Back to Directory/AI & ML

ai.smithery/zeta-chain-cli

Create friendly, customizable greetings for any name or audience. Break the ice in demos, onboardi…

AI & MLTypeScriptv1.0.0
View on GitHub

ZetaChain CLI

A command-line interface for building and interacting with ZetaChain universal applications. Seamlessly interact with EVM, Solana, Bitcoin, Sui, and TON, all from one CLI.

✨ Features

  • Scaffold new ZetaChain universal apps from templates
  • Spin up a local multi-chain development environment (EVM, Solana, etc.) in one command
  • Query cross-chain fees, contracts, balances, cross-chain transaction, tokens, and more
  • Make cross-chain calls between Solana, Sui, Bitcoin, TON, and universal apps on ZetaChain
  • Transfer supported tokens across connected chains

✅ Prerequisites

  • Node.js ≥ 18
  • Git (for template cloning)
  • (Optional) Docker ≥ 24 for localnet

🚀 Quick Start

Run without installing:

bash
npx zetachain@next new

Or install globally:

bash
npm install -g zetachain@latest

Use zetachain@next for bleeding-edge builds.

📘 Examples

Create a new project:

bash
zetachain new

Start localnet:

bash
zetachain localnet start

Query cross-chain balances:

bash
zetachain query balances

🤖 MCP Server Installation

The ZetaChain CLI can be used as an MCP (Model Context Protocol) server, allowing AI assistants like Claude Code and Cursor to execute ZetaChain commands.

Local Installation (Recommended)

Install locally for full access to your filesystem, accounts, and localnet:

bash
npm install -g zetachain
zetachain mcp install --client claude    # for Claude Code
# or
zetachain mcp install --client cursor    # for Cursor

Then restart your AI editor to activate the MCP server.

Check installation status:

bash
zetachain mcp list

Remove:

bash
zetachain mcp remove --client claude

Cloud Installation (Smithery)

For quick setup without local installation, visit Smithery and click "One-Click Install".

⚠️ Note: The cloud version runs on remote servers and cannot access your local files, accounts, or localnet.

🧭 CLI Reference

For full command documentation:

bash
zetachain docs

Or use --help with any command:

bash
zetachain accounts --help

🤝 Contributing

We welcome contributions! Please open issues or submit pull requests.

📚 Learn More

Learn More

How to Use MCP Servers With Ollama and Local LLMsOllama does not natively speak MCP, but bridge tools like MCPHost let local models call MCP tools over stdio. MCPFind indexes 832 servers in the ai-ml category. This guide covers which models support tool calling, how to wire MCPHost to any local model, and which server categories are worth running offline.Read articleMCP vs LangChain Tools: Which Should You Use?LangChain tools and MCP servers both give AI models access to external functions, but they work at different layers. This guide compares them on architecture, cross-client reuse, and long-term maintenance using adoption data from the MCPFind directory's 6,105 indexed servers.Read articleMCP vs Function Calling: Which Should You Build With?MCP and function calling solve different problems in AI agent architecture. Function calling is tight, in-process, and fast. MCP is modular, reusable across models, and designed for production tooling. We analyzed both patterns against real servers in the MCPFind directory to map out when each one wins.Read article