Data

Tools

Indexes

Applications

Experiments

Awesome

An open API service indexing awesome lists of open source software.

https://github.com/raphabot/awesome-cybersecurity-agentic-ai


https://github.com/raphabot/awesome-cybersecurity-agentic-ai

List: awesome-cybersecurity-agentic-ai

Last synced: 3 months ago
JSON representation

Awesome Lists containing this project

README 

          


	Awesome




# Awesome Cybersecurity Agentic AI



## Table of Contents

- [MCP Servers](#mcp-servers)

- [Research](#research)

- [Tools](#tools)

- [Frameworks](#frameworks)

- [Datasets](#datasets)

- [Communities](#communities)



## MCP Servers

- [alexgoller/illumio-mcp-server](https://github.com/alexgoller/illumio-mcp-server) - MCP server for Illumio PCE, enabling AI-driven workload management, label operations, and traffic flow analysis for security.

- [Bamimore-Tomi/ghidra_mcp](https://github.com/Bamimore-Tomi/ghidra_mcp) - MCP server for Ghidra, providing reverse engineering and binary analysis capabilities to LLMs and agentic workflows.

- [addcontent/nuclei-mcp](https://github.com/addcontent/nuclei-mcp) -  MCP server implementation for Nuclei, a fast and customizable vulnerability scanner.

- [PortSwigger/mcp-server](https://github.com/PortSwigger/mcp-server) - MCP integration for Burp Suite, enabling web security testing and automation via agentic AI workflows.

- [MorDavid/BloodHound-MCP-AI](https://github.com/MorDavid/BloodHound-MCP-AI) - MCP server for BloodHound, providing Active Directory analysis and attack path discovery for agentic AI.

- [MCPPhalanx/binaryninja-mcp](https://github.com/MCPPhalanx/binaryninja-mcp) - MCP server for Binary Ninja, enabling binary analysis and reverse engineering in agentic workflows.

- [BurtTheCoder/mcp-virustotal](https://github.com/BurtTheCoder/mcp-virustotal) - MCP server for querying the VirusTotal API for file and URL malware analysis.

- [BurtTheCoder/shodan-mcp-server](https://github.com/BurtTheCoder/mcp-shodan) - MCP server for querying Shodan, providing data on Internet-connected devices for security analysis.

- [BurtTheCoder/mcp-dnstwist](https://github.com/BurtTheCoder/mcp-dnstwist) - MCP server for DNS fuzzing with dnstwist, detecting phishing and domain takeover threats.

- [BurtTheCoder/mcp-maigret](https://github.com/BurtTheCoder/mcp-maigret) - MCP server for OSINT data collection with Maigret, gathering user info from various sources.

- [atomicchonk/roadrecon_mcp_server](https://github.com/atomicchonk/roadrecon_mcp_server) - MCP server for Azure AD data analysis with ROADRecon, mapping Azure Active Directory environments.

- [mobilehackinglab/jadx-mcp-plugin](https://github.com/mobilehackinglab/jadx-mcp-plugin) - Jadx plugin for MCP server access, used for decompiling Android apps.

- [urldna/mcp](https://github.com/urldna/mcp) - urlDNA MCP server for phishing detection and URL analysis through advanced contextual scanning.



## Research

- [D-CIPHER](https://arxiv.org/html/2502.10931v2) - A multi-agent framework for collaborative CTF solving.

- [BreachSeek](https://arxiv.org/html/2409.03789v1) - A Multi-Agent Automated Penetration Tester

- [AutoCTF: Automated Capture The Flag Framework](https://arxiv.org/abs/2306.00988) - Research on an automated CTF framework using agentic AI for autonomous penetration testing and vulnerability discovery.

- [CyberBattleSim (Microsoft)](https://github.com/microsoft/CyberBattleSim) - Research platform for simulating cybersecurity environments and evaluating autonomous agents in attack/defense scenarios.

- [OpenAI Cybersecurity Challenge](https://openai.com/research/cybersecurity-challenge) - Research initiative exploring the use of LLMs and agentic AI for automated vulnerability discovery and exploitation.

- [Multi-Agent Systems for Cybersecurity](https://arxiv.org/abs/2107.07229) - Survey and research on the application of multi-agent systems in cybersecurity, including threat detection and response.

- [LLM Agents for Automated Penetration Testing](https://arxiv.org/abs/2402.02444) - Paper on leveraging LLM-based agents for autonomous penetration testing and red teaming.

- [AI CTF: Autonomous Agents in Cybersecurity Competitions](https://arxiv.org/abs/2311.09999) - Research on the use of agentic AI in CTF competitions and cybersecurity challenges.

- [Dynamic-Risk-Assessment](https://arxiv.org/abs/2505.18384) - Dynamic risk assessment specifically for offensive cybersecurity agents, offering insights into evaluating the risks and potential impact of autonomous attack tools.

- [CAI: An Open, Bug Bounty-Ready Cybersecurity AI](https://arxiv.org/abs/2504.06017) - Comprehensive research on an open-source agentic AI system for cybersecurity and in particular for bug bounty, featuring hierarchical agent patterns, multi-agent collaboration, and autonomous penetration testing capabilities.



## Tools

- [AgentFence](https://github.com/agentfence/agentfence) - Open-source platform for automatically testing AI agent security, detecting vulnerabilities like prompt injection, secret leakage, and system instruction exposure.

- [AICA Agent](https://github.com/aica-iwg/aica-agent) - Autonomous intelligent cyberdefense agent for research and production, supporting advanced detection, response, and management capabilities.

- [msoedov/agentic_security](https://github.com/msoedov/agentic_security) - An open-source vulnerability scanner specifically designed for Agent Workflows and LLMs, aiming to protect against issues like jailbreaks and fuzzing attacks.

- [agenticsorg/agentic-security](https://github.com/agenticsorg/agentic-security) - An AI-powered security analysis tool intended to automatically detect vulnerabilities within code repositories.

- [pentagi](https://github.com/vxcontrol/pentagi) - Fully autonomous AI-powered agent system designed for penetration testing.

- [`CAI` (Cybersecurity AI)](https://github.com/aliasrobotics/CAI) - Open-source Bug Bounty-ready AI system with hierarchical agentic patterns, supporting autonomous penetration testing, vulnerability discovery, and multi-agent cybersecurity workflows.

- [Vulert](vulert.com) - Vulert secures software by detecting vulnerabilities in open-source dependencies—without accessing your code. It supports Js, PHP, Java, Python, and more

- [Agentic Radar](https://github.com/splx-ai/agentic-radar) - Open-source CLI security scanner for agentic workflows.

- [Reaper](https://github.com/ghostsecurity/reaper) - Open Source Agentic Web App security testing and tampering tool by Ghost Security



## Frameworks

- [MAESTRO (CSA)](https://cloudsecurityalliance.org/blog/2025/02/06/agentic-ai-threat-modeling-framework-maestro) - Threat modeling framework for agentic AI, focusing on multi-agent security, layered risk analysis, and secure agentic system design.

- [Microsoft Semantic Kernel](https://github.com/microsoft/semantic-kernel) - Context-aware agentic AI framework for integrating semantic reasoning and automation in security operations.

- [ATFAA/SHIELD](https://arxiv.org/abs/2504.19956) - Advanced threat and mitigation frameworks for securing generative/agentic AI agents, with a focus on unique agent vulnerabilities and enterprise security.

- [Microsoft AutoGen](https://github.com/microsoft/autogen) - Framework for orchestrating multi-agent systems, enabling collaborative AI agents for complex cybersecurity and automation tasks.

- [LangChain](https://github.com/langchain-ai/langchain) - Modular framework for building LLM-powered agentic workflows, including security automation, retrieval-augmented generation, and tool integration.

- [LangGraph](https://github.com/langchain-ai/langgraph) - Graph-based extension of LangChain for advanced state management and multi-agent workflows, suitable for cybersecurity automation.

- [CrewAI](https://github.com/crewAIInc/crewAI) - Open-source framework for orchestrating teams of AI agents, supporting collaborative and specialized agentic workflows in security contexts.

- [Agno](https://github.com/agno-agi/agno) - Lightweight, high-performance library for building Agents.



## Datasets

- [CyberBattleSim Dataset](https://github.com/microsoft/CyberBattleSim) - Synthetic cybersecurity environments and logs for training and evaluating autonomous agents in attack/defense scenarios.

- [CTF Datasets (DEF CON, CSAW, PicoCTF, etc.)](https://github.com/ctfs/write-ups-2014#datasets) - Real-world and simulated Capture The Flag (CTF) challenges and solutions for agentic AI and automated penetration testing research.

- [DARPA Transparent Computing Datasets](https://drive.google.com/drive/folders/1okt4AYElyBohW4XiOBqmsvjwXsnUjLVf) - Large-scale, labeled system event data for red/blue team cyber operations, suitable for multi-agent and autonomous defense research.

- [UNSW-NB15](https://research.unsw.edu.au/projects/unsw-nb15-dataset) - Network traffic and labeled attack data for training and evaluating AI-based intrusion detection and response agents.

- [CICIDS 2017/2018](https://www.unb.ca/cic/datasets/) - Realistic network traffic datasets with labeled attacks for developing and benchmarking agentic cybersecurity solutions.



## Learning Resources/Podcast

- [AI Security Podcast](https://www.aisecuritypodcast.com/) - Interviews with CISOs of Anthrophic, DeepMind and more doing amazing work in LLM and cybersecurity. Topics include Agentic AI, Red Team with AI, AI for Security and Security from AI & more. The show is hosted by 2 former CISOs and currently has the largest CISO & Tech Leader audience for AI Security.

- [Agentic Security Newsletter](https://agenticsecurity.substack.com/) - A Newsletter that explores how autonomous, AI-driven agents are reshaping both offensive and defensive security. Each issue dives into the latest in tactics, tools, and ideas defining the future of security.

- [awesome-ai-agents](https://github.com/e2b-dev/awesome-ai-agents) - A curated list of AI autonomous agents. While not exclusively cybersecurity focused, it's a valuable resource for discovering emerging frameworks and platforms that could be adapted for security purposes.



## Communities

- *Submit your awesome Agentic AI Cybersecurity community here!*



---



*Contributions welcome! See [contributing guidelines](CONTRIBUTING.md) for details.*