MCP servers and skills: search, filter by where they run, and compare.
Hands-on labs for securing AI agents and agentic protocols based open standards
MCPLink only★ 1Few stars
Using MCP tool practices to empower an LLM to cross reference incident data of security alerts with known KEV/NVD data and escalate accordingly, removing noise and drawing attention to more valid conc
MCPLink only★ 1Few stars
Governance for AI agents: a deny-by-default policy layer for Claude Code and agent/skill builds. Every tool call is authorized, contained, and audited. Apache-2.0.
MCPLink only★ 3Few stars
AI/LLM security knowledge base — OWASP LLM Top 10, MITRE ATLAS, prompt injection, agentic security. An Obsidian vault: 92 interlinked, fully-cited pages.
MCPLink only★ 6
An open-source, AI-native Model Context Protocol (MCP) server bridging Large Language Models with core network diagnostic tools for automated observability, threat detection, and agentic security orch
MCPLink only★ 1Few stars
Agentic security control plane for MCP and AI agent tool calls. MCP-native policy gateway with topology discovery and audit.
MCPLink only★ 6
Detect and Deny - Deterministic Function-Level Guardrails for AI Agents
MCPLink only★ 18
The "Metasploitable" of MCP — a deliberately vulnerable Model Context Protocol server for agentic-security training, mapped to the OWASP Top 10 for Agentic Applications.
MCPLink only★ 7
Local security layer for AI coding agents that blocks secret leaks, destructive commands, unsafe Git operations, and unauthorized network access.
MCPLink only★ 1Few stars
Offensive-security scanner for multi-agent systems: MCP and A2A agent protocols plus MQTT agent messaging, verified against the reference SDKs. Aligned with OWASP Agentic Top 10 (2026).
MCPLink onlyFew stars
Ed25519-signed tool manifests for MCP. Stop tool-poisoning and rug-pull attacks with cryptographic verification.
MCPLink only★ 1Few stars
Guardian is a next-generation agentic security system built on the Model Context Protocol (MCP). Unlike static scripts, it uses LangGraph to autonomously reason through AWS infrastructure, identify cr
MCPLink only★ 1Few stars
Claude skill — applies ASD/CISA/NSA/NCSC agentic AI security framework inline during agent development
SkillLink onlyFew stars
Secure AI customer support demo using LangChain, Groq, FastMCP, and Descope to compare unprotected MCP tools with scoped, JWT-protected tool access.
MCPLink only★ 5
Open-source adversary emulation for AI agents and MCP servers.
MCPLink only★ 584
AI red-teaming tool and LLM security framework to evaluate agentic AI applications. Tests prompt injections, handles vulnerability assessment, SBOM generation, and static analysis.
MCPLink only★ 67
Real-time security guardrail enforcer for agent call chains intercepting tool cascades (AppSentinels style)
SkillLink only★ 8
Agentic AI security — guidance site, control surface, masterfabric-next-sec, and ISMS pack (SOC 2 / ISO 27001 / ASVS L2)
MCPLink only★ 8
SAIL V2 (Secure AI Lifecycle) as an agent skill — the full 91-risk catalog for AI/agent gap assessments, security roadmaps, and compliance checklists. Installs on Claude Code, Codex, ChatGPT, Antigrav
SkillLink only★ 113
Let AI agents do real WordPress work via MCP. 61 core abilities, 12 add-ons, 280+ ecosystem abilities for content, builders, SEO, security, files, and operations.
MCPLink only★ 39
An open database of real-world AI agent incidents.
MCPLink only★ 27
Agentic API security fuzzer synthesizing directory traversal mutations, URL encodings, and path normalization escapes
SkillLink only★ 7
Agentic API security fuzzer synthesizing directory traversal mutations, URL encodings, and path normalization escapes
SkillLink only★ 7
Who stands behind it
