Glin Profanity MCP Server
MCP (Model Context Protocol) server that provides profanity detection as tools for AI assistants like Claude Desktop, Cursor, and Windsurf.
Best for: AI-assisted content review workflows, batch moderation, audit reports, and content validation before publishing.
Installation
Claude Desktop
Add to ~/Library/Application Support/Claude/claude_desktop_config.json:
CODEBLOCK0
Cursor
Add to .cursor/mcp.json:
CODEBLOCK1
Available Tools
Core Detection
| Tool | Description |
|---|
| INLINECODE2 | Check text for profanity with detailed results |
| INLINECODE3 |
Censor profanity with configurable replacement |
|
batch_check | Check multiple texts at once (up to 100) |
|
validate_content | Get safety score (0-100) with action recommendation |
Analysis
| Tool | Description |
|---|
| INLINECODE6 | Context-aware analysis (medical, gaming, etc.) |
| INLINECODE7 |
Detect leetspeak and Unicode tricks |
|
explain_match | Explain why text was flagged |
|
compare_strictness | Compare detection across strictness levels |
Utilities
| Tool | Description |
|---|
| INLINECODE10 | Suggest clean replacements |
| INLINECODE11 |
Analyze up to 500 texts for stats |
|
create_regex_pattern | Generate regex for custom detection |
|
get_supported_languages | List all 24 supported languages |
User Tracking
| Tool | Description |
|---|
| INLINECODE14 | Track messages for repeat offenders |
| INLINECODE15 |
Get user's moderation history |
|
get_high_risk_users | List users with high violation rates |
Example Prompts
Content Review
CODEBLOCK2
Batch Operations
CODEBLOCK3
Understanding Flags
CODEBLOCK4
Content Cleanup
CODEBLOCK5
When to Use
Use MCP server when:
- - AI assists with content review workflows
- Batch checking user submissions
- Generating moderation reports
- Content validation before publishing
- Human-in-the-loop moderation
Use core library instead when:
- - Automated real-time filtering (hooks/middleware)
- Every message needs checking without AI involvement
- Performance-critical applications (< 1ms response)
Resources
- - npm: https://www.npmjs.com/package/glin-profanity-mcp
- GitHub: https://github.com/GLINCKER/glin-profanity/tree/release/packages/mcp
- Core library: https://www.npmjs.com/package/glin-profanity
Glin Profanity MCP 服务器
MCP(模型上下文协议)服务器,为Claude Desktop、Cursor和Windsurf等AI助手提供脏话检测工具。
最佳用途: AI辅助内容审核工作流、批量审核、审计报告以及发布前内容验证。
安装
Claude Desktop
添加到 ~/Library/Application Support/Claude/claudedesktopconfig.json:
json
{
mcpServers: {
glin-profanity: {
command: npx,
args: [-y, glin-profanity-mcp]
}
}
}
Cursor
添加到 .cursor/mcp.json:
json
{
mcpServers: {
glin-profanity: {
command: npx,
args: [-y, glin-profanity-mcp]
}
}
}
可用工具
核心检测
| 工具 | 描述 |
|---|
| checkprofanity | 检查文本中的脏话并返回详细结果 |
| censortext |
使用可配置的替换字符屏蔽脏话 |
| batch_check | 同时检查多个文本(最多100个) |
| validate_content | 获取安全评分(0-100)并附带操作建议 |
分析
| 工具 | 描述 |
|---|
| analyzecontext | 上下文感知分析(医疗、游戏等场景) |
| detectobfuscation |
检测Leetspeak和Unicode混淆技巧 |
| explain_match | 解释文本为何被标记 |
| compare_strictness | 比较不同严格级别的检测结果 |
实用工具
| 工具 | 描述 |
|---|
| suggestalternatives | 建议干净的替换词 |
| analyzecorpus |
分析最多500个文本以获取统计数据 |
| create
regexpattern | 生成用于自定义检测的正则表达式 |
| get
supportedlanguages | 列出所有24种支持的语言 |
用户追踪
| 工具 | 描述 |
|---|
| trackusermessage | 追踪消息以识别重复违规者 |
| getuserprofile |
获取用户的审核历史记录 |
| get
highrisk_users | 列出违规率高的用户 |
示例提示
内容审核
检查这50条用户评论,告诉我哪些需要审核
在发布前验证这篇博客文章 - 使用高严格级别
使用医疗领域上下文分析这篇医学文章
批量操作
批量检查此数组中的所有消息,仅返回被标记的消息
为这些评论生成审核审计报告
理解标记
解释为什么f4ck被检测为脏话
比较此游戏聊天消息的严格级别
内容清理
为这个被标记的文本建议专业替代词
屏蔽脏话但保留首字母
使用场景
使用MCP服务器时:
- - AI辅助内容审核工作流
- 批量检查用户提交内容
- 生成审核报告
- 发布前内容验证
- 人工参与审核
使用核心库时:
- - 自动化实时过滤(钩子/中间件)
- 每条消息都需要检查且无需AI参与
- 性能关键型应用(响应时间<1毫秒)
资源
- - npm:https://www.npmjs.com/package/glin-profanity-mcp
- GitHub:https://github.com/GLINCKER/glin-profanity/tree/release/packages/mcp
- 核心库:https://www.npmjs.com/package/glin-profanity