security tools for AI agents: URL safety scanning, prompt injection detection (200+ patterns), email/password breach checks via HIBP, domain & IP reputation analysis, and AI skill supply chain scanning. Free tier (3 calls/day) or pay-per-request with USDC micropayments via x402.
Scored across 9 tools
Most tools target clearly distinct resources: domain, email, IP, password, prompt, URL, and skill scans are easy to tell apart. The main ambiguity is between check_password and check_password_range, and full_scan intentionally overlaps with all individual check_* tools as an aggregator.
The set is consistently snake_case and mostly follows a check_<target> pattern. Minor deviation: full_scan and scan_skill use scan rather than check, but the convention remains readable and predictable.
Nine tools is well-scoped for a security-checking API. Each tool has a clear role, with dedicated checks for common targets plus aggregate/full scan entry points.
The surface covers domain, email, IP, password, URL, prompt injection, and AI skill/plugin scanning, with full_scan aggregating checks. Minor gaps exist around broader file/hash malware analysis or CVE/vulnerability lookup, but core security-check workflows are covered.
Check domain reputation: DNS records, blacklists (Spamhaus, SpamCop, SORBS), SPF/DMARC, SSL.
Inputs: domain (required).
Check if an email address has been exposed in known data breaches via HIBP.
Inputs: email (required).
Check IP reputation: blacklists, Tor exit node detection, reverse DNS.
Inputs: ip (required).
Check if a password hash (SHA-1) has been exposed in known data breaches via HIBP.
Inputs: hash (required).
Look up a SHA-1 hash prefix in the HIBP k-Anonymity database.
Inputs: prefix (required).
Detect prompt injection in text. Analyzes across 4 categories (direct injection, encoding tricks, exfiltration, indirect injection) with 200+ detection patterns. Designed for real-time inline usage before processing untrusted user input. Returns boolean verdict, confidence score (0-1), matched patterns with evidence, and decoded content if encoding obfuscation was detected. Response time <100ms p95.
Inputs: prompt (required), context.
Check a URL for malware, phishing, and other threats. Uses URLhaus + heuristic analysis.
Inputs: url (required).
Run all security checks on a target (URL, domain, IP, or email). Most comprehensive scan.
Inputs: target (required).
Scan an AI agent skill/plugin for security issues across 8 risk categories (Snyk ToxicSkills taxonomy). Checks for prompt injection, malicious code, suspicious downloads, credential handling, secret detection, third-party content, unverifiable dependencies, and financial access patterns. Static analysis only — no code execution. Returns risk score (0-100), severity-ranked findings with file locations, and human-readable summary.
Inputs: files, skill.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Add one secure layer between your agents and this server.