freemcplab / Directory / Playground / Kaggle Skill

● Community shepsci ⚡ Instant

Kaggle Skill

Name: Kaggle Skill (Claude Skill)
Author: shepsci

Complete Kaggle integration — competition reports, dataset/model downloads, notebook execution.

A skill that wires Kaggle into Claude Code: list competitions, download datasets/models, submit predictions, fetch notebook executions, track badges. Works across Claude Code, Cursor, Codex, Gemini CLI through skills.sh.

▶ Watch demo 📦 Install 💡 Use Cases

Why use it

Key features

Competition browsing + submission
Dataset and model download with versioning
Notebook execution status + outputs
Badge progress tracking
Multi-agent compatibility via skills.sh standard

Live Demo

What it looks like in practice

kaggle-skill.replay ▶ ready

0/0

Install

Pick your client

~/Library/Application Support/Claude/claude_desktop_config.json · Windows: %APPDATA%\Claude\claude_desktop_config.json

{
  "mcpServers": {
    "kaggle-skill": {
      "command": "git",
      "args": [
        "clone",
        "https://github.com/shepsci/kaggle-skill",
        "~/.claude/skills/kaggle-skill"
      ],
      "_inferred": true
    }
  }
}

Open Claude Desktop → Settings → Developer → Edit Config. Restart after saving.

~/.cursor/mcp.json · .cursor/mcp.json

{
  "mcpServers": {
    "kaggle-skill": {
      "command": "git",
      "args": [
        "clone",
        "https://github.com/shepsci/kaggle-skill",
        "~/.claude/skills/kaggle-skill"
      ],
      "_inferred": true
    }
  }
}

Cursor uses the same mcpServers schema as Claude Desktop. Project config wins over global.

VS Code → Cline → MCP Servers → Edit

{
  "mcpServers": {
    "kaggle-skill": {
      "command": "git",
      "args": [
        "clone",
        "https://github.com/shepsci/kaggle-skill",
        "~/.claude/skills/kaggle-skill"
      ],
      "_inferred": true
    }
  }
}

Click the MCP Servers icon in the Cline sidebar, then "Edit Configuration".

~/.codeium/windsurf/mcp_config.json

{
  "mcpServers": {
    "kaggle-skill": {
      "command": "git",
      "args": [
        "clone",
        "https://github.com/shepsci/kaggle-skill",
        "~/.claude/skills/kaggle-skill"
      ],
      "_inferred": true
    }
  }
}

Same shape as Claude Desktop. Restart Windsurf to pick up changes.

~/.continue/config.json

{
  "mcpServers": [
    {
      "name": "kaggle-skill",
      "command": "git",
      "args": [
        "clone",
        "https://github.com/shepsci/kaggle-skill",
        "~/.claude/skills/kaggle-skill"
      ]
    }
  ]
}

Continue uses an array of server objects rather than a map.

~/.config/zed/settings.json

{
  "context_servers": {
    "kaggle-skill": {
      "command": {
        "path": "git",
        "args": [
          "clone",
          "https://github.com/shepsci/kaggle-skill",
          "~/.claude/skills/kaggle-skill"
        ]
      }
    }
  }
}

Add to context_servers. Zed hot-reloads on save.

claude mcp add kaggle-skill -- git clone https://github.com/shepsci/kaggle-skill ~/.claude/skills/kaggle-skill

One-liner. Verify with claude mcp list. Remove with claude mcp remove.

Use Cases

Real-world ways to use Kaggle Skill

Pull a competition dataset, train a baseline, submit predictions

👤 Kagglers iterating fast ⏱ ~15 min intermediate

When to use: You want to get a first submission on the leaderboard quickly.

Prerequisites

Server/skill installed and authenticated — See repo README

Flow

Pull data

Use the Kaggle skill to download the latest version of competition 'titanic' to ./data.✓ Copied

→ Dataset downloaded; files listed
Submit

After my notebook runs, submit submission.csv with message 'baseline LR'.✓ Copied

→ Submission id + public score when scored

Outcome: A real submission on the leaderboard with one chat.

Pitfalls

Daily submission limits per competition — usually 5–10. The skill warns when you're close. — Daily submission limits per competition — usually 5–10. The skill warns when you're close.

Combine with: filesystem

Combinations

Pair with other MCPs for X10 leverage

kaggle-skill + filesystem

Pair with filesystem

Use this skill together with filesystem.✓ Copied

Tools

What this MCP exposes

Tool	Inputs	When to call	Cost
list_competitions	category, status	Find active competitions	1 API call
download_dataset	ref, version	Pull a dataset locally	Disk I/O
submit	competition, file, message	Submit predictions	1 API call

Cost & Limits

What this costs to run

API quota: Kaggle rate limits apply
Tokens per call: Varies
Monetary: Free for public competitions
Tip: Cache downloads.

Security

Permissions, secrets, blast radius

Credential storage: ~/.kaggle/kaggle.json with chmod 600

Data egress: kaggle.com

Troubleshooting

Common errors and fixes

403 Forbidden on download

Accept the competition's rules on Kaggle first via the web UI. The CLI cannot accept rules.

Verify: Visit competition page

kaggle.json missing

Place your API token at ~/.kaggle/kaggle.json with chmod 600.

Verify: kaggle competitions list

Alternatives

Kaggle Skill vs others

Alternative	When to use it instead	Tradeoff
Kaggle CLI directly	You want raw CLI	No agent integration

Resources

📖 Read the official README on GitHub

🐙 Browse open issues

🔍 Browse all 400+ MCP servers and Skills