detect_obfuscation

MCP tool from Glin Profanity by glincker

Detect leetspeak and Unicode tricks

How to use it

Project documentation lists detect_obfuscation for the Glin Profanity MCP server. Add the server to your MCP client (Claude Desktop, Cursor, Windsurf and others), then check which tools your installed version makes available. Tool availability can depend on configuration and credentials. A server handshake does not verify this tool’s behavior. See the full listing for setup details.

Install Glin Profanity

$npm install glin-profanity
FULL GLIN PROFANITY LISTING

Other tools in Glin Profanity (23)

analyze_context

Context-aware analysis with domain whitelists

analyze_corpus

Analyze up to 500 texts for moderation stats

batch_check

Check multiple texts in one operation

censor_text

Censor profanity with configurable replacement

check_profanity

Check text for profanity with detailed results

check_prompt_injection

Scan text for prompt injection attacks (rule-based, 50 patterns)

compare_strictness

Compare results across strictness levels

create_regex_pattern

Generate regex patterns for custom detection

explain_match

Explain why text was flagged with reasoning

get_high_risk_users

List users with high violation rates

get_stream_stats

Get streaming session statistics

get_supported_languages

List all 24 supported languages

get_user_profile

Get moderation profile for a specific user

redact_pii

Redact PII into reversible vault-backed placeholders

reset_user_profile

Reset a user's moderation history

restore_pii

Restore PII placeholders to original values via vault session

scan_pii

Detect PII: email, phone, SSN, credit card, IBAN, passport, and more

scan_secrets

Detect leaked API keys, tokens, and credentials (110 patterns + entropy)

stream_batch

Stream multiple texts with live results

stream_check

Real-time streaming profanity check

suggest_alternatives

Suggest clean alternatives for profane content

track_user_message

Track user messages for repeat offender detection

validate_content

Content validation with safety scoring (0-100)