YUSA
Prompt-injection firewall for AI agents: scan untrusted text, fence it, gate tool calls.
Busca por la tarea que quieres hacer o por la app que usas, y luego filtra por categoría.
Ordenado por puntuación de uso: estrellas de GitHub, descargas semanales, lo reciente de su última versión y si su endpoint responde. Más usado no es lo mismo que mejor.
Cómo leer una tarjeta:↓ Descargas por semanai★ Estrellas de GitHubiTres pilares: reseñas · revisiones · usoiActualizado = fecha en que se publicó la última versión en el registroi
Prompt-injection firewall for AI agents: scan untrusted text, fence it, gate tool calls.
Record what your AI did as tamper-evident evidence for ISO 42001, EU AI Act and SOC 2. Hash-only.
Governed Symantec DCS operations — 35 MCP tools, read-only with audit.
Manage a Ubiquiti UniFi network: devices, clients, WiFi, firewall and VPN. Read-only by default.
Human approval for AI agents: E2E-encrypted secrets and gated Gmail, GitHub and MCP tools.
On-device NIST SP 800-38G FF1 (9/9 CAVP) pseudonymization, OWASP MCP05/06 guard & EU AI Act AIBOM.
Security gateway: verifies what MCP servers really do, then confines each call. Needs Docker.
MCP server for the Frame security scanner: scan, verify, fix, exploit, packs and separation logic.
30 security tools + the Vigia agent to audit MCP servers before you connect.
Temporary authorized security research probe. Safe to ignore. Will be removed shortly.
Audit repos for security, code quality and AI code risks; read findings and open fix PRs.
Deterministic authorization and security guard for AI agent actions with signed receipts.
Triage semgrep findings with GMI Inference, with cost shown before every run.
WatchGuard Cloud Firebox, Endpoint Security, ThreatSync, NDR and AuthPoint APIs for every customer
CLI and MCP server for RocketCyber Managed SOC: triage, MTTR, and posture analytics.
Proofpoint TAP threats, VAPs, clickers, and IOCs from your terminal, with a local threat store.
Pay-per-call agent security (x402): injection, tools, shell/SQL, memory, leaks, docs, safe web reads
MCP security trust layer: scan packages, inspect repos, check exposure, monitor changes.
Scans AI coding sessions and assistant configs for leaked secrets and risky hooks; local, redacted
Read-only Keeper MSP posture across every client, with history, a change feed and no path to a
Kolivri AI Voice MCP Server — real phone line for AI agents with KYC & rate-limit guards.
Security layer for AI agents: Retrieve for controlled SQL reads, Guard for allow/deny writes.
RAM-only HTTP debugging proxy and MCP server in Go. AI agents see salted tags, never secrets.
Site/email/agent safety and monitors: SPF/DKIM, SEO, change + RSS monitors, hidden-AI, WHOIS (7).