Should I allow this text? Profanity and toxicity checks that are hard to fool, with the evidence.
Score is being calculated.
Check up to 100 texts at once. Each item has an id and a text; results come back in order.
| Name | Required | Description | Default |
|---|---|---|---|
| items | Yes | ||
| policy | No | ||
| context | No |
Decide whether a text should be allowed: profanity, slurs, threats and sexual language, including disguised spellings. Returns the action (allow, review, block), the evidence, a one-sentence reason and a censored version. Use context "username" for names shown publicly.
| Name | Required | Description | Default |
|---|---|---|---|
| mask | No | ||
| mode | No | ||
| text | Yes | ||
| policy | No | ||
| context | No |
A complete, runnable recipe for adding Unprofane to a platform (supabase, clerk, firebase, auth0, better-auth, unity, godot, or plain http) in a language.
| Name | Required | Description | Default |
|---|---|---|---|
| language | Yes | ||
| platform | Yes |
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
check_batchcheck_textget_integration_snippetToxicity scores (0-1) for text before an agent posts it. Perspective API compatible. No LLM.
Toxicity, sentiment, NER, PII detection, and language identification tools
Sentiment, toxicity, entity extraction, PII, translation, summary, QA, fraud scoring, safety audit.
Detect grooming, bullying, fraud, and 16+ online threats across text, voice, image, and video.
Add one secure layer between your agents and this server.
