# prime-intellect-mcp

> Use this tool when you need to autonomously manage cloud GPU resources, provision and terminate Prime Intellect GPU pods, and enforce hard spend caps. It solves problems related to resource allocation, cost control, and scalability for AI workloads. The prime-intellect-mcp server takes in rental and termination requests as inputs and outputs managed GPU pods with controlled expenses.

Canonical page: https://skillsregistry.net/skills/kvrancic-prime-intellect-mcp  
JSON: https://api.skillsregistry.net/v1/skills/kvrancic-prime-intellect-mcp

## Description

The server enables Claude Code to rent, drive, and terminate Prime Intellect GPU pods with hard spend caps, allowing AI agents to provision and manage cloud GPU resources autonomously.

## Trust

- **Trust score (0–1):** 0.70
- **Verification tier:** verified
- **Last scanned:** 2026-09-02

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** ai-ml
- **Updated:** 2026-09-02

## Source

- **Source listing:** [Glama](https://glama.ai/mcp/servers/t5br5pxl92)
- **Repository:** <https://github.com/kvrancic/prime-intellect-mcp>

## 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": "kvrancic-prime-intellect-mcp"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/kvrancic-prime-intellect-mcp` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/kvrancic-prime-intellect-mcp/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