広告掲載
MCP.so
ログイン

Kaggle MCP (MCP) Server

@arrismo

リポジトリ

基本情報

カテゴリ

データと分析

ライセンス

MIT

トランスポート

stdio

作者

arrismo

Kaggle MCP (MCP) Server について

MCP server for Kaggle

#kaggle#mcp-server

Kaggle MCP (MCP) Server の設定

以下の設定を使って、このサーバーを MCP 対応クライアントに追加してください。

{
  "mcpServers": {
    "kaggle-mcp": {
      "command": "python",
      "args": [
        "-m",
        "venv",
        ".venv"
      ]
    }
  }
}

Kaggle MCP (MCP) Server のツール

ツール一覧はまだありません

この掲載には表示できるツール一覧がまだありません。サーバーにツールがないという意味ではありません。対応機能はプロジェクトのドキュメントをご確認ください。

ツールは README から自動的に抽出されます。メンテナーは ## Tools という見出しの下に記載することで、このタブに反映できます。

概要

What is Kaggle MCP (Model Context Protocol) Server?

It is a Model Context Protocol (MCP) server that exposes Kaggle dataset search, download, and EDA prompt generation to MCP clients such as Claude Desktop. It is intended for data scientists and developers who want to interact with Kaggle datasets through AI assistants.

How to use Kaggle MCP (Model Context Protocol) Server?

Install dependencies using uv sync or pip install -r requirements.txt, set up Kaggle credentials via environment variables or kaggle.json, then run the server with uv run kaggle-mcp or python src/server.py. Configure your MCP client (e.g., Claude Desktop) by adding the server to its config file with the appropriate command and environment variables.

Key features of Kaggle MCP (Model Context Protocol) Server

  • Search Kaggle datasets by keyword.
  • Download and unzip Kaggle datasets locally.
  • Generate a starter exploratory data analysis (EDA) prompt.
  • Supports Kaggle credentials via environment variables or kaggle.json.
  • Runs locally, in Docker, or through Smithery.
  • Communicates over MCP stdio with clients like Claude Desktop.

Use cases of Kaggle MCP (Model Context Protocol) Server

  • Search for Kaggle datasets by keyword from an AI assistant.
  • Download and unzip a specific dataset to a local directory.
  • Generate an EDA notebook prompt to kickstart data analysis.
  • Integrate Kaggle dataset workflows into a Claude Desktop session.

よくある質問

1

How do I set up Kaggle credentials?

Use either environment variables (`KAGGLE_USERNAME` and `KAGGLE_KEY`) in a `.env` file, or place your `kaggle.json` file in the standard Kaggle location (`~/.kaggle/kaggle.json` on macOS/Linux).

2

What are the system requirements?

Python 3.10 or higher, a Kaggle account with an API token, and an MCP-compatible client (e.g., Claude Desktop).

3

How do I run the server in Docker?

Build the image with `docker build -t kaggle-mcp .` and run it with `docker run --rm -i --env-file .env kaggle-mcp` (using a `.env` file with your credentials).

4

How do I configure the server for Claude Desktop?

Add the server to `claude_desktop_config.json` under `mcpServers` with the command

コメント

「データと分析」の他のコンテンツ

AgentPixel

AllSource Data Corporation

Most website visitors leave without filling out a form. AgentPixel turns the ones who click Accept into contacts your AI agent reads. 30-day trial, no card.

CoinLobster

CoinLobster

The only MCP server with live whale trades across 15 exchanges plus on-chain DEX flow. Smart Money Radar, real liquidations and outcome-scored signals. No API key required.

3

SocialAPIs — Facebook & Instagram Data

SocialAPIsHub

Facebook & Instagram data for AI agents — pages, posts, groups, Ads Library, Marketplace, profiles and reels. 47 read-only tools with structured output.

1

CompanyData

CompanyData

Company search and enrichment for AI agents: 200+ countries of company data from official business registers. Search companies, get full firmographic records and look up exact city names. Hosted MCP, no install.

YouTube MCP Server

HasData

Hosted YouTube MCP server for search, video metadata, channel data and timestamped transcripts. Connect Claude, Cursor or other MCP clients with HasData; no YouTube API key required.

6
広告掲載