UI-TARS-desktop — security grade SAFE, quality 69/100

Security audit verdict: SAFE · quality 69/100

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 bytedance · MCP Server · ★ 38.9k

Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h

🔒 Is UI-TARS-desktop safe to install? View the security audit →

About UI-TARS-desktop

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. It aims to provide a workflow that is closer to human-like task completion through cutting-edge mu

agentagent-tarsbrowser-usecomputer-usecoworkgui-agentgui-operatormcpmcp-servermultimodal

Quick Facts

Stars38,933
Forks3,937
LanguageTypeScript
CategoryMCP Server
LicenseApache-2.0
Quality Score68.7429440435133/100
Open Issues444
Last Updated2026-09-11
Created2025-01-19
Platformsbrowser, mcp, node
Est. Tokens~18k

UI-TARS-desktop alternative? Top 6 similar tools

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.

  • gpt-researcher by assafelovic · ⭐ 29.2k

    An autonomous agent that conducts deep research on any data using any LLM providers

  • midscene by web-infra-dev · ⭐ 15.0k

    GUI Agent for E2E Testing

  • bytebot by bytebot-ai · ⭐ 11.1k

    Bytebot is a self-hosted AI desktop agent that automates computer tasks through natural language commands, ope

  • Upsonic by Upsonic · ⭐ 8.0k

    Build autonomous AI agents in Python.

  • Scrapling by D4Vinci · ⭐ 83.2k

    🕷️ An adaptive Web Scraping framework that handles everything from a single request to a full-scale crawl! Do

  • context7 by upstash · ⭐ 62.4k

    Context7 Platform -- Up-to-date code documentation for LLMs and AI code editors

More MCP Server Tools

Explore other popular mcp server tools:

View all MCP Server tools →

Popular TypeScript Agent Tools

Frequently Asked Questions

What is UI-TARS-desktop?

UI-TARS-desktop is The Open-Source Multimodal AI Agent Stack: Connecting Cutting-Edge AI Models and Agent Infra. It is categorized as a MCP Server with 38.9k GitHub stars.

What programming language is UI-TARS-desktop written in?

UI-TARS-desktop is primarily written in TypeScript. It covers topics such as agent, agent-tars, browser-use.

How do I install or use UI-TARS-desktop?

You can find installation instructions and usage details in the UI-TARS-desktop GitHub repository at github.com/bytedance/UI-TARS-desktop. The project has 38.9k stars and 3937 forks, indicating an active community.

What license does UI-TARS-desktop use?

UI-TARS-desktop is released under the Apache-2.0 license, making it free to use and modify according to the license terms.

What are the best alternatives to UI-TARS-desktop?

The top alternatives to UI-TARS-desktop on Agent Skills Hub include gpt-researcher, midscene, bytebot. Each offers a different approach to the same problem space — compare them side-by-side by stars, quality score, and community activity.

How this security grade is produced

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:

View on GitHub → Browse MCP Server tools