# kaggle-mcp

> kaggle-mcp — parkseokjune-kaggle-mcp. Use this tool when you need to manage Kaggle competitions and datasets safely, or track submissions and execute kernels with built-in safeguards. It connects Claude to Kaggle, enabling analysis and competition management while preventing destructive actions and prompt injection. Ideal for data scientists and developers requiring secure and controlled interactions with Kaggle datasets and competitions.

Canonical page: https://skillsregistry.net/skills/parkseokjune-kaggle-mcp  
JSON: https://api.skillsregistry.net/v1/skills/parkseokjune-kaggle-mcp

## Description

A safety-first MCP server that connects Claude to Kaggle, enabling competition management, dataset analysis, submission tracking, and kernel execution with built-in safeguards against destructive actions and prompt injection.

## Trust

- **Trust score (0–1):** 0.69
- **Verification tier:** scanned
- **Last scanned:** 2026-08-29

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** ai-ml
- **Updated:** 2026-08-29

## Source

- **Source listing:** [Glama](https://glama.ai/mcp/servers/nprnmgl6bj)
- **Repository:** <https://github.com/parkseokjune/kaggle-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": "parkseokjune-kaggle-mcp"
    }
  }
}
```

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