mcpField
S
Smithery CLI

Smithery CLI

Local
smithery.aiDeveloper Tools849Updated 21w ago
RepositoryVisit website

About Smithery CLI

Smithery CLI is a command line tool for connecting to, searching and calling MCP servers and skills from the terminal. It suits developers who manage the MCP servers used by their agents from the command line.

Key features

  1. 01Search the Smithery registry for MCP servers
  2. 02Manage MCP server connections
  3. 03Find and call tools from connected servers
  4. 04OAuth login and token management
  5. 05Publish MCP server URLs or bundles

Use cases

  1. 01Adding and calling tools from a service such as GitHub
  2. 02Finding tools matching a task across connected servers
  3. 03Publishing an MCP server to the Smithery registry

MCP support

Smithery CLI acts as an MCP client that adds, lists and removes server connections and calls the tools they provide.

Configuration

Local server config is the same for every client. Copy it into your client’s MCP config file.

mcp.json · Universal config
{
  "mcpServers": {
    "cli-smithery-ai": {
      "command": "npx",
      "args": [
        "-y",
        "skills"
      ]
    }
  }
}
Run commandnpx -y skills

Local servers need a runtime on your machine (e.g. Node.js 18+). Config file locations differ by client; see your client’s docs.

Packages
npmskills

Tools

No tool list yet

Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.

Details

From the project README

Smithery CLI NPM Version NPM Downloads

Smithery CLI connects your agents to thousands of skills and MCP servers directly from the command line. To get started, simply run npx skills add smithery/cli.

Installation

npm install -g smithery@latest

Requires Node.js 20+.

Commands

MCP Servers
smithery mcp search [term]              # Search the Smithery registry
smithery mcp add <url>                  # Add an MCP server connection
smithery mcp list                       # List your connections
smithery mcp remove <ids...>            # Remove connections
Tools

Interact with tools from MCP servers connected via smithery mcp.

smithery tool list [connection]        # List tools from your connected MCP servers
smithery tool find [query]             # Search tools by name or intent
smithery tool get <connection> <tool>  # Show full details for one tool
smithery tool call <connection> <tool> [args]  # Call a tool
Skills

Browse skills on the Smithery Skills Registry and install them with the upstream installer:

npx skills add <skill>   # e.g. npx skills add smithery-ai/cli
Auth
smithery auth login                     # Login with Smithery (OAuth)
smithery auth logout                    # Log out
smithery auth whoami                    # Check current user
smithery auth token                     # Mint a service token
smithery auth token --policy '<json>'   # Mint a restricted token
Namespaces
smithery namespace list                 # List your namespaces
smithery namespace use <name>           # Set current namespace
Publishing
smithery mcp publish <url> -n <org/server>          # Publish an MCP server URL
smithery mcp publish <bundle.mcpb> -n <org/server>  # Publish an MCP bundle

Examples

# Search and connect to an MCP server
smithery mcp search "github"
smithery mcp add github --id github

# Find and call tools from your connected MCP servers
smithery tool find "create issue"
smithery tool call github create_issue '{"title":"Bug fix","body":"..."}'

# Browse and install skills
smithery skill search "frontend" --json --page 2
smithery skill add anthropics/frontend-design --agent claude-code

# Publish your MCP server URL
smithery mcp publish https://my-mcp-server.com -n myorg/my-server

# Publish a built MCP bundle
smithery mcp publish ./server.mcpb -n myorg/my-server

Development

git clone https://github.com/smithery-ai/cli
cd cli && pnpm install && pnpm run build
npx . --help

Contributing

Contributions welcome! Please submit a Pull Request.

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.