Security & Testing MCP Servers

MCP servers for security scanning, vulnerability testing, secrets management and QA automation. Each entry is scanned with the deterministic Capability-Flow Trust Model — grades are computed, never self-reported.

Agent Shield npm

@elliotllliu/agent-shield

Multi-engine AI agent security scanner — one scan, four engines, one report

Security & Testing Score 79/100 27 findings 56/wk Cap. High

Mobile Security npm

mobile-security-mcp

Mobile app security analysis MCP server for Android APK and iOS IPA files

Security & Testing Score 79/100 17 findings 42/wk Cap. High

Guard npm

@agentsid/guard

MCP server for safe shell, file, database, git, and HTTP access. Every operation validated against per-agent permission rules. Powered by AgentsID.

Security & Testing Score 79/100 18 findings 14/wk Cap. High

Mund Source verified npm

@weave_protocol/mund

The Guardian Protocol - MCP-based security monitoring for agentic AI systems

Security & Testing Score 76/100 7 findings 109/wk Cap. High

Ludus npm

ludus-mcp

MCP server for managing Ludus cybersecurity training environments through natural language commands

Security & Testing Score 76/100 23 findings 15/wk Cap. High

Faostat PyPI

faostat-mcp

MCP server exposing the full FAOSTAT API to AI assistants

Security & Testing Score 74/100 2 findings Cap. Moderate

Kbot npm

@kernel.chat/kbot

Open-source terminal AI agent. 100+ specialist skills + audit-grade finance infra via @kernel.chat/kbot-finance. Content-addressed envelopes, hash-chained audit log, jurisdiction-aware regulatory verifier. The AI Intelligence Layer never produces the numb

Security & Testing Score 72/100 57 findings 802/wk Cap. Critical