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 zilliztech · Codex Skill · ★ 119
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
🔒 Is mfs safe to install? View the security audit →
MFS — Multi-source File-like Search A context harness for AI agents — and for building them: one unified workspace over your code, memory, skills, docs, messages, and every data source. <img src="https://img.shields.io/badge/Discord-chat-72
| Stars | 119 |
| Forks | 14 |
| Language | Python |
| Category | Codex Skill |
| License | Apache-2.0 |
| Quality Score | 62.1852793262459/100 |
| Open Issues | 2 |
| Last Updated | 2026-07-31 |
| Created | 2026-04-20 |
| Platforms | claude-code, codex, python |
| Est. Tokens | ~22k |
These tools work well together with mfs for enhanced workflows:
Looking for a mfs alternative? If you're comparing mfs with other codex skill tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.
Structural code intelligence for AI agents — semantic search, knowledge graphs, and a built-in MCP server in o
Local AI-powered document search and editing with first-in-class hybrid retrieval, LLM answers, WebUI, REST AP
An instruction layer for AI coding agent
Local-first persistent agentic memory powered by Recursive Memory Harness (RMH). Open source must win.
DeepContext is an MCP server that adds symbol-aware semantic search to Claude Code, Codex CLI, and other agent
Memory for AI that works like yours—local, instant, persistent. 13x faster than Pinecone, 5x leaner than RAG.
Explore other popular codex skill tools:
mfs is A context harness for AI agents: all your scattered context — code, memory, docs, databases, SaaS — in one searchable, browsable, file-like interface.. It is categorized as a Codex Skill with 119 GitHub stars.
mfs is primarily written in Python. It covers topics such as agent, agent-memory, claude-code.
You can find installation instructions and usage details in the mfs GitHub repository at github.com/zilliztech/mfs. The project has 119 stars and 14 forks, indicating an active community.
mfs is released under the Apache-2.0 license, making it free to use and modify according to the license terms.
The top alternatives to mfs on Agent Skills Hub include octocode, gno, rosetta. 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: