"Viber" matching MCP servers:

60-rule static security scanner and MCP skill poisoning auditor that detects leaked secrets, unguarded API routes, missing database RLS, and prompt injection in AI-generated codebases.

Enables MCP-compatible AI applications to perform read-only npm package and project dependency safety scans, returning proceed, caution, or block verdicts without executing package code.

Enables scanning of code and URLs for security vulnerabilities (hardcoded secrets, missing headers, etc.) via Claude Code, integrating with the vibe-audit security scanner.

Enables AI-powered security scanning of codebases through conversational analysis, allowing users to assess, threat model, code review, DAST test, and generate security reports using natural language with Claude.