Hyperbolic GPU
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.
Composite of vulnerability cleanliness, spec conformance, provenance, stability, and usage signals — scanned and weighted by Cognium. Human and agent signals are tracked separately. Last scanned 2026-09-19.
Scan details: Circle-IR · 2026-09-19 · Appeal
View full trust & usage report →Metadata
- Version
- 1.0.0
- Skill type
- atomic
- Execution layer
- mcp-remote
- Category
- iot-hardware
- Source
- PulseMCP
- Repository
- github.com/hyperboliclabs/hyperbolic-mcp
- Author type
- human
- Last scanned
- 2026-09-19
- Updated
- 2026-09-19
Use via MCP
Resolve Hyperbolic GPU from your agent
Streamable HTTP transport at https://api.skillsregistry.net/mcp. No auth for read tools. Discovery: .well-known/mcp.json.
One command in your shell — Claude Code wires it up and verifies the connection. Run /mcp in any session to confirm.
claude mcp add --transport http --scope user skillsregistry https://api.skillsregistry.net/mcp--scope user for --scope project to commit it to .mcp.json.