广告合作
MCP.so
登录

Kaggle-MCP: Kaggle API Integration for Claude AI

@54yyyu

代码仓库主页

基本信息

分类

数据与分析

许可证

MIT

传输方式

stdio

作者

54yyyu

关于 Kaggle-MCP: Kaggle API Integration for Claude AI

Kaggle-MCP: Connect Claude AI to the Kaggle API through the Model Context Protocol (MCP), enabling competition, dataset, and kernel operations through the AI interface.

#mcp#kaggle#claude-ai#mcp-server

Kaggle-MCP: Kaggle API Integration for Claude AI 配置

使用下面的配置,将此服务器添加到你的 MCP 客户端。

{
  "mcpServers": {
    "kaggle-mcp-54yyyu": {
      "command": "uv",
      "args": [
        "pip",
        "install",
        "git+https://github.com/54yyyu/kaggle-mcp.git"
      ]
    }
  }
}

Kaggle-MCP: Kaggle API Integration for Claude AI 工具

工具列表暂未提供

当前收录暂时没有可展示的工具列表，不代表服务没有工具。请查阅项目文档了解支持的能力。

工具是从 README 中自动提取的。维护者可以在 ## Tools 标题下列出工具,即可填充这部分内容。

概览

What is Kaggle-MCP?

Kaggle-MCP connects Claude AI to the Kaggle API through the Model Context Protocol (MCP), enabling competition, dataset, and kernel operations through the AI interface. It is built for data scientists, machine learning practitioners, and anyone who wants to interact with Kaggle’s resources using natural language.

How to use Kaggle-MCP?

Install via the provided one-line script (curl on macOS/Linux, powershell on Windows) or manually with pip or uv. After installation, run kaggle-mcp-setup to update your Claude Desktop configuration, or manually add the server entry to the Claude Desktop config file. Obtain Kaggle API credentials from your Kaggle account settings, place the kaggle.json file in ~/.kaggle/, and secure it with chmod 600. Then ask Claude to list competitions, download datasets, search kernels, and more.

Key features of Kaggle-MPC

  • Authentication: Securely authenticate with your Kaggle credentials
  • Competitions: Browse, search, and download data from Kaggle competitions
  • Datasets: Find, explore, and download datasets from Kaggle
  • Kernels: Search for and analyze Kaggle notebooks/kernels
  • Models: Access pre-trained models available on Kaggle

Use cases of Kaggle-MPC

  • Competition Research: Quickly access competition details, data, and leaderboards
  • Dataset Discovery: Find and download datasets for analysis projects
  • Learning Resources: Locate relevant kernels and notebooks for specific topics
  • Model Discovery: Find pre-trained models for various machine learning tasks

常见问题

1

How do I set up Kaggle API credentials?

Go to your Kaggle account settings, click “Create New API Token” to download a `kaggle.json` file, move it to `~/.kaggle/kaggle.json`, and set permissions with `chmod 600 ~/.kaggle/kaggle.json`. Alternatively, authenticate directly through Claude using the `authenticate()` tool with your username and API key.

2

Where is the Claude Desktop configuration file located?

The configuration file is typically at `~/Library/Application Support/Claude/claude_desktop_config.json` on macOS, `%APPDATA%\Claude\claude_desktop_config.json` on Windows, and `~/.config/Claude/claude_desktop_config.json` on Linux.

3

What are the system requirements?

Python 3.8 or newer, Claude Desktop or API access, a Kaggle account with API credentials, and MCP Python SDK 1.6.0+.

4

How can I install Kaggle-MCP?

Use the one‑line installer: `curl -LsSf https://raw.githubusercontent.com/54yyyu/kaggle-mcp/main/install.sh | sh` on macOS/Linux or the PowerShell equivalent on Windows. You can also install manually with `pip install git+https://github.com/54yyyu/kaggle-mcp.git` (or with `uv`).

5

What can I do with Kaggle-MCP after setup?

You can list active competitions, view leaderboards, download datasets (e.g., Boston housing), search for kernels about sentiment analysis, find datasets about climate change, and authenticate with your username and API key—all through natural‑language commands to Claude.

评论

数据与分析 分类下的更多 MCP 服务器

TikTok MCP Server

HasData

Hosted TikTok MCP server for AI agents: read public profiles, account videos, comments and replies, or search videos and creators. Structured JSON for creator research and content analysis.

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

AskWatch Google Search Console MCP

AskWatch

Ask Google Search Console in plain language from Claude, ChatGPT, Cursor or Claude Code. Connect your Google account once and AskWatch issues a personal link: no Cloud project, no credentials.json, nothing to run or host

A

Aayat AI

Aayat AI

Pay-per-use data and tools for AI agents: crypto token safety and rug checks, web search with cited answers, page-to-Markdown, up-to-date library docs, package safety, company research and UK/EU open data. 160 tools, 20

V

VenuNite Events

400,000+ source-verifiable US events from independent venues/community calendars in all 50 states.

广告合作