# mcp-server-kaggle-exec

> Use this tool when you need to run GPU-accelerated Python code without local GPU hardware, enabling seamless execution of machine learning tasks on Kaggle from any MCP-compatible AI assistant. It solves problems of limited local computing resources and facilitates remote GPU acceleration. The tool accepts Python code as input and outputs the execution results, ideal for use cases requiring intensive computational power.

Canonical page: https://skillsregistry.net/skills/pdwi2020-mcp-server-kaggle-exec  
JSON: https://api.skillsregistry.net/v1/skills/pdwi2020-mcp-server-kaggle-exec

## Description

Enables running GPU-accelerated Python code on Kaggle from any MCP-compatible AI assistant without local GPU hardware.

## Trust

- **Trust score (0–1):** 0.69
- **Verification tier:** scanned
- **Last scanned:** 2026-08-31

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** iot-hardware
- **Updated:** 2026-08-31

## Source

- **Source listing:** [Glama](https://glama.ai/mcp/servers/w1ipvmp4pj)
- **Repository:** <https://github.com/pdwi2020/mcp-server-kaggle-exec>

## 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": "pdwi2020-mcp-server-kaggle-exec"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/pdwi2020-mcp-server-kaggle-exec` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/pdwi2020-mcp-server-kaggle-exec/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