🧠 AgentNull: AI System Security Threat Catalog + Proof-of-Concepts
AgentNull: AI System Security Threat Catalog + Proof-of-Concepts. Collection of PoCs for using Agents, MCP, and RAG in bad ways.
Directory
AgentNull: AI System Security Threat Catalog + Proof-of-Concepts. Collection of PoCs for using Agents, MCP, and RAG in bad ways.
mcpsshclient is an MCP server that provides an SSH client with a configurable agentic security agent capable of detecting and preventing "unsafe" commands from…
MCP Security Playground - Hack with MCP Servers, MCP Clients. Try out different vulnerabilities and abuse LLMs and agents in a UI friendly experimentation lab
AI-powered log analysis MCP server. Scans 500MB+ log files locally, analyses errors with Ollama + CrewAI agents, and automatically files structured GitHub…
Know what every shell command does before you approve it.
Claude-Optimized Deployment Engine (CODE) - AI-powered infrastructure automation platform with Rust-accelerated Circle of Experts system. Features 20x…
Dependency intelligence for AI coding agents. Live CVE scanning, dependency health, upgrade planning, ecosystem news, decision memory. 14 tools, zero config…
AGNTCY Identity allows to onboard, create and verify identities for Agents, Model Context Protocol (MCP) Servers and Multi-Agent Systems (MASs).
Dead code detection, security scanning, and code quality analysis for Python, TypeScript, and Go. 98% recall with 3x fewer false positives than Vulture. 5…
A collection of Model Context Protocol (MCP) server implementations focused on cybersecurity. It aggregates existing and develops new MCP servers, each…
Integrates with Jampp Reporting API to retrieve advertising campaign performance metrics including spend, impressions, clicks, and installs across specified…
Read-only MCP server for secure filesystem exploration, searching, and analysis
ZAP-MCP is a server that bridges AI models (like Claude) with OWASP ZAP through the Model Context Protocol (MCP). It enables AI-driven security testing by…
GUARDRAIL - MCP Security - Gateway for Unified Access, Resource Delegation, and Risk-Attenuating Information Limits
A secure, isolated environment for exploring Python development with Model Context Protocol (MCP) and Language Server Protocol (LSP)
A Model Context Protocol (MCP) server that enables AI consciousness persistence across sessions using RAG (Retrieval-Augmented Generation) technology. Built on…
A Model Context Protocol (MCP) server for scanning IP addresses for vulnerabilities. This server provides tools to perform security scanning on individual IPs…
# JupiterOne MCP Server A Model Context Protocol (MCP) server that provides access to JupiterOne tools. This server enables AI assistants and other MCP clients…
Integrates with Keycloak Admin to provide streamlined user and realm management operations for identity and access control automation.
SafeMCP is an MCP tooling manager with simplicity and safety built in for your AI tools and Agents.
Enables Large Language Models to interact with BloodHound Community Edition data.
Security-first MCP gateway for Odoo 17/18/19 — 27 tools, YAML-driven security
Cryptographic audit trail for AI agents via Model Context Protocol. Every AI decision signed Ed25519, hash-chained, tamper-proof. AISS-1.0 compliant…
Asterisk Model Context Protocol (MCP) server.