agent-desktop — security grade SAFE, quality 67/100

Security audit verdict: SAFE · quality 67/100

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 lahfir · MCP Server · ★ 1.3k

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

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

About agent-desktop

AGENT DESKTOP OBSERVE. DECIDE. ACT. agent-desktop is a native desktop automation CLI designed for AI agents, built with Rust. It gives structured access to any application through OS accessibility trees — no screens

accessibilityaccessibility-apiai-agentsautomationclicomputer-usecomputer-use-agentcomputer-use-agentsdesktop-automationmacos

Quick Facts

Stars1,324
Forks87
LanguageRust
CategoryMCP Server
LicenseApache-2.0
Quality Score67.0341816624874/100
Open Issues22
Last Updated2026-09-17
Created2026-02-19
Platformscli, mcp, rust
Est. Tokens~27k

Compatible Skills

These tools work well together with agent-desktop for enhanced workflows:

  • tsk-tsk — semantic(0.18)+complementary+same_lang+similar_pop+shared_platform (56%)
  • desktopctl — semantic(0.41)+complementary+same_lang+shared_platform (54%)
  • agent-browser — semantic(0.34)+complementary+same_lang+shared_platform (52%)

agent-desktop alternative? Top 6 similar tools

Looking for a agent-desktop alternative? If you're comparing agent-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-codex-computer-use by iFurySt · ⭐ 2.1k

    👾 Open Computer Use – Open-Source Alternative to Codex Computer Use

  • ghost-os by ghostwright · ⭐ 1.7k

    Full computer-use for AI agents. Self-learning workflows. Native macOS. No screenshots required.

  • TuriX-CUA by TurixAI · ⭐ 3.2k

    This is the official website for TuriX Computer-use-Agent

  • OpenAdapt by OpenAdaptAI · ⭐ 1.7k

    Compile a demonstrated GUI workflow into a deterministic, locally executable program. Zero model calls on heal

  • open-computer-use by coasty-ai · ⭐ 763

    State of the Art 82% OSWorld Computer Using Agent, production-ready. Remote and Local! Setup using one API Key

  • Agent by macOS26 · ⭐ 562

    Agent! Is a native macOS App that works with any LLM [local and cloud], [open source and paid] Claude, OpenAI,

More MCP Server Tools

Explore other popular mcp server tools:

View all MCP Server tools →

Popular Rust Agent Tools

Frequently Asked Questions

What is agent-desktop?

agent-desktop is Agent Desktop gives any agent reliable computer use on the desktop. Built with Rust, it sees any app's real UI structure through OS accessibility trees and operates it — refs stay stable and actions s. It is categorized as a MCP Server with 1.3k GitHub stars.

What programming language is agent-desktop written in?

agent-desktop is primarily written in Rust. It covers topics such as accessibility, accessibility-api, ai-agents.

How do I install or use agent-desktop?

You can find installation instructions and usage details in the agent-desktop GitHub repository at github.com/lahfir/agent-desktop. The project has 1.3k stars and 87 forks, indicating an active community.

What license does agent-desktop use?

agent-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 agent-desktop?

The top alternatives to agent-desktop on Agent Skills Hub include open-codex-computer-use, ghost-os, TuriX-CUA. 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