반환: ok(true=처리됨, false=포털이 지금 응답 안 함→잠시 후 재시도),
data{columns, rows}(rows는 columns 순서의 값 배열, 최대 50컬럼·20행), total, truncated, source_note,
또는 안내 필드(url/parent_id/request_templates/message/page_url). data가 있으면 실제 행을 받은 것.
ok=false: retry later. data means actual rows, as value arrays in columns order (up to 50 columns/20 rows).

Input parameters:

- `dataset_id` (string, required)
- `n` (integer)

### `download_url` (~125 tokens)

다운로드 방법 (How to download)

전체 데이터를 사용자 컴퓨터로 받는 방법을 알려줍니다. 서버가 파일을 대신 저장하진 않고 주소·요청값·절차를 돌려줍니다.
Get client-side download instructions (URL, params, steps). The server never stores files.
반환: access_kind, url 또는 post_url/get_url, params, version_keys(파일 버전), message(절차), page_url.
예: '15028200 전체 JSON 받는 법', '15000001 원본 파일 다운로드 주소'

Input parameters:

- `dataset_id` (string, required)

## Diagnostics

Captured diagnostic sections: TLS, DNSSEC, Authorisation, Transports. The full working is on the page: https://verifymcp.io/servers/dev-datagokr-datagokr/datagokr#diagnostics

## Score history

- 2026-09-28: 70

## Common questions

### What is the datagokr — 한국 공공데이터 검색 (Korean public data search) MCP server?

datagokr — 한국 공공데이터 검색 (Korean public data search) is an MCP server listed in the public MCP registry as dev.datagokr/datagokr. Search Korea's public data portal (data.go.kr): find datasets, schema, preview rows, download steps. This page covers its hosted endpoint (https://datagokr.dev/mcp).

### Is the datagokr — 한국 공공데이터 검색 (Korean public data search) MCP server safe to use?

datagokr — 한국 공공데이터 검색 (Korean public data search) scores 70 out of 100 on VerifyMCP. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

### What tools does the datagokr — 한국 공공데이터 검색 (Korean public data search) MCP server expose?

datagokr — 한국 공공데이터 검색 (Korean public data search) exposes 6 tools: search, show, record, fields, get_preview, download_url. Their descriptions and schemas cost roughly 1,229 tokens of context every time the server is loaded.

### Does the datagokr — 한국 공공데이터 검색 (Korean public data search) MCP server require authentication?

No. We connected to datagokr — 한국 공공데이터 검색 (Korean public data search) without credentials and it answered, so anything it exposes is reachable by anyone who knows the address.

### Is the datagokr — 한국 공공데이터 검색 (Korean public data search) MCP server still maintained?

datagokr — 한국 공공데이터 검색 (Korean public data search) is still listed as active in the MCP registry. We last reached this channel on 28 September 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

## Links

- Remote endpoint: https://datagokr.dev/mcp
- Repository: https://github.com/datagokr-dev/datagokr
- Website: https://datagokr.dev/
- Changelog RSS feed: https://verifymcp.io/servers/dev-datagokr-datagokr/datagokr.xml
- Changelog JSON feed: https://verifymcp.io/servers/dev-datagokr-datagokr/datagokr.json
- HTML version of this page: https://verifymcp.io/servers/dev-datagokr-datagokr/datagokr