Hyperbolic GPU

Integrates with Hyperbolic's decentralized GPU network to discover available instances, rent compute resources, establish SSH conn

hyperboliclabs 18
Claude CodeClaude DesktopGeneric
View source ↗

This MCP server provides GPU cloud management and SSH connectivity for Hyperbolic's decentralized GPU network, enabling AI assistants to discover available GPU instances, rent compute resources, and execute remote commands on rented hardware. Built by Hyperbolic Labs using TypeScript with the MCP SDK, node-ssh, and direct API integration, it features real-time GPU marketplace querying with detailed hardware specifications (VRAM, CPU cores, RAM, storage), automated instance provisioning with startup delays, SSH connection management with private key authentication, and remote command execution capabilities. The implementation includes comprehensive instance lifecycle management from rental to termination, connection status monitoring, and structured JSON responses for all operations, making it valuable for AI researchers needing on-demand GPU access, developers requiring scalable compute for machine learning workloads, and automated workflows that need to provision, configure, and manage cloud GPU resources programmatically.

Source

Repository: https://github.com/hyperboliclabs/hyperbolic-mcp

Maintain Hyperbolic GPU?

Let people know it's listed here — add the badge (live metrics, light/dark aware) or a plain link to your README or docs.

[Hyperbolic GPU on getagentictools](https://getagentictools.com/mcp/hyperboliclabs-hyperbolic-mcp?ref=badge)