✨ From vibe coding to vibe deployment. UBOS MCP turns ideas into infra with one message.

Learn more

Frequently Asked Questions about the Novita MCP Server

Q: What is the Model Context Protocol (MCP)? A: MCP is an open protocol standardizing how applications provide context to Large Language Models (LLMs), allowing them to interact with external data and tools.

Q: What does the novita-mcp-server do? A: The novita-mcp-server acts as a bridge between UBOS and Novita AI, allowing seamless management of Novita AI resources like GPU instances from within the UBOS environment.

Q: What resources can I manage with the novita-mcp-server? A: Currently, the novita-mcp-server primarily supports GPU instance management, including listing, creating, starting, stopping, deleting, and restarting instances. Future releases will support additional resource types.

Q: How do I install the novita-mcp-server? A: You can install it using npm (npm install -g @novitalabs/novita-mcp-server) or through Smithery (visit the Smithery page for the server and follow the installation instructions).

Q: How do I configure the novita-mcp-server for use with Claude Desktop or Cursor? A: You’ll need to obtain your Novita API key and then configure your MCP client (Claude Desktop or Cursor) with the server’s command and environment variables, including your API key.

Q: Where do I get my Novita API key? A: You can find your Novita API key in the Novita AI Key Management settings.

Q: What are some example use cases for the novita-mcp-server? A: Examples include accelerating AI training, enabling real-time inference, scaling AI infrastructure, and developing custom AI agents.

Q: Do I need UBOS to use the novita-mcp-server? A: While the novita-mcp-server can be used independently, it’s designed to integrate seamlessly with the UBOS platform, enhancing UBOS’s AI agent development capabilities.

Q: Is the novita-mcp-server production ready? A: No, the novita-mcp-server is in beta, meaning it’s still under development and might have some limitations or bugs. It is highly recommended to test it before utilizing it in production.

Q: Where can I find more information about the Model Context Protocol (MCP)? A: You can find information on the official Model Context Protocol website.

Featured Templates

View More
Verified Icon
AI Assistants
Speech to Text
137 1882
AI Engineering
Python Bug Fixer
119 1433
Customer service
AI-Powered Product List Manager
153 868
Customer service
Service ERP
126 1188

Start your free trial

Build your solution today. No credit card required.

Sign In

Register

Reset Password

Please enter your username or email address, you will receive a link to create a new password via email.