Use Lakera AI Guardrails MCP to take action in your AI tools

Analyze Sentiment

Analyze text sentiment to detect negative, hostile, or inappropriate emotional tone in content.

Check for Jailbreak Attempt

Detect jailbreak attempts where users try to bypass AI safety guidelines and restrictions.

Check for Prompt Injection

Detect prompt injection attempts where users try to manipulate AI behavior through malicious prompts.

Detect PII

Detect personally identifiable information (PII) such as names, emails, phone numbers, addresses, and other sensitive data.

Detect Toxicity

Detect toxic, offensive, or harmful language including hate speech, profanity, and abusive content.

Screen Content

Screen text content for security threats including prompt injection, jailbreaks, PII, toxicity, and more using Lakera Guard.