by iii-hq · MCP Server · ★ 104
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.
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 | 104 |
| Forks | 14 |
| Language | TypeScript |
| Category | MCP Server |
| License | Apache-2.0 |
| Quality Score | 72/100 |
| Last Updated | 2026-04-03 |
| Created | 2026-03-01 |
| Platforms | mcp, node |
| Est. Tokens | ~90k |
The agent OS that evolves itself. Three primitives. 51 workers. Agents that write, test, and improve their own functions at runtime. Built on iii-engine — 18% overhead vs raw function calls. Website · Quickstart · Why AgentOS · Architecture · Intelligence · GitHub bash curl -fsSL https
These tools work well together with agentos for enhanced workflows:
Looking for a agentos alternative? If you're comparing agentos 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 agent OS that evolves itself. 51 workers, 18 security layers, self-improving functions. Built on iii-engin
A curated list of AI Agent evolution, memory systems, multi-agent architectures, and self-improvement projects
Aser is a lightweight, self-assembling AI Agent frame.
Polymcp provides a simple and efficient way to interact with MCP servers using custom agents
Open source AI coding platform with Web IDE, multi-agent system, 37+ tools, MCP protocol. MIT licensed.
Production-ready Next.js template for building AI agents with LangGraph.js. Features MCP integration for dynam
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: