MCP cover image

Smithery CLI MCP Server Installer

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

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

  • 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.

  • lumpenspace
  • Take an adjectivised noun, and create images making it progressively more adjective!

  • 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.

  • Beria Joey
  • 你的职业规划师,不走弯路就问我。Sponsor:小红书“ ItsJoe就出行 ”

  • jae-jae
  • Servidor MCP para obtener contenido de la página web con el navegador sin cabeza de dramaturgo.

  • Mintplex-Labs
  • La aplicación AI de escritorio todo en uno y Docker con trapo incorporado, agentes de IA, creador de agentes sin código, compatibilidad de MCP y más.

  • patruff
  • Puente entre los servidores Ollama y MCP, lo que permite a LLM locales utilizar herramientas de protocolo de contexto del modelo

  • pontusab
  • La comunidad de cursor y windsurf, encontrar reglas y MCP

  • WangRongsheng
  • 🧑‍🚀 全世界最好的 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) | Resumen de los mejores recursos del mundo.

  • n8n-io
  • Plataforma de automatización de flujo de trabajo de código justo con capacidades de IA nativas. Combine el edificio visual con código personalizado, auto-anfitrión o nube, más de 400 integraciones.

  • av
  • Ejecute sin esfuerzo LLM Backends, API, frontends y servicios con un solo comando.

  • 1Panel-dev
  • 🔥 1Panel proporciona una interfaz web intuitiva y un servidor MCP para administrar sitios web, archivos, contenedores, bases de datos y LLM en un servidor de Linux.

  • Azure
  • Este repositorio es para el desarrollo del servidor Azure MCP, llevando el poder de Azure a sus agentes.

    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.