by cyproxio · MCP Server · ★ 631
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
None of the 42 rules matched — no credential harvesting, no data exfiltration, no curl-pipe-shell installer. Scanned against 42 published rules built on the SlowMist agent-security taxonomy, refreshed every 8 hours. Full audit →
The quality score combines nine heuristic checks of the repo and its README: completeness, clarity, specificity, examples, structure, agent readiness, step-by-step content, instruction quality and security notes. It rates how well the project explains itself to an agent, not the code.
| Stars | 631 |
| Forks | 102 |
| Language | TypeScript |
| Category | MCP Server |
| License | MIT |
| Quality Score | 63/100 |
| Open Issues | 26 |
| Last Updated | 2026-03-30 |
| Created | 2025-04-03 |
| Platforms | browser, mcp, node |
| Est. Tokens | ~15k |
MCP for Security [!WARNING] This repository is no longer actively maintained.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...
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
Access control for AI agents. Set what Claude Code, Codex, Gemini, Cursor and any MCP server are allowed to do
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:
Grades come from a rule-based scan built on the SlowMist agent-security taxonomy: 42 published rules, covering credential harvesting, data exfiltration, curl | sh installers and more. 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: