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 alchaincyf · MCP Server · ★ 257
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
🔒 Is huashu-chrome safe to install? View the security audit →
huashu-chrome 「工具返回『已点击』不算数，页面真的动了才算。」 让任何 AI agent 操控你自己的 Chrome——带着你全部的登录态。 一个 MCP server + 一个 Chrome 扩展，22 个浏览器工具。Claude Code、Codex CLI、Cursor、Gemini CLI、Cline、Windsurf 通用。 看效果 · 安装 · 22 个工具 · 经验回流 · 安全 · 排错 不用 API key，不用重新登录，不用处理验证码——用的就是你此刻这个浏览器里的身份。 「npm 包？插件？CLI？还是 MCP？」——都是。它们是同一个产品的五个器官：npm 包是分发载体， CLI 是入口（install / mcp / doctor），MCP server 是 agent 的接口，本地桥是 127.0.0.1 上的 常驻路由器，Chrome 扩展是手。上图就是一条命令穿过它们的全程。 图解版完整说明书 → huasheng.ai/huashu-chrome 看效果 装上之后，你在 agent 里说的是这种话： 「查一下这本书在京东有几家在卖，评价怎么样」 「把这篇稿子发到小红书，配这 9 张图，明早 7:30 定时发」 「这个 B 站 UP 主最近 30 条视频的播放和字幕全拉下来」 「明天武汉到上海的高铁还有没有二等座，顺便告诉我票价」 「把这份表格里的记
| Stars | 257 |
| Forks | 38 |
| Language | JavaScript |
| Category | MCP Server |
| License | MIT |
| Quality Score | 58.3691957436363/100 |
| Open Issues | 2 |
| Last Updated | 2026-09-26 |
| Created | 2026-08-26 |
| Platforms | browser, claude-code, cli, codex, gemini, mcp, node |
| Est. Tokens | ~18k |
Explore other popular mcp server tools:
huashu-chrome is 让任何 AI agent 操控你自己的 Chrome——带着全部登录态。MCP + Chrome 扩展，Claude Code / Codex / Cursor / Gemini CLI 通用。. It is categorized as a MCP Server with 257 GitHub stars.
huashu-chrome is primarily written in JavaScript.
You can find installation instructions and usage details in the huashu-chrome GitHub repository at github.com/alchaincyf/huashu-chrome. The project has 257 stars and 38 forks, indicating an active community.
huashu-chrome is released under the MIT license, making it free to use and modify according to the license terms.
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: