MCP server/ai-tools

Glin Profanity MCP Server

ML-Powered Profanity Detection for the Modern Web

★ 45glincker/glin-profanity ↗by thegdsksupdated
1

Add it to Claude Code

claude mcp add glin-profanity -- npx -y glin-profanity-mcp
2

Make your agent remember this setup

glin-profanity's config, env vars, and the gotchas you hit — recalled in every future Claude Code, Cursor, and Codex session.

npx conare@latest

Free · one command · indexes the sessions already on disk. Set up in the browser instead →

What it does

  • ML-powered profanity detection
  • Detection of leetspeak and Unicode obfuscation tactics
  • Support for 24 languages
  • Context-aware content analysis
  • Batch processing capabilities for multiple inputs

Tools 2

check_textAnalyzes input text for profanity and offensive content using ML-powered detection.
batch_checkProcesses multiple text inputs for profanity detection in a single request.

Try it

Check this user comment for any offensive language or profanity: 'You are a fսck1ng idiot'.
Analyze the following list of messages for profanity and flag any that contain obfuscated offensive terms.
Does this text contain any profanity, considering potential leetspeak or Unicode evasion tactics?
Scan these forum posts for inappropriate content using the Glin Profanity tool.
Original README from glincker/glin-profanity
<h1 align="center">GLIN PROFANITY</h1>

<strong>ML-Powered Profanity Detection for the Modern Web</strong>

<a href="https://www.glincker.com/tools/glin-profanity" target="_blank"> </a>

📦 Packages

This monorepo maintains the following packages:

Package Version Description
glin-profanity Core profanity filter for JavaScript/TypeScript
glin-profanity Core profanity filter for Python
glin-profanity-mcp MCP server for AI assistants (Claude, Cursor, etc.)
openclaw-profanity Plugin for OpenClaw/Moltbot AI agents

Why Glin Profanity?

Most profanity filters are trivially bypassed. Users type f*ck, sh1t, or fսck (with Cyrillic characters) and walk right through. Glin Profanity doesn't just check against a word list—it understands evasion tactics.

┌─────────────────────────────────────────────────────────────────────────────┐
│                           GLIN PROFANITY v3                                 │
├─────────────────────────────────────────────────────────────────────────────┤
│                                                                             │
│   Input Text ──►  Unicode       ──►  Leetspeak    ──►  Dictionary  ──► ML  │
│

Frequently Asked Questions

What are the key features of Glin Profanity?

ML-powered profanity detection. Detection of leetspeak and Unicode obfuscation tactics. Support for 24 languages. Context-aware content analysis. Batch processing capabilities for multiple inputs.

What can I use Glin Profanity for?

Moderating user-generated content in real-time within AI-assisted workflows. Filtering offensive language in chat applications or comment sections. Ensuring AI-generated responses remain safe and free of profanity. Detecting attempts to bypass filters using character substitution.

How do I install Glin Profanity?

Install Glin Profanity by running: npx -y glin-profanity-mcp

What MCP clients work with Glin Profanity?

Glin Profanity works with any MCP-compatible client including Claude Desktop, Claude Code, Cursor, and other editors with MCP support.

Conare · memory for coding agents

Turn this server into reusable context

Keep Glin Profanity docs, env vars, and workflow notes in Conare so your agent carries them across sessions.

Set up free$npx conare@latest