Cover image

Smithery CLI MCP服务器安装程序

3 years

Works with Finder

2

Github Watches

29

Github Forks

219

Github Stars

Smithery CLI NPM Version NPM Downloads

The Smithery registry installer and manager for Model Context Protocol (MCP) servers, designed to be client-agnostic.

Requirements

  • NodeJS version 18 or above

Usage

npx @smithery/cli <command>

Available Commands

  • install <package> - Install a package
    • --client <name> - Specify the AI client
    • --config <json> - Provide configuration data as JSON (skips prompts)
  • uninstall <package> - Uninstall a package
    • --client <name> - Specify the AI client
  • inspect <server-id> - Inspect a server interactively
  • run <server-id> - Run a server
    • --config <json> - Provide configuration for the server
  • list clients - List available clients
  • list servers --client <name> - List installed servers for specific AI client
  • --help - Show help message
  • --verbose - Show detailed logs for debugging

Examples

# Install a server (requires --client flag)
npx @smithery/cli install mcp-obsidian --client claude

# Install a server with pre-configured data (skips prompts)
npx @smithery/cli install mcp-obsidian --client claude --config '{"vaultPath":"path/to/vault"}'

# Remove a server
npx @smithery/cli uninstall mcp-obsidian --client claude

# List available clients
npx @smithery/cli list clients

# List installed servers for claude
npx @smithery/cli list servers --client claude

# Inspect a specific server from smithery's registry
npx @smithery/cli inspect mcp-obsidian

# Run a server with configuration
npx @smithery/cli run mcp-obsidian --config '"{\\"key\\":\\"value\\"}"'

# Show help menu
npx @smithery/cli --help

# Install with verbose logging for debugging
npx @smithery/cli install mcp-obsidian --client claude --verbose

Important Notes

  • Remember to restart your AI client after installing or uninstalling servers
  • Use the inspect command for interactive server testing
  • Run without arguments to see the help menu
  • Use --verbose flag for detailed logs when troubleshooting

Development

This guide will help you get started with developing for @smithery/cli.

Getting Started

  1. Clone the repository:

    git clone https://github.com/smithery-ai/cli
    cd cli
    
  2. Install dependencies:

    npm install
    
  3. Build the project:

    npm run build
    

Development Commands

# List all servers
npx . <command>

# Inspect a specific server
npx . inspect <server-id>

# Install a server
npx . install <server-name> --client <client-name>

# Run with verbose logging
npx . <command> --verbose

Contributing

Contributions are welcome! Please feel free to submit a Pull Request.

相关推荐

  • Joshua Armstrong
  • Confidential guide on numerology and astrology, based of GG33 Public information

  • Emmet Halm
  • Converts Figma frames into front-end code for various mobile frameworks.

  • Elijah Ng Shi Yi
  • Advanced software engineer GPT that excels through nailing the basics.

  • https://maiplestudio.com
  • Find Exhibitors, Speakers and more

  • Alexandru Strujac
  • Efficient thumbnail creator for YouTube videos

  • https://zenepic.net
  • Embark on a thrilling diplomatic quest across a galaxy on the brink of war. Navigate complex politics and alien cultures to forge peace and avert catastrophe in this immersive interstellar adventure.

  • 林乔安妮
  • A fashion stylist GPT offering outfit suggestions for various scenarios.

  • pontusab
  • 光标与风浪冲浪社区,查找规则和MCP

  • av
  • 毫不费力地使用一个命令运行LLM后端,API,前端和服务。

  • 1Panel-dev
  • 🔥1Panel提供了直观的Web接口和MCP服务器,用于在Linux服务器上管理网站,文件,容器,数据库和LLMS。

  • GeyserMC
  • 与Minecraft客户端/服务器通信的库。

  • Mintplex-Labs
  • 带有内置抹布,AI代理,无代理构建器,MCP兼容性等的多合一桌面和Docker AI应用程序。

  • awslabs
  • AWS MCP服务器 - 将AWS最佳实践直接带入您的开发工作流程的专门MCP服务器

  • WangRongsheng
  • 🧑‍🚀 llm 资料总结(数据处理、模型训练、模型部署、 o1 模型、mcp 、小语言模型、视觉语言模型)|摘要世界上最好的LLM资源。

  • appcypher
  • 很棒的MCP服务器 - 模型上下文协议服务器的策划列表

  • chongdashu
  • 使用模型上下文协议(MCP),启用Cursor,Windsurf和Claude Desktop等AI助手客户,以通过自然语言控制虚幻引擎。

  • GLips
  • MCP服务器向像光标这样的AI编码代理提供FIGMA布局信息

    Reviews

    2 (1)
    Avatar
    user_Q0JCMN2v
    2025-04-17

    As a loyal MCP application user, I strongly recommend the CLI by smithery-ai. This tool has streamlined my workflow significantly with its powerful features and user-friendly interface. The comprehensive documentation available at https://github.com/smithery-ai/cli made it easy to get started and integrate into my projects. Overall, an excellent product for any developer looking to enhance their productivity.