# com.mcparmory/runpod

> Use this tool when you need to efficiently manage and scale GPU resources across different regions. It solves problems related to resource allocation, scalability, and endpoint management for GPU-intensive workloads. The tool accepts inputs such as pod configurations and scaling requirements, and outputs managed GPU pods and serverless endpoints.

Canonical page: https://skillsregistry.net/skills/com-mcparmory-runpod  
JSON: https://api.skillsregistry.net/v1/skills/com-mcparmory-runpod

## Description

Launch, scale, and manage GPU pods and serverless endpoints across regions

## Trust

- **Trust score (0–1):** 0.00
- **Verification tier:** scanned
- **Last scanned:** 2026-09-19

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** cloud-infra
- **Updated:** 2026-09-19

## Source

- **Source listing:** [MCP Registry](https://registry.modelcontextprotocol.io/v0/servers/com.mcparmory%2Frunpod)
- **Repository:** <https://github.com/mcparmory/registry>

## 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": "com-mcparmory-runpod"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/com-mcparmory-runpod` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/com-mcparmory-runpod/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