SSyncDev

Kaggle MCP Server

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

Local serverstdioPython

What is the Kaggle MCP server?

Most developer tooling work still happens through a UI a human drives. Kaggle MCP server moves it into the conversation instead. 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.

The short version

  • 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

The tools it exposes

The server publishes 1 tool. What each one is for:

  • Windows — The Windows tool exposed by this server

What it needs from you

  • Python 3.8 or newer - Claude Desktop or API access - Kaggle account with API credentials - MCP Python SDK 1.6.0+

Getting it running

git on PyPI is all you need. Most clients run it directly, so configuration is a few lines and a restart.

How it compares

Plenty of developer tooling servers cover similar ground. The differences that matter in practice are scope of access and how much setup stands between you and a working tool call. Kaggle's toolset — Windows — is a fair guide to whether it matches your workflow. It is maintained by 54yyyu; worth a glance at recent repository activity before you build anything load-bearing on it.

SyncDev reviews every entry in this directory against the project's own documentation before publishing, and revisits them as servers change.

Things to watch

  • It runs with your machine's permissions. That is convenient and also the reason to think about what you point it at before you approve a tool call.
  • Keep per-call confirmation enabled while you learn its behaviour; it is the cheapest safeguard you have.

Available tools

ToolWhat it does
WindowsThe Windows tool exposed by this server.

How to install the Kaggle MCP server

{
  "mcpServers": {
    "kaggle-mcp-54yyyu": {
      "command": "uvx",
      "args": ["git"]
    }
  }
}

Add to claude_desktop_config.json, then restart Claude Desktop.

Configuration

  • Python 3.8 or newer - Claude Desktop or API access - Kaggle account with API credentials - MCP Python SDK 1.6.0+

Example prompts to try

  • “Use Kaggle to Windows.”

Frequently asked questions

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.

Alternatives to the Kaggle MCP server

Context7

Official

Kill hallucinated APIs — version-accurate, up-to-date library documentation injected straight into context.

Developer ToolsRemoteTypeScript★ 32.0k

Playwright

Official

Microsoft's official browser automation server — drive a real browser through the accessibility tree, no screenshots needed.

Browser AutomationTypeScript★ 21.0k

GitHub

Official

GitHub's official server — repos, issues, pull requests, Actions and code security, straight from your assistant.

Developer ToolsRemoteGo★ 20.0k

Linear

Official

Issue tracking at the speed of conversation — Linear's official hosted server with OAuth and zero install.

Productivity & Project ManagementRemoteTypeScript

Git

Official

Local repository surgery — status, diffs, commits, branches and history for any repo on disk.

Developer ToolsPython★ 63.0k

Time

Official

Timezone sanity for AI — current time anywhere and correct conversions, without the model doing date math.

Developer ToolsPython★ 63.0k