novita MCP Server

README

Novita MCP Server

novita-mcp-server is a Model Context Protocol (MCP) server that provides seamless interaction with Novita AI platform resources. We recommend accessing this server through Claude Desktop, Cursor, or any other compatible MCP client.

Features

⚠️ Beta Notice: novita-mcp-server is currently in beta and only supports GPU instance management. Additional resource types will be supported in future releases.

Currently, novita-mcp-server enables management the resources of GPU instances product.

Supported operations are as follows:

Cluster(/Region): List;
Product: List;
GPU Instance: List, Get, Create, Start, Stop, Delete, Restart;
Template: List, Get, Create, Delete;
Container Registry Auth: List, Create, Delete;
Network Storage: List, Create, Update, Delete;

Installation

You can install the package using npm, or Smithery:

Using npm

npm install -g @novitalabs/novita-mcp-server

Using Smithery

Visit the https://smithery.ai/server/@novitalabs/novita-mcp-server and follow the "Install" instructions to install the server.

Configuration to use novita-mcp-server

First, you need to get your Novita API key from the Novita AI Key Management.

And next, you can use the following configuration for both Claude Desktop and Cursor:

📌 Tips

For Claude Desktop, you can refer to the Claude Desktop MCP Quickstart guide to learn how to configure the MCP server.

For Cursor, you can refer to the Cursor MCP Quickstart guide to learn how to configure the MCP server.

{
  "mcpServers": {
    "@novitalabs/novita-mcp-server": {
      "command": "npx",
      "args": ["-y", "@novitalabs/novita-mcp-server"],
      "env": {
        "NOVITA_API_KEY": "your_api_key_here"
      }
    }
  }
}

Examples

Here are some examples of how to use the novita-mcp-server to manage your resources with Claude Desktop or Cursor:

List clusters

List all the Novita clusters

List products

List all available Novita GPU instance products

List GPU instances

List all my running Novita GPU instances

Create a new GPU instance

Create a new Novita GPU instance:

Name: test-novita-mcp-server-01
Product: any available product
GPU Number: 1
Image: A standard public PyTorch/CUDA image
Container Disk: 60GB

Testing

This project uses Jest for testing. The tests are located in the src/tests directory.

You can run the tests using one of the following commands:

npm test

novita-mcp-server FAQ

How do I connect novita-mcp-server to my MCP client?

Use compatible MCP clients like Claude Desktop or Cursor to connect via the server's endpoint.

What GPU resource operations does novita-mcp-server support?

It currently supports GPU instance management including provisioning, monitoring, and deprovisioning.

Is novita-mcp-server production ready?

It is currently in beta with GPU instance management; more features will be added in future releases.

Can novita-mcp-server manage other Novita AI resources besides GPUs?

Not yet; support for additional resource types is planned for future updates.

Does novita-mcp-server support multiple MCP clients simultaneously?

Yes, it is designed to handle multiple client connections for resource management.

How secure is the communication between MCP clients and novita-mcp-server?

The server follows MCP security principles ensuring scoped, secure, and observable interactions.

Can I automate GPU instance scaling using novita-mcp-server?

Yes, it enables automation of GPU instance provisioning and deprovisioning within AI workflows.

Where can I find documentation for novita-mcp-server?

Documentation and usage details are available on the GitHub repository and MCP ecosystem portals.

novita-mcp-server

Use This MCP server To

README