computer-use-linux — security grade SAFE, quality 67/100

Security audit verdict: SAFE · quality 67/100

Flagged: sudo usage. Scanned against the SlowMist agent-security taxonomy, refreshed every 8 hours. Full audit →

by agent-sh · MCP Server · ★ 540

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

🔒 Is computer-use-linux safe to install? View the security audit →

About computer-use-linux

computer-use-linux Control a real Linux desktop from any MCP host. reads accessibility trees, takes screenshots, and drives clicks, scrolls, and keystrokes across GNOME, KDE/KWin, Hyprland, i3, and COSMIC — Wayland-first, X11 best-effort. The Rust crate is published as and the npm wrapper as . Prebuilt binaries ship with the latest release. What this is is a Rust MCP server and CLI for Linux desktop control. The crate ships the main co

agentaicargoclaudecodexcomputer-usegnomehermeslinuxllm

Quick Facts

Stars540
Forks57
LanguageRust
CategoryMCP Server
LicenseMIT
Quality Score67.1421664662391/100
Open Issues2
Last Updated2026-09-14
Created2026-05-13
Platformsclaude-code, codex, mcp, rust
Est. Tokens~29k

Compatible Skills

These tools work well together with computer-use-linux for enhanced workflows:

  • BitFun — semantic(0.22)+complementary+same_lang+similar_pop+shared_platform (53%)
  • computer-agent — semantic(0.19)+complementary+same_lang+similar_pop+shared_platform (52%)

computer-use-linux alternative? Top 6 similar tools

Looking for a computer-use-linux alternative? If you're comparing computer-use-linux 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-computer-use by e2b-dev · ⭐ 2.2k

    AI computer use powered by open source LLMs and E2B Desktop Sandbox

  • tuui by AI-QL · ⭐ 1.2k

    A desktop MCP client designed as a tool unitary utility integration, accelerating AI adoption through the Mode

  • 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

  • wcgw by rusiaaman · ⭐ 674

    Shell and coding agent on mcp clients

  • ClaudeR by IMNMV · ⭐ 337

    Connect RStudio to Claude Code, Codex, Gemini, and other LLM agents via MCP. Multi-agent orchestration, automa

  • rust-docs-mcp-server by Govcraft · ⭐ 291

    🦀 Prevents outdated Rust code suggestions from AI assistants. This MCP server fetches current crate docs, use

More MCP Server Tools

Explore other popular mcp server tools:

View all MCP Server tools →

Popular Rust Agent Tools

Frequently Asked Questions

What is computer-use-linux?

computer-use-linux is Linux desktop control over MCP — AT-SPI, GNOME Shell, Wayland portals, ydotool. It is categorized as a MCP Server with 540 GitHub stars.

What programming language is computer-use-linux written in?

computer-use-linux is primarily written in Rust. It covers topics such as agent, ai, cargo.

How do I install or use computer-use-linux?

You can find installation instructions and usage details in the computer-use-linux GitHub repository at github.com/agent-sh/computer-use-linux. The project has 540 stars and 57 forks, indicating an active community.

What license does computer-use-linux use?

computer-use-linux is released under the MIT license, making it free to use and modify according to the license terms.

What are the best alternatives to computer-use-linux?

The top alternatives to computer-use-linux on Agent Skills Hub include open-computer-use, tuui, open-computer-use. 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