by vitalops · MCP Server · ★ 88
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
pip install 'opendesk[core,mcp]'
npm install @vitalops/opendesk-sdkTaken from the project's README on GitHub. Check the security audit before running it.
Flagged: sudo usage. Scanned against 43 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 | 88 |
| Forks | 18 |
| Language | Python |
| Category | MCP Server |
| License | MIT |
| Quality Score | 68/100 |
| Open Issues | 2 |
| Last Updated | 2026-10-20 |
| Created | 2026-05-07 |
| Platforms | claude-code, mcp, python |
| Est. Tokens | ~16k |
opendesk Give any AI agent eyes and hands on your desktop. Opendesk is a computer use framework that lets AI agents navigate your computer just like a human would — screenshots, mouse, keyboard, UI interaction, OCR, workflow recording, scheduling, and remote machine control.
Looking for a opendesk alternative? If you're comparing opendesk 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.
Daymon puts your favorite AI to work 24/7. It schedules, remembers, and orchestrates your own virtual team. Fr
ToolHive is an application that allows you to install, manage and run MCP servers and connect them to AI agent
MCP server for computer use & browser automation - screenshot, OCR, click, type, find_text, Chrome/Electron C
AI浏览器 MCP Server — Windows 本地浏览器自动化 MCP 服务端 · 334 个工具全量真机核验(0 失败/0 闪退) · Cursor/Claude Code/Claude Desktop/Tra
Lightweight agent orchestration dev tool that lives in your repo
Your own digital life form — local AI companion with persistent memory, IDE workspace, MCP support, and 30+ to
Explore other popular mcp server tools:
Grades come from a rule-based scan built on the SlowMist agent-security taxonomy: 43 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: