by Epistates · MCP Server · ★ 62
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
brew install --cask epistates/tap/mcp-safari
git clone https://github.com/Epistates/MCPSafari.gitTaken 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 | 62 |
| Forks | 7 |
| Language | JavaScript |
| Category | MCP Server |
| License | MIT |
| Quality Score | 75/100 |
| Last Updated | 2026-10-26 |
| Created | 2026-03-23 |
| Platforms | browser, claude-code, mcp, node |
| Est. Tokens | ~17k |
MCPSafari: Native Safari MCP Server for AI Agents Give Claude, Cursor, or any MCP-compatible AI full native control of Safari on macOS. Navigate tabs, click/type/fill forms (even React), read HTML/accessibility trees, execute JS, capture screenshots, inspect console & network — all with 23 secure tools.
Looking for a MCPSafari alternative? If you're comparing MCPSafari 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.
Native Safari browser automation for AI agents. 98 tools via AppleScript — zero overhead, keeps logins, runs s
🚀 MCP aggregator for batching multiple tool calls into a single request. Reduces overhead, saves tokens, and
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 Claude Code and other coding agents drive and debug Chrome from the shell. DOM, network, console and raw C
let any ai agent use the local browser
Anti-detection browser MCP server for AI agents — navigate, interact, and automate the web without getting blo
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: