by ZSeven-W · MCP Server · ★ 129
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 | 129 |
| Forks | 9 |
| Language | TypeScript |
| Category | MCP Server |
| License | MIT |
| Quality Score | 73/100 |
| Last Updated | 2026-10-06 |
| Created | 2026-08-14 |
| Platforms | mcp, node |
| Est. Tokens | ~16k |
DSH Noema Long-term memory for DeepSeek Harness — durable, inspectable agent memory backed by Noema. Recall Before Work • Import From 9 Agent Tools • Settings-Page Memory Management • Crash Keep-Alive • Hot Reload npm: @zseven-w/dsh-noema · Current plugin release: 0.1.0-rc.4 · Tested with DSH 0.1.5-rc.1 English · 简体中文 · 繁體中文 · 日本語 · 한국어 · Français · Español · Deutsch ·...
Looking for a dsh-noema alternative? If you're comparing dsh-noema 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.
Structural memory for AI coding agents. Bi-temporal graph, MCP-native, zero LLM calls. Cursor · Claude Code ·
A portable memory protocol for AI agents — load it as standing rules; a curation discipline + reference spec +
Local-first persistent agentic memory powered by Recursive Memory Harness (RMH). Open source must win.
LLM-supervised persistent memory for AI agents — graph-based recall, cross-session knowledge, single binary. W
Deepseek Harness、Openclaw知识图谱记忆插件。2026年4月受邀发布在清华大学讨论会。Knowledge Graph + Memory；Knowledge Graph Context Engine
Composable mathematics tools for agents
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: