by ofershap · MCP Server · ★ 58
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
git clone https://github.com/ofershap/real-browser-mcp.git
npx real-browser-mcp --setup cursorTaken from the project's README on GitHub.
None of the 42 rules matched — no credential harvesting, no data exfiltration, no curl-pipe-shell installer. Scanned against 42 published rules built on the SlowMist agent-security taxonomy, refreshed every 8 hours.
The quality score combines nine heuristic checks of the repo and its README: completeness, clarity, specificity, examples, structure, agent readiness, step-by-step content, instruction quality and security notes. It rates how well the project explains itself to an agent, not the code.
| Stars | 58 |
| Forks | 12 |
| Language | JavaScript |
| Category | MCP Server |
| License | MIT |
| Quality Score | 73/100 |
| Last Updated | 2026-11-02 |
| Created | 2026-03-02 |
| Platforms | browser, claude-code, mcp, node |
| Est. Tokens | ~15k |
real-browser-mcp The missing piece in AI coding: your agent can now see your REAL browser. <a href="https://github.com/ofershap/real-browser-mcp/actions/workflow
Looking for a real-browser-mcp alternative? If you're comparing real-browser-mcp 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.
Anti-detection browser MCP server for AI agents — navigate, interact, and automate the web without getting blo
📜 An MCP server for conversation history search and retrieval in Claude Code
🤖 Taskade MCP · Official MCP server and OpenAPI to MCP codegen. Build AI agent tools from any OpenAPI API and
MCP server for Claude Code/VSCode/Cursor/Windsurf to use editor self functionality. ⚡ Get real-time LSP diagno
🏛 [UNDER CONSTRUCTION] A (roman) claude plugin marketplace
MCP server for YouTube — search videos, get transcripts, channels, and playlists. Works with Claude, Cursor &
Explore other popular mcp server tools:
Grades come from a rule-based scan built on the SlowMist agent-security taxonomy: 42 published rules, covering credential harvesting, data exfiltration, curl | sh installers and more. 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: