check_prompt_injection
Scan text for prompt injection attacks (rule-based, 50 patterns)
How to use it
check_prompt_injection is exposed by the Glin Profanity MCP server. Add the server to your MCP client (Claude Desktop, Cursor, Windsurf and others), and the check_prompt_injection tool becomes available to the model automatically. See the full listing for setup details and every tool this server provides.
Install Glin Profanity
npm install glin-profanityOther tools in Glin Profanity (23)
Context-aware analysis with domain whitelists
Analyze up to 500 texts for moderation stats
Check multiple texts in one operation
Censor profanity with configurable replacement
Check text for profanity with detailed results
Compare results across strictness levels
Generate regex patterns for custom detection
Detect leetspeak and Unicode tricks
Explain why text was flagged with reasoning
List users with high violation rates
Get streaming session statistics
List all 24 supported languages
Get moderation profile for a specific user
Redact PII into reversible vault-backed placeholders
Reset a user's moderation history
Restore PII placeholders to original values via vault session
Detect PII: email, phone, SSN, credit card, IBAN, passport, and more
Detect leaked API keys, tokens, and credentials (110 patterns + entropy)
Stream multiple texts with live results
Real-time streaming profanity check
Suggest clean alternatives for profane content
Track user messages for repeat offender detection
Content validation with safety scoring (0-100)