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 LvcidPsyche · MCP Server · ★ 765
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
🔒 Is auto-browser safe to install? View the security audit →
Auto Browser Give your AI agent a real browser, with a human in the loop. Auto Browser is an MCP-native browser control plane for authorized workflows. It gives MCP clients, LLM agents, and operators a shared Playwright browser with human takeover, reusable auth profiles, approvals, audit trails, and local-first deployment. Works with: Claude Desktop Cursor any MCP client that can talk HTTP or stdio direct REST callers when you want curl-first control Why Auto Browser MCP-native from day one. The browser surface is already packaged as an MCP server instead of bolted on after the fact. Human takeover when the web gets brittle. noVNC keeps the same live session available when a person needs to step in. Login once, reuse later. Save named auth profiles and reo
| Stars | 765 |
| Forks | 124 |
| Language | Python |
| Category | MCP Server |
| License | MIT |
| Quality Score | 67.113164815462/100 |
| Last Updated | 2026-08-14 |
| Created | 2026-03-09 |
| Platforms | browser, claude-code, docker, mcp, python |
| Est. Tokens | ~15k |
Looking for a auto-browser alternative? If you're comparing auto-browser 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.
Safe runtime for autonomous on-chain AI agents: isolated sandboxes, Library skills, encrypted secrets.
🌐Web Agent Protocol (WAP) - Record and replay user interactions in the browser with MCP support
Local-first personal agentic OS and everything app for coding, knowledge work, web design, automations, and ar
Supercharge AI Agents, Safely
Persistent memory for AI coding agents
c4 GenAI Suite
Explore other popular mcp server tools:
auto-browser is Give your AI agent a real browser — with a human in the loop. Open-source MCP-native browser agent.. It is categorized as a MCP Server with 765 GitHub stars.
auto-browser is primarily written in Python. It covers topics such as ai-agent, ai-agents, browser-automation.
You can find installation instructions and usage details in the auto-browser GitHub repository at github.com/LvcidPsyche/auto-browser. The project has 765 stars and 124 forks, indicating an active community.
auto-browser is released under the MIT license, making it free to use and modify according to the license terms.
The top alternatives to auto-browser on Agent Skills Hub include sandboxed.sh, web-agent-protocol, CoWork-OS. 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: