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 hanzili · MCP Server · ★ 94
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
🔒 Is hanzi-in-chrome safe to install? View the security audit →
English | 中文 Hanzi Browse The context layer for browsing agents. Your browsing agent keeps failing on real sites — X uses Draft.js, LinkedIn hides the connect button, Gmail needs keyboard shortcuts. Hanzi Browse ships 24 site playbooks — hints for the LLM, not brittle scripts — so it actually finishes the task. Works with <img src="https://browse.hanzilla.co/logos/openai-logo-6323x4zd.png" width="24" height="24" alt="Codex" titl
| Stars | 94 |
| Forks | 20 |
| Language | JavaScript |
| Category | MCP Server |
| Quality Score | 69.8800195188294/100 |
| Open Issues | 6 |
| Last Updated | 2026-03-25 |
| Created | 2026-01-24 |
| Platforms | browser, claude-code, mcp, node |
| Est. Tokens | ~6427k |
These tools work well together with hanzi-in-chrome for enhanced workflows:
Looking for a hanzi-in-chrome alternative? If you're comparing hanzi-in-chrome 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.
One command for every interface—search, run, and inspect real software across APIs, browsers, desktops, local
MCP server for computer use & browser automation - screenshot, OCR, click, type, find_text, Chrome/Electron C
让 Agent 直接操作真实 Chrome 的 MCP 服务，支持页面扫描、CDP、截图与物理输入
Native Safari browser automation for AI agents. 98 tools via AppleScript — zero overhead, keeps logins, runs s
Browser-automation agent for Chrome — natural-language tasks executed through native tool calling, scoped Skil
AI-powered annotations for localhost development. Create visual feedback on your apps and let AI coding agents
Explore other popular mcp server tools:
hanzi-in-chrome is any llm browsing for you in chrome. It is categorized as a MCP Server with 94 GitHub stars.
hanzi-in-chrome is primarily written in JavaScript. It covers topics such as ai-agent, browser-automation, chrome.
You can find installation instructions and usage details in the hanzi-in-chrome GitHub repository at github.com/hanzili/hanzi-in-chrome. The project has 94 stars and 20 forks, indicating an active community.
The top alternatives to hanzi-in-chrome on Agent Skills Hub include Uni-CLI, native-devtools-mcp, agent-browser-mcp. 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: