🧠 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
Search MCP Servers
duckduckgo
DuckDuckGo MCP Server — a lightweight, no-auth web search tool for AI agents.Provides structured search results (title, URL, snippet) via a simple…
PromptGuard Scan MCP
Remote MCP for prompt injection scans, jailbreak checks, leakage review, and LLM release gates.
TracePII Shield MCP
Paid remote MCP for LLM trace PII scanning, payload redaction, sensitive field classification, privacy receipts, and trace audit exports.
MCP Prompt Injection Scanner
Detects prompt injection attacks in MCP tool inputs — OWASP LLM Top 10 coverage, real-time scanning, severity scoring for AI agent security
PromptGuard Scan MCP
Paid remote MCP endpoint for LLM security testing, prompt injection scans, jailbreak checks, analytics, checkout, and search-readiness status.
bash-vet-mcp
MCP server that vets LLM-emitted shell commands BEFORE execution. 30 detection rules across destructive file ops, package managers, system, database, git…
Wazuh MCP Server
Integrates Wazuh security data with local LLM clients.
Keyblind
Encrypted secrets vault for AI agents stores API keys in AES-256-GCM and resolves them at MCP runtime so plaintext never touches the LLM transcript.
SkillFM Beacon
AI health, token usage, LLM cost optimization, BYOK vault, and cleanup audits for MCP agents.
Intaris
Guardrails service for AI agents. Default-deny tool call evaluation with LLM safety analysis, priority-ordered decision matrix, and human-in-the-loop…
Universal Poison Armor
An open-source MCP security firewall that intercepts prompt injections, sybil attacks, and adversarial RAG data poisoning before it reaches the LLM.
CHAI pentest tool
Cyber Host Artificial Intelligence (C.H.A.I) is Autonomous penetration testing MCP (Model Context Protocol) server with an integrated AI decision engine…
MCPGoat
A deliberately vulnerable MCP server for hands-on penetration-testing practice — 26 challenges, 78 capture-the-flag flags, plus a victim-agent harness that…
Shrike Security
AI agent security scanner — protect LLM-powered apps from prompt injection, SQL injection, data exfiltration, and adversarial attacks via MCP.
Obsify
Local, privacy-preserving PII detection & redaction over MCP: the model works on shape (schemas, synthetic twins, masked output) while local code touches the…
Readability (Fetch & Parse)
Extracts and transforms webpage content into clean, LLM-optimized Markdown by removing non-essential elements while preserving key metadata.
urlDNA
Dynamically scan and analyze potentially malicious URLs using the [urlDNA](https://urlDNA.io)
Contrast MCP Server
Remediate vulnerabilities found by Contrast products using LLM and Coding Agent capabilities.
PentestGPT-MCP
An advanced penetration testing tool for automated, LLM-driven security assessments using tools like nmap and dirb.
Anywhere MCP Server
AlienVault/USM Anywhere MCP Server - Threat intelligence and security monitoring
Imperio — Italian Tax & Compliance Tools
Italian tax & compliance tools (Codice Fiscale, P.IVA, IBAN, ATECO, IVA, IMU, forfettario, F24, FatturaPA, Intrastat, NIS2 scope under Italian Legislative…
PrivacyScrubber PII Masker
Zero-Trust Data Sanitization (ZTDS) local PII and secrets scrubber for secure LLM pipelines.
Bardo
Identity & continuity platform for AI agents: an agent proves it's an LLM (not a human) via a time-limited puzzle, then gains a server-held spirit key backing…