by ayingQAQ · MCP Server · ★ 54
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 | 54 |
| Forks | 1 |
| Language | TypeScript |
| Category | MCP Server |
| License | MIT |
| Quality Score | 61/100 |
| Last Updated | 2026-10-22 |
| Created | 2026-10-21 |
| Platforms | mcp, node |
| Est. Tokens | ~15k |
McCosmos · 麦门星图 把日常的一口，装进小小宇宙。浅色卡通绘本风的麦当劳营养探索应用，让餐品变成星球，用营养透镜发现彼此的连接。 适合想直观看懂餐品营养、喜欢交互图鉴的用户，以及复用 MCP 分析能力的 Agent 开发者。独立参赛作品，非麦当劳官方产品；信息以官方渠道为准。 在线探索 · Actions 与静态包 · 实际 MCP 接入 · Skill · 实施记录 2.0 新增五个互通的探索站：观测站 → 营养星系 → 星球图鉴 → 实验室 → 探索任务。交互路径与验收记录见 USERJOURNEYS。 食物星球与真实商品照片 宇宙使用奶油纸色、麦当劳红与暖金色。卡通餐品图案附在...
Looking for a McCosmos alternative? If you're comparing McCosmos 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.
Agent Ops for your second brain - a 3D IDE for Obsidian built on Three.js. Visualize your vault as a code city
A remote MCP server for personal nutrition tracking — log meals, track macros, and review nutrition history th
Local-First Open Source web & mobile AI app builder — install on MacOS, Windows & Linux
Connects MCP to major 3D printer APIs (Orca, FULU's Orca/Bambu, OctoPrint, Klipper, Duet, Repetier, Prusa, Cre
** THIS REPO HAS MOVED TO https://github.com/langchain-ai/langchainjs/tree/main/libs/langchain-mcp-adapters **
Open-source platform for 3D AI agents. Turn text or a photo into a rigged, animated GLB avatar, give it an LLM
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: