by kejixiaoliang · MCP Server · ★ 64
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 | 64 |
| Forks | 60 |
| Language | JavaScript |
| Category | MCP Server |
| License | MIT |
| Quality Score | 57/100 |
| Open Issues | 37 |
| Last Updated | 2026-10-22 |
| Created | 2026-08-13 |
| Platforms | mcp, node |
| Est. Tokens | ~25k |
🐋 Awesome DeepSeek Harness Plugins A curated directory of 280+ DeepSeek Harness () plugins across 14 categories — every entry with ⭐ stars and a command. Bilingual (EN + 中文), machine-readable data, auto-sync CI.
Looking for a awesome-dsh-plugins alternative? If you're comparing awesome-dsh-plugins 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.
🐋 DeepSeek Harness 插件总目录 · The catalog of DSH plugins：1958 个仓库 / 1819 个真插件（Skills · MCP · Tools · UI · Orches
Persistent multi-model workflow teams for DeepSeek Harness — dynamic lead planning, bounded DAGs, per-agent mo
MCP management console for the official DeepSeek Harness MCP client: /mcp command with health diagnostics and
DeepSeek Harness (dsh) plugin development knowledge base: the 10-chapter development guide, release playbook,
Unofficial DSH (DeepSeek Harness) plugin: use chat.deepseek.com web models as an LLM provider - browser-login
Use your ChatGPT Plus / Pro (Codex) subscription in DeepSeek Harness (DSH): GPT-6 & Codex models, images, web
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: