{"id":"agent-security-scanner-mcp","name":"agent-security-scanner-mcp","af_score":80.5,"security_score":56.5,"reliability_score":47.5,"what_it_does":"Security scanner MCP server for AI coding agents. Prompt injection firewall, package hallucination detection (4.3M+ packages), 1700+ vulnerability rules with AST & taint analysis, LLM-powered semantic code review, auto-fix. For Claude Code, Cursor, Windsurf, Cline, OpenClaw.","best_when":null,"avoid_when":null,"last_evaluated":"2026-03-21T23:56:42.878192+00:00","has_mcp":true,"has_api":true,"auth_methods":["api_key"],"has_free_tier":true,"known_gotchas":[],"error_quality":null}