Kadlint

io.github.feelyday由 GitHub 帳號 feelyday 發布v0.1.1更新於 Oct 24, 2026

Korean ad-compliance linter for cosmetics and health-food marketing copy

已驗證STDIO僅桌面開發者工具商業與電商

概覽

AI 產生的概覽

本機 MCP 伺服器,用來檢查韓文化妝品與健康機能食品行銷文案中的違規廣告用語,並提供法律依據與較安全的替代說法。

可以做什麼
檢查廣告文案:check_ad_copy 工具會檢測韓文行銷文字,可限定為化妝品、健康食品或通用規則,並回傳違規類別、法律依據、嚴重程度與建議替代說法。
適用情境
適合在撰寫或審閱韓文化妝品、健康機能食品廣告時,於發布前快速排查涉藥或缺乏依據的宣稱。
執行需求
透過 npm 套件 kadlint 以 npx 作為本機程序執行,需要 Node.js 18 或更新版本。未宣告帳號、API 金鑰或環境變數。
安裝前請注意
它是基於人工整理規則詞典的啟發式檢查工具,並非法律意見;檢查通過不保證合規,法規也可能變動。廣告的最終法律責任由廣告主承擔,高風險文案請諮詢專業人士。

安裝

在 SourceWeft 中

  1. 開啟 儀表板中的 Kadlint,將其新增到工作區。
  2. 為需要使用其工具的對話啟用該服務。

Desktop only,透過 STDIO。 STDIO 服務會啟動本機處理程序,因此需要 SourceWeft 桌面主機。

其他 MCP 客戶端

參照 儲存庫 中的啟動說明。

README

kadlint

Korean ad-compliance linter for cosmetics and health-food marketing copy — detects prohibited claims with the legal basis, severity, and safer alternatives.

[npm version] [CI] [license]

한국어 README

Korean law tightly regulates what cosmetics and health-functional-food ads may claim. A face cream may not say it "treats acne" (that is a drug claim under the Cosmetics Act), a probiotic may not promise to "boost immunity" unless that exact functionality was approved, and "No.1" / "100% natural" claims require objective substantiation under the Fair Labeling and Advertising Act. Korea's Ministry of Food and Drug Safety (MFDS) keeps detecting thousands of unlawful online ads in these categories every year — in 2025 its routine sweeps again flagged large batches of cosmetics and health-food ads for drug-like or unsubstantiated claims, and violations can mean ad bans, sales suspensions, and fines.

kadlint lints Korean marketing copy against a curated dictionary of 299 rules (183 cosmetics, 51 health-food, 65 common) distilled from:

  • 화장품법 (Cosmetics Act) and its enforcement rules (별표5)
  • 건강기능식품법 / 식품표시광고법 (Health Functional Foods & Food Labeling/Advertising Acts)
  • 표시광고법 (Fair Labeling and Advertising Act)
  • MFDS advertising guidelines and enforcement precedents

Every finding comes with the violation category, the legal basis citation, a severity (high / medium / low), an explanation, and safer alternative phrasings.

Install

sh
npm install -g kadlint     # CLInpm install kadlint        # library

Requires Node.js >= 18.

CLI

sh
kadlint check ad-copy.txtkadlint check ./landing-pages --format json --min-severity highkadlint check - < draft.md                 # stdinkadlint check banner.html --domain cosmetics,common
ad-copy.txt:1:1 [HIGH] '여드름 치료' — 의약품 오인 표현 (cos-113)    근거: 화장품법 제13조제1항제1호, 식약처 「화장품 표시·광고 관리 지침」    대체 표현: 피지·각질 케어로 매끈한 피부결 / (실증 보유 시) 여드름성 피부에 사용 적합
✖ 1건 발견 (high 1 · medium 0 · low 0) — 파일 1개, 규칙 299개 검사
  • Supported inputs: .txt, .md, .html (tags stripped, offsets preserved), directories (recursive), - (stdin).
  • Exit codes: 0 clean, 1 findings at/above --min-severity, 2 usage error.
  • Literal rules match through inserted spaces, middle dots, and hyphens (살 균, 살·균, 살-균), a common evasion tactic; disable with --no-normalize.

API

ts
import { lint, lintFile } from 'kadlint';
const result = lint('여드름 치료에 탁월한 크림', { domains: ['cosmetics'] });for (const f of result.findings) {  console.log(f.ruleId, f.severity, f.match, f.legalBasis, f.alternatives);}
const fileResult = lintFile('landing.html', { minSeverity: 'medium' });

Options: domains (cosmetics | health_food | common), minSeverity, normalize (default true).

When one of a rule's exceptions phrases appears within 80 characters of a match (e.g. an approved functional claim used verbatim), the finding is downgraded to low with an explanatory note.

MCP server

kadlint-mcp exposes a check_ad_copy { text, domain? } tool over stdio so LLM assistants can lint copy while drafting it.

Claude Desktop (claude_desktop_config.json):

json
{  "mcpServers": {    "kadlint": {      "command": "npx",      "args": ["-y", "kadlint", "kadlint-mcp"]    }  }}

If installed globally, "command": "kadlint-mcp" suffices:

json
{  "mcpServers": {    "kadlint": { "command": "kadlint-mcp" }  }}

Claude Code:

sh
claude mcp add kadlint -- kadlint-mcp

or in .mcp.json:

json
{  "mcpServers": {    "kadlint": {      "command": "kadlint-mcp",      "args": []    }  }}

Playground

playground/index.html is a dependency-free static page (GitHub Pages friendly): paste copy, get highlighted matches and rule cards with the legal basis and alternatives.

Rule dictionary

Rules live in data/*.json:

json
{  "id": "cos-113",  "pattern": "여드름.{0,8}(개선|치료|완화|박멸|없애|케어|예방)",  "pattern_type": "regex",  "violation": "의약품 오인 표현",  "legal_basis": "화장품법 제13조제1항제1호",  "severity": "high",  "message": "…why this is prohibited…",  "alternatives": ["피지·각질 케어로 매끈한 피부결"],  "exceptions": ["여드름성 피부 완화 기능성화장품 심사(보고) 효능효과"]}

data/_needs_review.json is a backlog of candidate rules that have not been verified yet; it is excluded from the npm package. Contributions welcome — see CONTRIBUTING.md (no coding required, every rule must cite its legal basis).

Disclaimer

  • kadlint is not legal advice. It is a heuristic linter over a hand-curated dictionary.
  • A clean result does not guarantee compliance — false negatives are inherent to pattern matching, and regulations change.
  • Final legal responsibility for any advertisement rests with the advertiser. Consult a qualified professional for high-stakes copy.

Roadmap

  • v0.2: PyPI mirror (pip install kadlint), review of the 25 backlog rules in _needs_review.json, and a pipeline for tracking MFDS guideline revisions.

License

MIT © 2026 Jungkyun Lim

來源:README.md,提交 9a207ba

工具

0
SourceWeft 尚未在沙箱中啟動過該軟體包,因此其工具未知。

版本歷史

1
  1. v0.1.1最新Sep 16, 2026

評分

已滿足適用檢查項的 50%

該評分衡量此收錄條目的完整程度,依據註冊中心條目、端點與公開來源計算得出。它不是對伺服器本身的評價,也不表示伺服器安全或目前可用:可連通性是帶日期的檢查結果,評分也不包含安裝量或使用者評價。

  • 近 30 天內可連通25 分

    請保持端點能夠回應 MCP 握手;SourceWeft 每 30 天探測一次。

  • 已宣告認證方式10 分

    請在註冊中心條目中宣告憑證請求標頭,或保持端點能夠回應探測,以便判定其認證方式。

  • 已列出工具15 分

    請讓伺服器在無憑證時回應 tools/list,或發布可在沙箱中無憑證啟動的軟體包。

  • 描述必需15 分
  • 圖示10 分
  • 文件15 分
  • 授權條款10 分