# Thunder Compute

> Use this tool when you need to accelerate AI workloads, research, or development with on-demand GPU instances. Thunder Compute solves problems of limited computing resources, providing a scalable and flexible platform for handling demanding tasks. It accepts inputs such as SSH keys and disk snapshot configurations, and outputs managed GPU instances and billing information.

Canonical page: https://skillsregistry.net/skills/thunder-compute  
JSON: https://api.skillsregistry.net/v1/skills/thunder-compute

## Description

Thunder Compute is a GPU cloud platform providing on-demand GPU instances for developers, researchers, and AI workloads. Through the MCP server, you can create and manage GPU instances, handle SSH keys, manage disk snapshots, and monitor billing — all without leaving your AI assistant workflow.

## Trust

- **Trust score (0–1):** 0.50
- **Verification tier:** unverified

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** monitoring
- **Updated:** 2026-04-25

## Source

- **Source listing:** [PulseMCP](https://www.pulsemcp.com/servers/thunder-compute)
- **Repository:** <https://github.com/thunder-compute/thunder-cli>

## Use it

Resolve this record through the SkillsRegistry MCP server (no auth, read-only):

```
claude mcp add --transport http --scope user skillsregistry https://api.skillsregistry.net/mcp
```

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "get_skill",
    "arguments": {
      "slug": "thunder-compute"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/thunder-compute` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/thunder-compute/pull`

---
SkillsRegistry indexes agent skills from public registries and GitHub. Skills we have analysed are scanned with Circle-IR and scored on six dimensions; each listing states its scan coverage. More: https://skillsregistry.net/llms.txt