Flagged: sudo usage. Scanned against the SlowMist agent-security taxonomy, refreshed every 8 hours. Full audit →
by pacifio · MCP Server · ★ 4.4k
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
🔒 Is atlas safe to install? View the security audit →
Download · Discord · Docs · Contributing · Issues · Roadmap <img src="https://trendshift.io/api/badge/trendshift/repositories/56020/daily?language=Rust" alt="pacifio%2Fatlas | Tre
| Stars | 4,390 |
| Forks | 273 |
| Language | Rust |
| Category | MCP Server |
| License | MIT |
| Quality Score | 63.7214034651117/100 |
| Open Issues | 24 |
| Last Updated | 2026-09-14 |
| Created | 2026-05-14 |
| Platforms | claude-code, cli, codex, mcp, rust |
| Est. Tokens | ~25k |
These tools work well together with atlas for enhanced workflows:
Looking for a atlas alternative? If you're comparing atlas 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 fullstack MCP framework to develop MCP Apps for ChatGPT / Claude & MCP Servers for AI Agents.
The world's first open-source AI-native vector design tool and the first to feature concurrent Agent Teams. De
One Hub All LLMs For You | 为个人打造的 LLM API 聚合网关
The control plane for AI coding agents.
AI writes code. This automates everything else · 24 plugins · 49 agents · 44 skills · for Claude Code, OpenCod
Lightweight Agent Workstation for Codex CLI + Claude Code — with task scheduler, git worktree & remote control
Explore other popular mcp server tools:
atlas is Source control for agents. Use multiple coding agents, track their changes and query them in one place. It is categorized as a MCP Server with 4.4k GitHub stars.
atlas is primarily written in Rust. It covers topics such as ai, ai-coding-assistant, claude-code.
You can find installation instructions and usage details in the atlas GitHub repository at github.com/pacifio/atlas. The project has 4.4k stars and 273 forks, indicating an active community.
atlas is released under the MIT license, making it free to use and modify according to the license terms.
The top alternatives to atlas on Agent Skills Hub include mcp-use, openpencil, octopus. 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: