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 ghostwright · MCP Server · ★ 1.5k
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
🔒 Is phantom safe to install? View the security audit →
Phantom An AI co-worker with its own computer. Website · Get a Free Phantom · Docs · Issues The Idea AI agents today are disposable. You open a chat, get an answer, close the tab, and the context is gone. Next time you start from scratch. Every session is day one. Phantom takes a different approach: give the AI its own computer. A dedicated machine where it installs software, spins up databases, builds dashboards, remembers what you told it last week, and gets measurably better at your job every day. Your laptop stays yours. The agent's workspace is its own. This is not a chatbot. It is a co-worker that runs on Slack, has its own email addre
| Stars | 1,470 |
| Forks | 194 |
| Language | TypeScript |
| Category | MCP Server |
| License | Apache-2.0 |
| Quality Score | 65.835206931614/100 |
| Open Issues | 65 |
| Last Updated | 2026-06-16 |
| Created | 2026-03-26 |
| Platforms | claude-code, docker, mcp, node |
| Est. Tokens | ~19k |
Looking for a phantom alternative? If you're comparing phantom 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 open-source AI coworker for your team: agents with their own cloud computer, your tools and context, handi
everything-claude-code 中文翻译项目：完整的 Claude Code 配置集合（agents, skills, hooks, commands, rules, MCPs）。源自 Anthropic
The Typescript MCP Framework
MaverickMCP - Personal Stock Analysis MCP Server
Safe runtime for autonomous on-chain AI agents: isolated sandboxes, Library skills, encrypted secrets.
비개발자를 위한 한국 실무 AI 코워커 패밀리 — Claude Cowork·ChatGPT Work에서 /project 한 번으로 시작
Explore other popular mcp server tools:
phantom is An AI co-worker with its own computer. Self-evolving, persistent memory, MCP server, secure credential collection, email identity. Built on the Claude Agent SDK.. It is categorized as a MCP Server with 1.5k GitHub stars.
phantom is primarily written in TypeScript. It covers topics such as ai-agents, ai-coworker, anthropic.
You can find installation instructions and usage details in the phantom GitHub repository at github.com/ghostwright/phantom. The project has 1.5k stars and 194 forks, indicating an active community.
phantom is released under the Apache-2.0 license, making it free to use and modify according to the license terms.
The top alternatives to phantom on Agent Skills Hub include useagent, everything-claude-code-zh, mcp-framework. 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: