by cobusgreyling · MCP Server · ★ 46
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
Featured in: Knowledge Base & RAG
None of the 44 rules matched — no credential harvesting, no data exfiltration, no curl-pipe-shell installer. Scanned against 44 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 | 46 |
| Forks | 8 |
| Language | Python |
| Category | MCP Server |
| License | MIT |
| Quality Score | 70/100 |
| Last Updated | 2026-07-06 |
| Created | 2026-07-03 |
| Platforms | mcp, python |
| Est. Tokens | ~15k |
A compounding knowledge base maintained by LLM agents — inspired by Karpathy's LLM Wiki pattern
Looking for a llm-wiki alternative? If you're comparing llm-wiki 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.
Notion MCP server with token auth: connect Claude Code, Claude Desktop, Cursor, VS Code and Codex to Notion pa
A Model Context Protocol (MCP) server that implements the Zettelkasten knowledge management methodology, allow
Local-first AI PKM for coding conversations: import Claude Code/Cursor/Codex, distill notes, semantic search,
Architecture-first skill lifecycle for AI agents. BinEval binary scoring with threshold-blind, cross-family-ca
The World's Most Comprehensive, Authoritative, and Structured Open Source Data Source Knowledge Base
Build Karpathy's LLM Wiki with Claude Code. L1/L2 cache architecture. Logseq + Obsidian support.
Explore other popular mcp server tools:
Grades come from a rule-based scan built on the SlowMist agent-security taxonomy: 44 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: