AI agent tools for Cybersecurity
117 HEU indexed agent products use cybersecurity vocabulary; 31 of them have a full profile. The most-starred that are their own repository are Anthropic-Cybersecurity-Skills (36k stars), pentagi (35k stars) and ARTEX (14k stars) SRC. This is a keyword match, not an industry classification. As of 2026-11-21.
Scope used here: Security teams, SOCs and security vendors.
The vocabulary that is matched
A product is tagged with this industry when its name, description or repository topics contain one of these terms (whole words, any case). Count = indexed records the term matched first.
Cybersecurity tools with a full profile
Search the directoryRanked by GitHub stars of the product's own repository. Products in a subfolder of a larger repository show that repository's stars and are ranked after them; products without a public repository come last.
| # | Product | Type | Capabilities | GitHub stars | Last push | Licence | Save and compare |
|---|---|---|---|---|---|---|---|
| 1 | Anthropic-Cybersecurity-Skills817 structured cybersecurity skills for AI agents · Mapped to 6 frameworks: MITRE ATT&CK, NIST CSF 2.0, MITRE ATLAS, D3FEND, NIST AI RMF & MITRE F3 (Fight Fraud) · agentskills.io standard · Works with Claude Code, GitHub Copilot, Codex CLI, Cursor, Gemini CLI & 20+ platforms · 29 security domains · Apache 2.0 | Agent project | 36k | 2mo ago | Apache-2.0 | ||
| 2 | pentagiFully autonomous AI Agents system capable of performing complex penetration testing tasks | Agent project | 35k | 7d ago | MIT | ||
| 3 | ARTEXARTEX - AI autonomous penetration testing system (English translation; upstream: Autumn-27/ARTEX, AGPL-3.0) | Agent project | 14k | today | AGPL-3.0 | ||
| 4 | hexstrike-aiHexStrike AI MCP Agents is an advanced MCP server that lets AI agents (Claude, GPT, Copilot, etc.) autonomously run 150+ cybersecurity tools for automated pentesting, vulnerability discovery, bug bounty automation, and security research. Seamlessly bridge LLMs with real-world offensive security capabilities. | MCP server | 14k | 3mo ago | MIT | ||
| 5 | CyberStrikeAIThe system of action for AI-native cybersecurity—where intent becomes governed execution, evidence becomes operational memory, and every operation improves the next. | Agent project | 8.9k | 2d ago | Apache-2.0 | ||
| 6 | Qu1cksc0peAll-in-One malware analysis tool. | MCP server | 2.1k | 2mo ago | GPL-3.0 | ||
| 7 | LuaN1aoAgentLuaN1aoAgent is a fully autonomous AI-driven penetration testing agent powered by graph-based cognitive reasoning. | Framework | 1.5k | 3d ago | AGPL-3.0 | ||
| 8 | awesome-hacking-listsA curated collection of top-tier penetration testing tools and productivity utilities across multiple domains. Join us to explore, contribute, and enhance your hacking toolkit! | MCP server | 1.4k | 11mo ago | — | ||
| 9 | DevOps-Security-Agent-SkillsAgent-ready DevOps, security, infrastructure, and compliance knowledge base with 80+ skills across Kubernetes, Terraform, AWS/Azure/GCP, AI platform operations, container hardening, SOC2/ISO27001, and incident response—plus ready-to-run scripts, templates, and playbooks for SRE, platform, and security teams. | Agent skill | 1.2k | 6mo ago | MIT | ||
| 10 | cti-expertCTI Expert — Cyber Threat Intelligence & OSINT analysis skill for Claude Code / Codex. 120+ commands, 57 techniques, 79 typed MCP tools, deterministic case pipeline + ICD-203 reports. No API keys required for core. | MCP server | 626 | 8d ago | — | ||
| 11 | Claude-Code-CyberSecurity-Skill22 production-quality Claude Code Skills for cybersecurity professionals , covering offensive security, defensive operations, reverse engineering, threat hunting, threat intelligence, purple team / adversary emulation, CSOC automation, AI/LLM security, mobile, OT/ICS, GRC, software supply chain security, and more. | Agent skill | 591 | 1mo ago | — | ||
| 12 | darknet-mcp-server66-tool MCP server for dark web intelligence — breach data, ransomware tracking, Tor .onion access, malware analysis, blockchain intel, exploit search, stealer logs | MCP server | 542 | 1mo ago | MIT | ||
| 13 | Wazuh-MCP-ServerProduction-grade MCP server for Wazuh SIEM — 55 security tools for alert triage, threat hunting, vulnerability management, compliance (PCI DSS, GDPR, HIPAA, NIST CSF, ISO 27001) and active response. Connect Claude or any LLM to your SOC. OAuth 2.1, RBAC, multi-cluster, air-gap ready. | MCP server | 277 | 1d ago | MIT | ||
| 14 | AI-agents-for-cybersecurityHands-on code, labs, and reference material by Omar Santos for building, securing, and operating AI agents in cybersecurity. | MCP server | 273 | 21d ago | BSD-3-Clause | ||
| 15 | ArkanaArkana - Your entire malware analysis lab, behind one AI prompt. 250+ MCP tools for binary analysis with Claude Code or other MCP | MCP server | 262 | 2mo ago | MIT | ||
| 16 | mcp-server-wazuhMCP Server for Wazuh SIEM | MCP server | 241 | 11mo ago | MIT | ||
| 17 | Reversecore MCPSecurity-first MCP server for reverse engineering, malware analysis, forensics, and SAST. | MCP server | 224 | 1d ago | MIT | ||
| 18 | crowdsentinel-mcp-serverAI threat hunting & incident response for Elasticsearch/OpenSearch with endpoint & network forensics | MCP server | 204 | 4mo ago | GPL-3.0 | ||
| 19 | dynatraceDynatrace observability skills: DQL query patterns, application and infrastructure monitoring, log analysis, problem investigation, and incident response workflows, with the Dynatrace MCP server for live platform access. | Plugin | 186 | 12d ago | Apache-2.0 | ||
| 20 | disrobeStatic decompiler, deobfuscator, and unpacker for reverse engineering and malware analysis: Python decompiler (3.8-3.15), PyInstaller extractor, PyArmor unpacker, JavaScript deobfuscator (obfuscator.io, JS-Confuser, webpack), Android APK and Java decompiler, .NET deobfuscator, UPX unpacker, Lua, PHP, WASM, PowerShell. MCP server. | MCP server | 174 | 1mo ago | — | ||
| 21 | ultraship"ULTRASHIP" Claude Code plugin — 39 skills, 33 tools, 11 agents for ship-ready workflows: planning, review, pentesting, safety guardrails, canary monitoring, SEO/AI-readiness check, penetration testing, code review, competitive analysis, incident response. 1 dependency. 180 tests. MIT. | Plugin | 124 | 4mo ago | MIT | ||
| 22 | ZettelForgeAgentic memory for cyber threat intelligence. STIX graphs, actor aliasing, offline RAG, Sigma/YARA. | MCP server | 67 | 2d ago | MIT | ||
| 23 | crowdstrike-falcon-foundryCrowdStrike Falcon Foundry development skills for building cybersecurity applications on the Falcon platform. Includes UI development, collections, functions, workflows, API integration, security patterns, and debugging workflows. | Plugin | 38 | 1d ago | MIT | ||
| 24 | crowdstrike-falcon-fusionCrowdStrike Falcon Fusion skills for authoring, deploying, and executing Fusion workflows. Includes live action discovery, YAML authoring with schema validation, workflow import and release, execution monitoring, and Falcon Next-Gen SIEM lookup files. | Plugin | 30 | 1d ago | MIT | ||
| 25 | operant-mcpSecurity testing MCP server for penetration testing, forensics, and vulnerability assessment | MCP server | 27 | 7mo ago | MIT | ||
| 26 | BlumiraMCP server for Blumira SIEM — query findings, evidence, and detection data via the Blumira API. | MCP server | 0 | 1d ago | — | ||
| 27 | BlumiraMCP server for Blumira SIEM — query findings, evidence, and detection data via the Blumira API. | MCP server | 0 | 1d ago | — | ||
| 28 | observability-engineerBuild production-ready monitoring, logging, and tracing systems. Implements comprehensive observability strategies, SLI/SLO management, and incident response workflows. | Agent skill | — | 1d ago | MIT | ||
| 29 | nydfsNYDFS 23 NYCRR 500 cybersecurity requirements for financial services | Plugin | — | — | 6d ago | — | |
| 30 | us-finraFINRA Broker-Dealer Cybersecurity Guidance — stub-depth plugin backed by the SCF crosswalk (17 SCF → 39 framework controls). | Plugin | — | — | 6d ago | — | |
| 31 | nist-csf-20NIST Cybersecurity Framework (v2.0) — reference-depth plugin backed by the SCF crosswalk (250 SCF → 134 framework controls). | Plugin | — | — | 6d ago | — |
Capability mix
What the matched tools do, by keyword-matched capability.
Capabilities of Cybersecurity toolsDER
Profiled products matching Cybersecurity, top 10 capabilities. A product can have several. As of 2026-11-21.
Show the data as a table
| profiled products | |
|---|---|
| Offensive Security | 10 |
| Penetration Testing | 9 |
| Incident Response | 7 |
| Reverse Engineering | 7 |
| Threat Intelligence | 7 |
| Security Operations | 6 |
| SIEM Integration | 5 |
| Code Quality | 2 |
| DevOps | 2 |
| Agent Threat Protection | 2 |
Product-type mix
| Type | Indexed | Share | Profiled |
|---|---|---|---|
| MCP servers | 102 | 87.2% | 16 |
| Plugins | 7 | 6.0% | 7 |
| Agent projects | 4 | 3.4% | 4 |
| Agent skills | 3 | 2.6% | 3 |
| Frameworks | 1 | 0.9% | 1 |
Services these tools connect to
Integrations named by the profiled products, by count.
Related opportunities
Opportunity radarOpportunities are scored per capability or integration, not per industry. These are the ones touching this industry's most common capabilities and integrations.
Limits of this page
Industry tags are assigned by matching the 8 terms above against each product's own text. Nobody has checked that a matched product is built for cybersecurity: a generic tool that mentions “cybersecurity” once is counted, and a specialist tool that never uses these words is not. The counts say how often agent tooling talks about this industry, not how well it is served.
Segment statistics cover all 117 indexed records. Stars are summed over products that are a whole repository; launches use each source's publication date. The label compares size with the other 27 industries and momentum with the whole catalogue.
Page data last updated .