mcpField
S
Sui Serverless MCP Core

Sui Serverless MCP Core

Local
sui-butler.tamagolabs.comCloud & Infra0Updated 75w ago

About Sui Serverless MCP Core

Sui Serverless MCP Core is the backend for SUI Butler, providing serverless infrastructure for MCP services on the Sui blockchain. It supports zkLogin authentication, transaction requests, and a dashboard for access keys and transaction approval.

Key features

  1. 01AWS serverless infrastructure
  2. 02zkLogin authentication via Enoki
  3. 03Transaction request handling
  4. 04Metadata storage for zkLogin accounts
  5. 05Dashboard for access keys and approvals

Use cases

  1. 01Authenticate using a Google account with zkLogin
  2. 02Submit Sui transaction requests from an MCP-compatible client
  3. 03Review and approve pending transactions in the dashboard
  4. 04Manage access keys

MCP support

The backend supports MCP services on Sui. MCP-compatible clients can submit transaction requests, which users approve through the dashboard in zkLogin mode.

Configuration

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

No install method listed yet

We haven’t collected a package or remote endpoint for this server. Follow the instructions in the project README.

Repository

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

Sui Butler Backend

This repository is part of the SUI Butler system — a server implementation for enabling Model Context Protocol (MCP) service on the Sui blockchain using zkLogin.

It contains the backend infrastructure built with AWS Serverless Stack to support MCP features, including APIs, databases, and the user dashboard for managing access keys and approving transactions.

Note: We can use without the backend with the private key mode. Refer to the main repo for more details.

System Overview

This project uses the AWS Amplify stack for full-stack, serverless infrastructure as code. Key components include:

  • Frontend: Built with Next.js and deployed on Amplify Hosting.
  • API: Using Next.js app API routes for transaction management.
  • zkLogin: For authentication with zkLogin via Enoki. Support only Google account on this version.
  • Database: Storing metadata associated with zkLogin accounts. Each user is uniquely identified via their email and wallet address.

zkLogin Transaction Flow

When a user operates in zkLogin mode using an MCP-compatible AI client:

  1. The client pushes a transaction request to the backend (via this system).

  2. The transaction is stored in the database with a pending status.

  3. The user can visit the dashboard to manually approve the transaction using their zkLogin-authenticated session.

Deploying to AWS

For detailed instructions on deploying the AWS Cloud, refer to the deployment section of the AWS documentation.

License

This library is licensed under the MIT-0 License. See the LICENSE file.

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.