Sui Butler

Provides MCP-based access to Sui blockchain tools, including wallet, token, DeFi, and CLI integration.
  • typescript

2

GitHub Stars

typescript

Language

5 months ago

First Indexed

2 months ago

Catalog Refreshed

Documentation & install

Readme and setup notes from the catalogue, plus a client-ready config you can copy for your MCP host.

Installation

Add the following to your MCP client configuration file.

Configuration

View docs
{
  "mcpServers": {
    "tamago-labs-sui-butler": {
      "command": "npx",
      "args": [
        "-y",
        "sui-butler",
        "--sui_private_key=YOUR_PRIVATE_KEY",
        "--sui_network=mainnet"
      ]
    }
  }
}

Sui Butler is an MCP server that lets AI models interact with the Sui blockchain through a structured set of tools. It enables reading data, performing token operations, managing accounts, and building smart contracts via an MCP-compatible interface, making it easier to develop and automate blockchain workflows with AI.

How to use

You use Sui Butler by connecting an MCP-compatible AI client to the server, then issuing natural language commands that map to the available MCP tools. You can perform read operations like checking balances and quotes, and you can initiate write operations such as transfers, swaps, and staking. For most new users, zkLogin mode provides a balance between security and convenience, while Private Key mode offers full control by handling transactions locally.

How to install

Prerequisites: you need Node.js and npm installed on your machine. You also need Claude Desktop or another MCP-compatible AI client to connect to the server.

Install the Sui Butler MCP client globally to begin using the server.

Additional sections

Configuration and usage details are provided below to help you run Sui Butler in either the Private Key or zkLogin mode. Ensure you replace placeholders with your actual values when you configure your MCP client.

zkLogin Transaction Flow: When you operate in zkLogin mode, your AI client sends a transaction request to the backend. The transaction is stored with a pending status, and you approve it in the dashboard using your zkLogin-authenticated session before it executes.

Security note: Private Key mode runs transactions locally via the MCP client, so you must securely manage your private keys. zkLogin mode relies on an interactive approval flow in the dashboard to authorize write operations.

Troubleshooting: If you encounter path issues with NVM-managed Node.js, you may need to configure absolute paths in your client configuration. Ensure the CLI and MCP client commands reference the correct Node binary and the correct sui-butler script.

Work with Local Files: When using local Move tooling, you can import a filesystem MCP library to reference your workspace. This lets the AI agent work with your project files directly.

Available tools

sui_get_wallet_address

Retrieve your wallet address

sui_get_all_balances

Get all token balances

sui_transfer_token

Transfer tokens to another address

sui_get_swap_quote

Get a quote for swapping tokens

sui_swap_tokens

Swap tokens on Cetus Aggregator

sui_get_validators

Get all active validators

sui_stake

Stake SUI tokens to a validator

sui_get_stake

Get all staked SUI tokens

sui_unstake

Unstake SUI tokens

sui_deploy_token

Deploy a new token on Sui

sui_get_sns_name_record

Get SNS domain information

sui_register_sns

Register a SNS domain

sui_cli_publish

Deploy a Move package to the network

sui_cli_move_test

Run Move unit tests on the folder

sui_cli_move_new

Create a new Move project

sui_cli_move_build

Build a Move package

sui_cli_call

Call a Move function

sui_cli_active_env

Get the currently active Sui network environment

sui_cli_active_address

Get the active address on Sui CLI

sui_cli_addresses

List all wallet addresses, their aliases

sui_cli_switch_address

Change the active address

pyth_search_price_feeds

Search for price feeds on Pyth

pyth_get_prices

Get prices by feed IDs

pyth_get_common_crypto_prices

Get common crypto prices

Built by
VeilStrat
AI signals for GTM teams
© 2026 VeilStrat. All rights reserved.All systems operational