No red flags found in any of the 11 categories — no credential harvesting, no data exfiltration, no curl-pipe-shell installer. Scanned against the SlowMist agent-security taxonomy, refreshed every 8 hours. Full audit →
by CyberStrikeus · MCP Server · ★ 1.9k
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
🔒 Is CyberStrike safe to install? View the security audit →
English | 简体中文 | 繁體中文 | 한국어 | Deutsch | Español | Français | Italiano | Dansk | 日本語 | Polski | Русский | Bosanski | العربية | Norsk | Português (Brasil) | ไทย | Türkçe | Українська | বাংলা | Ελληνικά | Tiếng Việt | हिन्दी The first open-source AI agent built for offensive security. Automated penetration testing from your terminal — plug in your Claude, GPT, or any LLM subscription and turn it into an autonomous red team agent with 13+ specialize
| Stars | 1,913 |
| Forks | 291 |
| Language | TypeScript |
| Category | MCP Server |
| License | AGPL-3.0 |
| Quality Score | 64.5585582941523/100 |
| Open Issues | 12 |
| Last Updated | 2026-08-21 |
| Created | 2026-02-14 |
| Platforms | aws, browser, mcp, node |
| Est. Tokens | ~19k |
These tools work well together with CyberStrike for enhanced workflows:
Looking for a CyberStrike alternative? If you're comparing CyberStrike with other mcp server tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.
The AI Agent for Cyber Security.
Turn Claude Code into your offensive security research assistant. Specialized AI subagents for authorized pene
Open-source AI pentester that proves every finding. Machine oracles re-run each exploit; verified bugs ship a
A security scanner for your LLM agentic workflows
A curated collection of top-tier penetration testing tools and productivity utilities across multiple domains.
An agent-native red-teaming workspace with a fast browser, direct HTTP traffic control, sandboxed execution, a
Explore other popular mcp server tools:
CyberStrike is Open-source AI-augmented offensive security harness. 13+ autonomous agents, 150+ LLM providers, 5,300+ models, 7,600+ Ed25519-signed attack skills, 56+ built-in tools, 176+ MCP tools. MITRE ATT&CK, OW. It is categorized as a MCP Server with 1.9k GitHub stars.
CyberStrike is primarily written in TypeScript. It covers topics such as ai, ai-agent, ai-security.
You can find installation instructions and usage details in the CyberStrike GitHub repository at github.com/CyberStrikeus/CyberStrike. The project has 1.9k stars and 291 forks, indicating an active community.
CyberStrike is released under the AGPL-3.0 license, making it free to use and modify according to the license terms.
The top alternatives to CyberStrike on Agent Skills Hub include numasec, pentest-ai-agents, pentest-ai. Each offers a different approach to the same problem space — compare them side-by-side by stars, quality score, and community activity.
Grades come from a rule-based scan built on the SlowMist agent-security taxonomy, covering 11 red-flag categories including credential harvesting, data exfiltration, and curl | sh installers. It is a first-layer scan, not a manual audit — we say so rather than overstate it.
The scale of the problem is documented independently: Liu et al. (2026), in a study of 31,132 agent skills, report that 26.1% contain security vulnerabilities. Our own full-catalog census is published as a citable open dataset.
Sources & who's responsible: