Scam Detection
Scam and phishing detection for AI agents: safe/warn/danger verdicts for URLs and messages.
- Transport
- Not stated
- Package
- —
- Registry id
- com.cautellus/scam-detection
No install snippet on purpose. A working MCP config is a command, its arguments and an environment block — the last two are where API keys live, so this catalogue never stores them and cannot publish them. Follow the link above for the authors' own instructions.
Cautellus offers scam protection for AI agents. The scan_url tool provides a verdict, risk score, and findings for a URL before an agent acts on it. The scan_message tool analyzes messages, emails, or text before an agent acts on them.
Each scan returns one of three verdicts: safe, warn, or danger, with specific guidance. A scan includes a 0-100 risk score and findings such as brand impersonation and typosquatting.
Summary drafted from the project's own website. Every sentence is backed by text on that page and was reviewed before publishing.