dsh-desktop — security grade SAFE, quality 60/100

Security audit verdict: SAFE · quality 60/100

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 vibeinging · MCP Server · ★ 587

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

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

About dsh-desktop

DSH Desktop 以官方 DSH Web 为核心的插件化桌面工作台。 精选社区 Bundle、离线 Profile、Git Worktree、文件附件与受控原生能力,组合在一个 Electron 应用中。 独立的社区开源项目,与深度求索不存在隶属、合作、授权或背书关系。中文 · English · 二次元版 README DSH Desktop 是社区维护的 Electron 发行版。它固定并运行官方 DeepSeek Harness npm 运行时,把 、Session、Agent、To

agentic-workflowsai-agentai-workbenchdata-analysisdeepseek-harnessdesktop-appdshdsh-pluginelectronlocal-first

Quick Facts

Stars587
Forks35
LanguageJavaScript
CategoryMCP Server
LicenseMIT
Quality Score59.7844771961016/100
Open Issues5
Last Updated2026-09-15
Created2026-08-13
Platformsbrowser, mcp, node
Est. Tokens~16k

Compatible Skills

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

  • dsh-find-plugins — semantic(0.41)+complementary+same_lang+similar_pop+shared_platform (64%)
  • dsh-chat-import — semantic(0.39)+complementary+same_lang+similar_pop+shared_platform (64%)
  • dsh-router-standard — semantic(0.36)+complementary+same_lang+similar_pop+shared_platform (63%)
  • dsh-anchored-standard — semantic(0.35)+complementary+same_lang+similar_pop+shared_platform (62%)
  • SenseNova-Skills — semantic(0.21)+complementary+rare_topics+same_lang+similar_pop+shared_platform (62%)

dsh-desktop alternative? Top 6 similar tools

Looking for a dsh-desktop alternative? If you're comparing dsh-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.

  • wesight by freestylefly · ⭐ 893

    Open-source desktop AI agent workspace with one-click Claude Code, Codex, OpenClaw, Hermes Agent setup and cus

  • Abu-Cowork by PM-Shawn · ⭐ 376

    Open-source alternative to Claude Cowork — a local-first AI agent desktop app · multi-model · self-evolving sk

  • cetus by drewnekota · ⭐ 143

    One macOS app for Claude Code, Codex, and every agent runtime you use — scheduled runs, global hotkey launcher

  • CaoGen by opengenesishq · ⭐ 121

    CaoGen — a vendor-neutral, local-first AI work desktop. Multi-provider agent runtime, GUI automation, MCP, Git

  • pawwork by Astro-Han · ⭐ 183

    PawWork — free, open-source desktop AI agent for macOS and Windows, built on DeepSeek Harness (DSH). Free mode

  • memtrace-public by syncable-dev · ⭐ 472

    Structural memory for AI coding agents. Bi-temporal graph, MCP-native, zero LLM calls. Cursor · Claude Code ·

More MCP Server Tools

Explore other popular mcp server tools:

View all MCP Server tools →

Popular JavaScript Agent Tools

Frequently Asked Questions

What is dsh-desktop?

dsh-desktop is DeepSeek Harness Desktop App: a local AI desktop workspace for DSH Sessions, projects, files, web research, plugins, and Office artifacts.. It is categorized as a MCP Server with 587 GitHub stars.

What programming language is dsh-desktop written in?

dsh-desktop is primarily written in JavaScript. It covers topics such as agentic-workflows, ai-agent, ai-workbench.

How do I install or use dsh-desktop?

You can find installation instructions and usage details in the dsh-desktop GitHub repository at github.com/vibeinging/dsh-desktop. The project has 587 stars and 35 forks, indicating an active community.

What license does dsh-desktop use?

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

What are the best alternatives to dsh-desktop?

The top alternatives to dsh-desktop on Agent Skills Hub include wesight, Abu-Cowork, cetus. 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