by bytedance · MCP Server · ★ 39.2k
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
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. Full audit →
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 | 39,220 |
| Forks | 3,969 |
| Language | TypeScript |
| Category | MCP Server |
| License | Apache-2.0 |
| Quality Score | 69/100 |
| Open Issues | 481 |
| Last Updated | 2026-10-09 |
| Created | 2025-01-19 |
| Platforms | browser, mcp, node |
| Est. Tokens | ~18k |
Introduction English | 简体中文 TARS\ is a Multimodal AI Agent stack, currently shipping two projects: Agent TARS and UI-TARS-desktop: Agent TARS UI-TARS-desktop Agent TARS is a general multimodal AI Agent stack, it brings the power of GUI Agent and Vision into your terminal, computer, browser and product. It primarily ships with a CLI and Web UI for usage.
Looking for a UI-TARS-desktop alternative? If you're comparing UI-TARS-desktop 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.
Open-source Python library for AI browser agents, plus Browser Use Cloud: stealth browsers and a hosted agent
An autonomous agent that conducts deep research on any data using any LLM providers
See interfaces like a human. E2E testing in natural language.
Bytebot is a self-hosted AI desktop agent that automates computer tasks through natural language commands, ope
Mobile MCP: let AI agents drive your iOS and Android apps. MCP server for simulators, emulators and real devic
Build autonomous AI agents in Python.
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: