by achiya-automation · MCP Server · ★ 232
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
Featured in: browser-use, Playwright MCP & AI Browser Agents
npx safari-mcp
npm install -g safari-mcpTaken 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 | 232 |
| Forks | 35 |
| Language | JavaScript |
| Category | MCP Server |
| License | MIT |
| Quality Score | 79/100 |
| Open Issues | 25 |
| Last Updated | 2026-11-03 |
| Created | 2026-03-18 |
| Platforms | browser, claude-code, mcp, node |
| Est. Tokens | ~20k |
🦁 Safari MCP The browser for your coding agent. Your real Safari, logged in — no Chrome, no heat, no headless. <img src="https://img.shields.io/badge/VSCode-InstallServer-0078d4?logo=visual-studio-code&logoColor=white" alt="Ins
These tools work well together with safari-mcp for enhanced workflows:
Looking for a safari-mcp alternative? If you're comparing safari-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.
MCPSafari: Native Safari MCP Server for AI Agents
The browser tool that can stop and ask you. A 2FA code, a CAPTCHA, a choice only you can make: it asks on your
let any ai agent use the local browser
Sync MCP servers, Skills, Agents & Commands across Claude Code, Cursor, OpenCode, Codex. One config, all tools
Anti-detection browser MCP server for AI agents — navigate, interact, and automate the web without getting blo
🏛 [UNDER CONSTRUCTION] A (roman) claude plugin marketplace
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: