No red flags found in any of the 11 categories — no credential harvesting, no data exfiltration, no curl-pipe-shell installer. Scanned against the SlowMist agent-security taxonomy, refreshed every 8 hours. Full audit →
by bybit-exchange · MCP Server · ★ 137
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
🔒 Is kaas safe to install? View the security audit →
KaaS — Knowledge as a Service English · 中文 Turn scattered notes, documents, and transcripts into a searchable, queryable personal Wiki — powered by LLM-driven knowledge compilation. Why We Built This KaaS started as an internal tool. Our knowledge lived scattered across documents, meetings, and email — and every time someone changed roles or left, the context they'd built up walked out with them. New people spent weeks piecing it back together. A distillation pipeline fixed that. It compiles each person's scattered material into a wiki tied to their role rather than their identity — so when someone moves on, the raw data goes but the distilled judgment stays for whoever fills the seat next. The payoff is the same either way: the organization stops re-answering the same questions. That's what convinced us it was worth open-sourcing. What Makes This Different Unlike typical RAG systems that chunk and embed raw text, KaaS compiles your content through a 4-phase LLM pipeline: The result is human-readable Markdown articles — not a black-box vector store. You can read, edit, and git-manage your knowledge base. Quick Start with your AI agent Alrea
| Stars | 137 |
| Forks | 17 |
| Language | Python |
| Category | MCP Server |
| License | MIT |
| Quality Score | 76.5402905621186/100 |
| Open Issues | 6 |
| Last Updated | 2026-09-11 |
| Created | 2026-07-29 |
| Platforms | claude-code, mcp, python |
| Est. Tokens | ~15k |
These tools work well together with kaas for enhanced workflows:
Looking for a kaas alternative? If you're comparing kaas 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 local-first LLM Wiki: open-source knowledge graph builder, RAG knowledge base, and agent memory store. Bui
LLM-powered knowledge base from your Claude Code, Codex CLI, Copilot, Cursor & Gemini sessions. Karpathy's LLM
The Complete AI Development Toolkit for Claude Code. 106 skills, 36 agents, 171 hooks. Install `ork` for stabl
The leading, most token-efficient MCP server for documentation exploration and retrieval via structured sectio
Local AI-powered document search and editing with first-in-class hybrid retrieval, LLM answers, WebUI, REST AP
🏛 [UNDER CONSTRUCTION] A (roman) claude plugin marketplace
Explore other popular mcp server tools:
kaas is Turn scattered notes, docs and transcripts into a queryable Markdown wiki — an LLM knowledge-base compiler with MCP access, no embeddings, self-hosted.. It is categorized as a MCP Server with 137 GitHub stars.
kaas is primarily written in Python. It covers topics such as ai-agents, claude-code, golang.
You can find installation instructions and usage details in the kaas GitHub repository at github.com/bybit-exchange/kaas. The project has 137 stars and 17 forks, indicating an active community.
kaas is released under the MIT license, making it free to use and modify according to the license terms.
The top alternatives to kaas on Agent Skills Hub include swarmvault, llm-wiki, orchestkit. Each offers a different approach to the same problem space — compare them side-by-side by stars, quality score, and community activity.
Grades come from a rule-based scan built on the SlowMist agent-security taxonomy, covering 11 red-flag categories including credential harvesting, data exfiltration, and curl | sh installers. 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: