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 cyproxio · MCP Server · ★ 631
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
🔒 Is mcp-for-security safe to install? View the security audit →
MCP for Security [!WARNING] This repository is no longer actively maintained. All tools have been migrated to Bolt — a fully rewritten, Docker-supported MCP security tool server. Please use Bolt instead: https://github.com/cyberstrikeus/bolt About Cyprox — The Future of AI-Driven Cybersecurity Cyprox is pioneering the future of cybersecurity by combining artificial intelligence and security tools to empower organizations with next-level threat detection and automated response. "The Future of Cybersecurity Humans and AI, Working Together..." Cyprox 🚀 AI Driven Solutions: Cybersecurity solutions using Agentic-AI systems with an AI-driven approach 🌐 Community-Driven: Open-source projects fostering collaboration and rapid evolution. ⚡ Speed & Precision: Automated threat detection that reduces human latency. 🔒 Secure & Transparent: Trustworthy platform built with
| Stars | 631 |
| Forks | 102 |
| Language | TypeScript |
| Category | MCP Server |
| License | MIT |
| Quality Score | 62.5038385287826/100 |
| Open Issues | 26 |
| Last Updated | 2026-03-30 |
| Created | 2025-04-03 |
| Platforms | browser, mcp, node |
| Est. Tokens | ~15k |
Looking for a mcp-for-security alternative? If you're comparing mcp-for-security 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.
Open-source AI pentester that proves every finding. Machine oracles re-run each exploit; verified bugs ship a
The AI Agent for Cyber Security.
Turn Claude Code into your offensive security research assistant. Specialized AI subagents for authorized pene
IAM for your AI agents. Set what Claude Code, Codex, Gemini, Cursor and any MCP server are allowed to do, revi
ToolHive is an enterprise-grade platform for running and managing Model Context Protocol (MCP) servers.
Open-source AI-augmented offensive security harness. 13+ autonomous agents, 150+ LLM providers, 5,300+ models,
Explore other popular mcp server tools:
mcp-for-security is MCP for Security: A collection of Model Context Protocol servers for popular security tools like SQLMap, FFUF, NMAP, Masscan and more. Integrate security testing and penetration testing into AI workfl. It is categorized as a MCP Server with 631 GitHub stars.
mcp-for-security is primarily written in TypeScript. It covers topics such as ai-assistants, ai-security, cybersecurity.
You can find installation instructions and usage details in the mcp-for-security GitHub repository at github.com/cyproxio/mcp-for-security. The project has 631 stars and 102 forks, indicating an active community.
mcp-for-security is released under the MIT license, making it free to use and modify according to the license terms.
The top alternatives to mcp-for-security on Agent Skills Hub include pentest-ai, numasec, pentest-ai-agents. 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: