SkillHub MCP
Enables AI assistants to search, discover, and get recommendations from 20,000+ skills, tools, agents, rules, and MCP servers.
README
⚡ SkillHub MCP
AI Resource Intelligence — Find the right tool for any AI task.
Search, discover, and get recommendations from 20,000+ skills, tools, agents, rules, and MCP servers — all from your terminal or AI client.
Quick Start
1. Setup (30 seconds)
npx skillhub-mcp setup
This auto-detects your installed AI clients (Codex, Claude, Cursor, Windsurf) and configures them automatically.
2. Restart your AI client
3. Done!
Your AI assistant can now discover and recommend tools. Try asking it:
"What tools should I use to build a RAG pipeline with LangChain?"
CLI Usage
SkillHub also works as a standalone CLI — no MCP client required.
Recommend tools for a task
npx skillhub-mcp recommend "build a REST API with authentication"
Output:
#1 Express.js ✓ 9.2
Fast, unopinionated web framework for Node.js
tool · cross-platform · expressjs
→ matches technologies: express, node; relevant to: api, coding
#2 Passport.js 8.8
Authentication middleware for Node.js
tool · cross-platform · jaredhanson
→ matches technologies: node; relevant to: authentication
Search resources
npx skillhub-mcp search "vector database"
Get resource details
npx skillhub-mcp info "LangChain"
Database statistics
npx skillhub-mcp stats
JSON output
All data commands support --json for piping and scripting:
npx skillhub-mcp recommend "kubernetes" --json | jq '.results[0]'
npx skillhub-mcp stats --json
MCP Tools
When connected to an AI client, SkillHub exposes these tools:
| Tool | Description |
|---|---|
recommend |
Analyze a task and recommend relevant resources |
search |
Search 20,000+ resources by keyword |
get_resource |
Get full details for a specific resource |
get_setup_guide |
Get install instructions for any resource |
analyze_stack |
Recommend tools based on your tech stack |
Security & Trust
This package is designed to be safe and auditable.
- ✅ Fully offline — zero network requests, no HTTP calls, no telemetry
- ✅ Zero runtime dependencies — self-contained bundle, nothing from
node_modules - ✅ No install scripts — no
postinstall, no code runs onnpm install - ✅ No eval — no
eval(),new Function(), or dynamic code execution - ✅ No shell access — no
exec(),spawn(), orchild_processusage - ✅ Filesystem access only in setup wizard — writes MCP client configs when you explicitly run
setup
See SECURITY.md for full details on runtime behavior and filesystem access.
Diagnostics
npx skillhub-mcp doctor
Checks Node.js version, npx path resolution, database loading, and MCP client configuration status.
Manual Client Setup
If the setup wizard doesn't work for your client, generate the config manually:
npx skillhub-mcp print-config codex # Codex (TOML)
npx skillhub-mcp print-config claude # Claude Desktop (JSON)
npx skillhub-mcp print-config cursor # Cursor (JSON)
npx skillhub-mcp print-config windsurf # Windsurf (JSON)
Important: The setup wizard uses absolute paths for
npx(e.g.,/opt/homebrew/bin/npx). GUI applications often don't inherit your shell's PATH.
Requirements
- Node.js 18+
- npm / npx
License
MIT
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。