Thunder Compute
Let your coding agent provision GPU instances, snapshots, SSH keys, and billing on Thunder Compute without leaving the editor.
Overview
Thunder Compute is a MCP server for the Operate phase that lets agents create, manage, and monitor GPU cloud instances, snapshots, SSH keys, and billing on Thunder Compute.
What is this MCP server?
- Streamable HTTP remote MCP at api.thundercompute.com:8443 (server schema 1.0.0)
- Create, manage, and monitor GPU cloud instances from the agent
- Snapshots and SSH key management for reproducible dev environments
- Billing visibility so indie builders can watch GPU spend
- Backed by thunder-cli on GitHub (Thunder-Compute/thunder-cli)
- Server version 1.0.0 in the published manifest
- Remote transport: streamable-http at https://api.thundercompute.com:8443/mcp
- Repository: github.com/Thunder-Compute/thunder-cli
Community signal: 33 GitHub stars.
What problem does it solve?
Solo builders waste cycles jumping between GPU dashboards, SSH setup, and billing pages while the agent could orchestrate the same tasks in one thread.
Who is it for?
Indie ML or GPU inference builders who already use Thunder Compute and want agent-driven instance and key management.
Skip if: Teams that only need local CPU dev boxes or who are not willing to trust an agent with cloud infrastructure actions.
What do I get? / Deliverables
After you register the remote MCP endpoint, your agent can drive Thunder GPU infrastructure conversations end-to-end with fewer manual CLI and console steps.
- Agent-callable tools for GPU instance create/manage/monitor flows
- SSH key and snapshot operations aligned with Thunder Compute
- Billing and status queries usable inside agent threads
Recommended MCP Servers
Journey fit
GPU workloads live in production and iteration loops after you ship—instance lifecycle and cost control sit squarely in the operate phase. Infra subphase covers remote compute, keys, snapshots, and billing—the day-two cloud footprint solo ML and inference builders manage.
How it compares
Remote GPU infrastructure MCP, not a local coding skill or generic file-editing plugin.
Common Questions / FAQ
Who is Thunder Compute MCP for?
Solo and small-team builders on Thunder’s GPU cloud who use Claude Code, Cursor, or similar agents and want MCP tools for instances, snapshots, SSH keys, and billing.
When should I use Thunder Compute MCP?
Use it during operate-phase infra work—spinning GPUs for training or inference, snapshotting environments, rotating SSH keys, or checking spend—without leaving the agent session.
How do I add Thunder Compute to my agent?
Add the published remote server URL https://api.thundercompute.com:8443/mcp (streamable-http) per your client’s MCP remote config, using the io.github.Thunder-Compute/thunder-compute manifest; confirm auth requirements on Thunder’s docs before production use.