awesome-claude-dxt: Awesome Claude Desktop Extensions (dxt) (not only Claude) mcpb

Security audit verdict: SAFE · quality 60/100

None of the 42 rules matched — no credential harvesting, no data exfiltration, no curl-pipe-shell installer. Scanned against 42 published rules built on the SlowMist agent-security taxonomy, refreshed every 8 hours.

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.

Quick Facts

About awesome-claude-dxt

Awesome Claude dxt A curated list of awesome (not only Claude) Desktop Extensions, tools, and resources What is DXT dxt is Desktop Extensions: One-click MCP server installation for Claude Desktop and other Desktop apps [!TIP] ⭐ Star the repo and follow milisp on X and github for more.

Compatible Skills

These tools work well together with awesome-claude-dxt for enhanced workflows:

• claude-cowork-linux — semantic(0.21)+complementary+same_lang+similar_pop+shared_platform (52%)
• AbsolutelySkilled — semantic(0.16)+complementary+same_lang+similar_pop+shared_platform (51%)
• awesome-agent-skills — semantic(0.27)+complementary+similar_pop+shared_platform (50%)
• awesome-claude — semantic(0.36)+complementary+similar_pop+shared_platform (48%)
• awesome-claude-code — semantic(0.34)+complementary+similar_pop+shared_platform (47%)

awesome-claude-dxt alternative? Top 6 similar tools

Looking for a awesome-claude-dxt alternative? If you're comparing awesome-claude-dxt 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.

• ollama-mcp by rawveg · ⭐ 176

  An MCP Server for Ollama

• golf by golf-mcp · ⭐ 840

  Production-Ready MCP Server Framework • Build, deploy & scale secure AI agent infrastructure • Includes Auth,

• awesome-mcp-security by Puliczek · ⭐ 738

  🔥🔒 Awesome MCP (Model Context Protocol) Security 🖥️

• wcgw by rusiaaman · ⭐ 674

  Shell and coding agent on mcp clients

• gram by speakeasy-api · ⭐ 277

  The AI control plane for every agent in your enterprise, built around an enterprise-grade MCP gateway. Give ea

• claudepro-directory by JSONbored · ⭐ 217

  HeyClaude (formerly Claude Pro Directory) is a searchable collection of pre-built AI skills, agents, MCP serve

More MCP Server Tools

Explore other popular mcp server tools:

• n8n ⭐ 209.6k
• gemini-cli ⭐ 108.7k
• awesome-mcp-servers ⭐ 97.2k
• TrendRadar ⭐ 63.5k
• context7 ⭐ 64.2k
• UI-TARS-desktop ⭐ 39.2k
• chrome-devtools-mcp ⭐ 54.8k
• github-mcp-server ⭐ 34.2k
• gpt-researcher ⭐ 30.0k
• Scrapling ⭐ 97.0k

Popular JavaScript Agent Tools

• XHS-Downloader ⭐ 13.2k · MCP Server
• xiaozhi-esp32-server ⭐ 11.2k · MCP Server
• firecrawl-mcp-server ⭐ 7.8k · MCP Server
• deep-research ⭐ 4.7k · MCP Server
• brightdata-mcp ⭐ 2.7k · MCP Server

How this security grade is produced

Grades come from a rule-based scan built on the SlowMist agent-security taxonomy: 42 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:

• SlowMist agent-security taxonomy
• Liu et al., An Empirical Study of Agent Skill Security (2026)
• Our census dataset (DOI 10.5281/zenodo.21292799) · Hugging Face mirror
• How we grade: all 42 rules, the source tiers and known limits
• Full methodology & who runs this