Analysiert Texte auf stilistische Probleme wie Passiv, Weasel Words und KI-typische Muster, um die Schreibqualität zu verbessern.
Auch bekannt als theserverlessdev/wsc, wsc, wsc-mcp
- Stars
- 9
- Tools
- 4
- Downloads, 30 Tage
- —
- Neueste Version
- 2.2.2
- Letzter Commit
- 11. Nov. 2026
- Lizenz
- MIT
Was ist Writing Style Checker MCP?
Writing Style Checker ist ein MCP server. Analysiert Texte auf stilistische Probleme wie Passiv, Weasel Words und KI-typische Muster, um die Schreibqualität zu verbessern. Er stellt 4 Tools bereit, etwa check_text, fix_duplicates, list_word_lists.
Zusammenfassung generiert aus dem README des Projekts
Über Writing Style Checker MCP server
Der Writing Style Checker fungiert als Prose Linter, der darauf ausgelegt ist, spezifische Schreibprobleme und Muster zu identifizieren, die häufig in KI-generierten Texten vorkommen. Er hilft Schreibenden, die Qualität zu steigern, indem er Passivkonstruktionen, Weasel Words, Fülladverbien, Hedging, Nominalisierungen und zu lange Sätze markiert. Zudem enthält er einen spezialisierten Detektor für KI-Merkmale, der spezifische Wörter und strukturelle Muster erkennt, die in maschinell erzeugten Inhalten überrepräsentiert sind.
Entwickler können diesen Service über einen Remote MCP server via Streamable HTTP transport integrieren oder den lokalen stdio-basierten Server über das wsc-mcp npm package installieren. Die lokale Version bietet ein zusätzliches check_file Tool, um Dateien direkt von deiner Festplatte zu analysieren. Nutzer können die Erkennungsregeln über eine .wscrc.json Konfigurationsdatei anpassen, um spezifische Wortlisten und Schwellenwerte zu aktivieren, zu deaktivieren oder zu modifizieren.
Was du damit machen kannst
- 1KI-typische Schreibmuster erkennenLass den Assistenten spezifische Wörter oder Satzstrukturen identifizieren, die darauf hindeuten, dass ein Text von einer KI geschrieben wurde.
- 2Doppelte Wörter bereinigenWeise den Client an, direkt aufeinanderfolgende Wortwiederholungen in einem Textblock zu entfernen.
- 3Lokale Markdown-Dateien prüfenLass die KI eine bestimmte Datei auf deinem Computer lesen und auf stilistische Mängel analysieren.
- 4Allgemeine Textqualität prüfenReiche einen Absatz ein, um ihn auf Passiv, Weasel Words und Fülladverbien zu überprüfen.
Geschrieben aus dem README des Projekts. Jeder Use Case wurde gegen ein Zitat daraus geprüft.
So installierst du Writing Style Checker MCP
Formate geprüft am 10. Nov. 2026Zu Cursor hinzufügenZu Goose hinzufügenWriting Style Checker MCP in Claude Code installieren
$ claude mcp add wsc -- npx -y wsc-mcpWriting Style Checker MCP in Cursor installieren
~/.cursor/mcp.json
{
"mcpServers": {
"wsc": {
"command": "npx",
"args": [
"-y",
"wsc-mcp"
]
}
}
}Writing Style Checker MCP in VS Code installieren
.vscode/mcp.json
{
"servers": {
"wsc": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"wsc-mcp"
]
}
}
}Writing Style Checker MCP in VS Code CLI installieren
$ code --add-mcp '{"name":"wsc","type":"stdio","command":"npx","args":["-y","wsc-mcp"]}'Writing Style Checker MCP in Claude Desktop installieren
claude_desktop_config.json
{
"mcpServers": {
"wsc": {
"command": "npx",
"args": [
"-y",
"wsc-mcp"
]
}
}
}Writing Style Checker MCP in Codex installieren
$ codex mcp add wsc -- npx -y wsc-mcpWriting Style Checker MCP in Codex config.toml installieren
~/.codex/config.toml
[mcp_servers.wsc] command = "npx" args = ["-y", "wsc-mcp"]
Writing Style Checker MCP in Gemini CLI installieren
$ gemini mcp add -s user wsc npx -- -y wsc-mcpWriting Style Checker MCP in Gemini settings.json installieren
~/.gemini/settings.json
{
"mcpServers": {
"wsc": {
"command": "npx",
"args": [
"-y",
"wsc-mcp"
]
}
}
}Writing Style Checker MCP tools 4
Erkannt aus dem READMEcheck_textfix_duplicateslist_word_listscheck_file
| check_text | — | |
| fix_duplicates | — | |
| list_word_lists | — | |
| check_file | — |
Automatisierte Checks
Geluften am 12. Nov. 2026Vollständiger Bericht →Unsere automatisierten Checks bestanden. Das ist kein Security-Audit: Lies den Code und gib dem Server nur den minimal notwendigen Zugriff. Wie die Checks funktionieren
- Source Repository verknüpft und erreichbarBestanden
- Open Source Lizenz (OSI)Bestanden
- Commit oder Release im letzten JahrBestanden
- Package-Name ähnelt keinem populären PackageBestanden
- Remote Endpoint nutzt HTTPSBestanden
- Destruktive Tools sind markiertBestanden
- Keine versteckten Anweisungen an das ModellBestanden
- Keine kritischen Advisories im Paket oder seinen AbhängigkeitenBestanden
README
Auf GitHub ansehenWriting Style Checker
A prose linter and AI-slop detector. WSC finds AI tells — words, phrases, and sentence structures overrepresented in AI-generated text, each flag backed by a published corpus study. It also catches classic writing issues: weasel words, passive voice, duplicate words, long sentences, nominalizations, hedging, and filler adverbs. Available as a web editor, HTTP API, MCP server, CLI, and GitHub Action.

Features
- Web Editor - Real-time highlighting with inline fix buttons for all 8 detectors
- HTTP API - POST text with optional config, retrieve structured JSON responses
- MCP Server (Remote) - Connect AI assistants via Streamable HTTP transport
- MCP Server (Local) - Stdio-based server via
wsc-mcpon npm - CLI - Check files from the command line via
wsc-lint - GitHub Action - Run checks in CI with
::warningannotations - Configurable - Customize detectors with
.wscrc.jsonfiles
What WSC is (and isn't)
WSC flags patterns that research on AI-generated text finds overrepresented, and cites a source for every flag. It does not, and cannot, prove authorship. Classifier-based detectors carry a documented false-accusation risk: a Stanford study found that seven of them misflagged 61% of essays written by non-native English speakers. WSC avoids that trap by design — every flag is a specific, explainable edit that improves the text no matter who, or what, wrote it.
Detection Rules
| Detector | Items | Description |
|---|---|---|
| Weasel Words | 95 words/phrases | Vague terms like "very", "basically", "arguably", "numerous" |
| Passive Voice | 260 irregular verbs | Auxiliary verbs + past participles (regular -ed + irregular) |
| Duplicate Words | — | Adjacent repeated words across whitespace, case-insensitive |
| Long Sentences | threshold: 30 words | Sentences exceeding a configurable word count |
| Nominalizations | 245 word pairs | Nouns replaceable with verbs ("utilization" → "use") |
| Hedging | 100 phrases | Phrases that weaken assertions ("I think", "it seems") |
| Filler Adverbs | 139 words | Adverbs adding emphasis without substance ("totally", "utterly") |
| AI Tells | 98 words (+111 inflected forms) + 83 phrases + 12 structural patterns | Words, phrases, and sentence constructions overrepresented in AI-generated text (delve, rich tapestry, It's not just X — it's Y) |
Word lists sourced from Matt Might's shell scripts and expanded with additional entries. AI tells draw on published corpus studies: Kobak et al. 2025 (Science Advances), Juzek & Ward 2025 (COLING), Liang et al. 2024 (Stanford), and Reinhart et al. 2025 (PNAS). Wikipedia's editor-maintained Signs of AI writing catalogue and AI-detection vendor reports round out the sources.
Configuration
Create a .wscrc.json to customize detectors. All tools (API, MCP, CLI) support it.
{
"$schema": "https://wsc.theserverless.dev/schema.json",
"ignore": ["CHANGELOG.md", "docs/vendor/**"],
"detectors": {
"weaselWords": {
"enabled": true,
"add": ["synergy", "leverage"],
"remove": ["very"]
},
"longSentences": { "maxWords": 25 },
"adverbs": { "enabled": false }
}
}
Every field is optional. Missing fields use defaults. JSON Schema provides autocompletion in VS Code.
ignore is an array of glob patterns relative to the working directory. The GitHub Action uses the repository root. The CLI adds these patterns to its built-in **/node_modules/** and **/.git/** skips, together with the Action exclude input and the CLI --ignore flag.
API Usage
POST /api/check
Analyze text for writing style issues. Accepts optional config object.
curl -X POST https://wsc.theserverless.dev/api/check \
-H "Content-Type: application/json" \
-d '{"text":"The code was written very quickly."}'
Response:
{
"summary": {
"total": 2,
"weaselWords": 1,
"passiveVoice": 1,
"duplicateWords": 0,
"longSentences": 0,
"nominalizations": 0,
"hedging": 0,
"adverbs": 0
},
"issues": {
"weaselWords": [{ "word": "very", "index": 21, "line": 1, "column": 22, "context": "..." }],
"passiveVoice": [{ "phrase": "was written", "index": 9, "line": 1, "column": 10, "context": "..." }],
"duplicateWords": [],
"longSentences": [],
"nominalizations": [],
"hedging": [],
"adverbs": []
},
"meta": { "characterCount": 34, "wordCount": 6, "sentenceCount": 1, "processingTimeMs": 2 }
}
With config:
curl -X POST https://wsc.theserverless.dev/api/check \
-H "Content-Type: application/json" \
-d '{"text":"The code was written very quickly.", "config":{"detectors":{"weaselWords":{"enabled":false}}}}'
GET /api/check
Returns API documentation as JSON.
GET /api/detectors
Returns the list of all 8 detectors with descriptions, configurability, and word counts.
GET /health
Runs a smoke test with known text and returns {"status":"healthy"} or 503.
Limits: Max 100,000 characters per request. CORS enabled for all origins.
MCP Server
The Writing Style Checker is available as an MCP server, letting AI assistants check your writing directly.
Tools
| Tool | Description |
|---|---|
check_text |
Analyze text for all 8 writing style issues. Accepts optional config. |
fix_duplicates |
Remove duplicate adjacent words and return cleaned text |
list_word_lists |
Return info about all detector word lists |
check_file |
(Local only) Read a file from disk and analyze it. Auto-discovers .wscrc.json. |
Remote MCP Server
Connect any MCP client to the hosted server - no installation required.
{
"mcpServers": {
"writing-style-checker": {
"type": "url",
"url": "https://wsc.theserverless.dev/mcp"
}
}
}
Local MCP Server (stdio)
Install via npm for local usage. Includes check_file for analyzing files on disk with auto-discovery of .wscrc.json.
npx wsc-mcp
Claude Desktop / Claude Code config:
{
"mcpServers": {
"writing-style-checker": {
"command": "npx",
"args": ["wsc-mcp"]
}
}
}
See the wsc-mcp npm page for full documentation.
CLI
Check files from the command line.
# Check all markdown files
npx wsc-lint check "**/*.md"
# Read from stdin
echo "The code was written very quickly." | npx wsc-lint check --stdin
# JSON output for scripting
npx wsc-lint check "**/*.md" --format json
# GitHub Actions annotations
npx wsc-lint check "**/*.md" --format github
# Create a config file
npx wsc-lint init
See the wsc-lint README for full documentation.
GitHub Action
- uses: theserverlessdev/wsc@v1
with:
files: '**/*.md'
max-warnings: 20
exclude: |
CHANGELOG.md
vendor/**
| Input | Default | Description |
|---|---|---|
files |
**/*.md |
Glob pattern for files to check |
config |
— | Path to .wscrc.json config file |
max-warnings |
unlimited | Max warnings before failing |
only-changed |
false |
On a pull request, check changed files that match files. If none match, skip the check. Other events check files. |
exclude |
— | Glob patterns to skip. Separate with a comma or a new line. Adds to config ignore. |
Privacy
The web editor runs in your browser - we never send text to any server. The API and MCP endpoints only process text you explicitly send to them.
Project Structure
.
├── src/
│ ├── core/ # Shared detection engine
│ │ ├── detector.ts # 8 detection algorithms
│ │ ├── words.ts # Word/phrase lists (800+ entries)
│ │ ├── config.ts # Config types, merging, validation
│ │ ├── config-node.ts # Node-only: file loading, discovery
│ │ ├── analyzer.ts # Unified analyzeText() entry point
│ │ └── index.ts # Public API exports
│ ├── docs/ # Documentation content (Markdown files)
│ ├── mcp/
│ │ └── handler.ts # MCP JSON-RPC 2.0 handler
│ ├── lib/
│ │ ├── App.svelte # Main editor page component
│ │ ├── stores/theme.ts # Theme store (light/dark/system)
│ │ └── components/ # UI components (StatsBar, ConfigPanel, etc.)
│ ├── routes/
│ │ ├── +layout.svelte # Shared layout (header, nav, footer)
│ │ ├── api/check/+server.ts # HTTP API endpoint
│ │ ├── mcp/+server.ts # MCP endpoint
│ │ ├── health/+server.ts # Health check endpoint
│ │ ├── docs/+page.svelte # Documentation page
│ │ └── words/+page.svelte # Word library browser
│ └── styles/
│ └── main.scss # Global styles (light + dark themes)
├── mcp-server/ # Standalone stdio MCP server (npm: wsc-mcp)
├── cli/ # CLI tool (npm: wsc-lint)
├── action/ # GitHub Action (composite)
├── tests/ # 341 tests across 18 files
├── static/
│ ├── schema.json # JSON Schema for .wscrc.json
│ ├── llms.txt # AI/LLM discovery file
│ └── llms-full.txt # Detailed LLM context
├── wrangler.toml # Cloudflare Workers config
└── svelte.config.js # SvelteKit configuration
Local Development
git clone https://github.com/theserverlessdev/wsc.git
cd wsc
npm install
npm run dev
Visit http://localhost:5173. The API is at /api/check, MCP at /mcp, health at /health.
Commands
| Command | Description |
|---|---|
npm run dev |
Start dev server |
npm run build |
Build for production |
npm run check |
Type check with svelte-check |
npm test |
Run all 341 tests |
npm run test:coverage |
Coverage report |
Deployment
Deployed as a Cloudflare Worker at wsc.theserverless.dev.
npm run build
npx wrangler deploy
Contributing
See CONTRIBUTING.md for development setup, testing, and pull request guidelines.
For substantial changes, please open an issue first.
Acknowledgements
- Matt Might for the original shell scripts
- Built with SvelteKit and Svelte 5, deployed on Cloudflare Workers
- Logo made with DiffusionBee
License
Writing Style Checker MCP Fragen
Wie füge ich Writing Style Checker MCP zu Claude Code hinzu?
Führe claude mcp add wsc -- npx -y wsc-mcp in deinem Terminal aus. Füge --scope user hinzu, damit der Server in jedem Projekt verfügbar ist.
Wie füge ich Writing Style Checker MCP zu Cursor hinzu?
Öffne ~/.cursor/mcp.json und füge den Server unter mcpServers hinzu, mit der Cursor-Config aus dem Installationsabschnitt oben.
Welche Tools bietet Writing Style Checker MCP?
Er stellt 4 Tools bereit, darunter check_text, fix_duplicates, list_word_lists, check_file.
Kann dieses Tool beweisen, ob ein Text von einer KI geschrieben wurde?
Nein, es liefert keinen Beweis für die Urheberschaft. Stattdessen markiert es spezifische Muster und Wörter, die in KI-generierten Texten überrepräsentiert sind, um nachvollziehbare Korrekturen zu ermöglichen.
Kann ich die Erkennungsregeln anpassen?
Ja, du kannst die Detektoren mithilfe einer .wscrc.json Konfigurationsdatei anpassen.
Ist mein Text privat, wenn ich den Web-Editor nutze?
Ja, der Web-Editor läuft vollständig in deinem Browser, sodass Texte niemals an einen Server gesendet werden.