
Kadlint
io.github.feelydayPublished by GitHub account feelydayv0.1.1Updated Oct 24, 2026
Korean ad-compliance linter for cosmetics and health-food marketing copy
Overview
A local MCP server that lints Korean cosmetics and health-food marketing copy for prohibited advertising claims, citing legal basis and safer alternatives.
- What you can do
- Check ad copy: the check_ad_copy tool lints Korean marketing text, optionally scoped to cosmetics, health-food or common rules, and returns findings with violation category, legal basis, severity and suggested alternative phrasings.
- When to use it
- Useful when drafting or reviewing Korean-language advertising for cosmetics or health-functional foods and you want a quick check for drug-like or unsubstantiated claims before publishing.
- Requirements
- Runs as a local process via npx from the npm package kadlint; requires Node.js 18 or later. No accounts, API keys or environment variables are declared.
Installation
In SourceWeft
- Open Kadlint in the dashboard and add it to a workspace.
- Enable the server for the chats that should use its tools.
Desktop only via STDIO. STDIO servers start a local process, so they need the SourceWeft desktop host.
Other MCP clients
Follow the launch instructions in the repository.
README
kadlint
Korean ad-compliance linter for cosmetics and health-food marketing copy — detects prohibited claims with the legal basis, severity, and safer alternatives.
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
Requires Node.js >= 18.
CLI
- Supported inputs:
.txt,.md,.html(tags stripped, offsets preserved), directories (recursive),-(stdin). - Exit codes:
0clean,1findings at/above--min-severity,2usage 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
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):
If installed globally, "command": "kadlint-mcp" suffices:
Claude Code:
or in .mcp.json:
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:
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
Source: README.md at commit 9a207ba
Tools
0Version history
1- v0.1.1LatestSep 16, 2026
Score
50% of the applicable checks met
How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.
- Reached in the last 30 days25 pts
Keep the endpoint answering the MCP handshake; SourceWeft probes it every 30 days.
- Auth declared10 pts
Declare the credential headers in the registry entry, or keep the endpoint answering the probe so its auth can be classified.
- Tools listed15 pts
Answer tools/list without a credential, or ship a package that starts in a sandbox without one.
- DescriptionRequired15 pts
- Logo10 pts
- Documentation15 pts
- License10 pts