Kaggle MCP Server

NodeJS Library for Kaggle API

Local serverstdio

What is the Kaggle MCP server?

NodeJS Library for Kaggle API. Exposed over MCP by the kaggle mcp server, that capability becomes something an assistant can invoke while it works, not something you go and do afterwards.

What it actually does

A node.js SDK for downloading datasets from Kaggle.com using the Kaggle API.

Adding it to your client

kaggle-node on npm is all you need. Most clients run it directly, so configuration is a few lines and a restart.

Its toolset

Everything the assistant can do here goes through one of these:

  • Authenticate — Authenticating is only needed to access public resources requiring user consent or private resources
  • Usage — Import and create KaggleNode object. ts import { KaggleNode } from 'kaggle-node';
  • Datasets — /** Filter search. 'sortBy' - Apply Kaggle sorting criteria, default 'HOTTEST'. 'fileType' - Filter by associated file type. 'license' - Filter by
  • References — The References tool exposed by this server

Configuration

You will need one environment variable: YOUR_KEY. The server will not start without them, which is usually why the tools fail to appear on a first run. Keep credentials in your client's env block or a secrets manager rather than in a file you might commit.

Caveats

  • 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.
  • Missing credentials fail quietly in some clients — if no tools show up, check the environment block first.
  • MCP clients confirm each tool call by default. Leave that on until you have watched what the kaggle mcp server does with a few real requests.

When to reach for it

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 — Authenticate, Usage, Datasets and 1 more — is a fair guide to whether it matches your workflow. It is maintained by anorde; 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.

Available tools

ToolWhat it does
AuthenticateAuthenticating is only needed to access public resources requiring user consent or private resources.
UsageImport and create KaggleNode object. ts import { KaggleNode } from 'kaggle-node';
Datasets/** Filter search. 'sortBy' - Apply Kaggle sorting criteria, default 'HOTTEST'. 'fileType' - Filter by associated file type. 'license' - Filter by license. 'search' - Filter by keyword search. 'tagIds' - Filter by tags.
ReferencesThe References tool exposed by this server.

How to install the Kaggle MCP server

{
  "mcpServers": {
    "kaggle-1": {
      "command": "npx",
      "args": ["-y", "kaggle-node"],
      "env": {
        "YOUR_KEY": "your-value"
      }
    }
  }
}

Add to claude_desktop_config.json, then restart Claude Desktop.

Configuration

VariableDescriptionRequired
YOUR_KEYCredential the server authenticates with.Yes

Example prompts to try

  • Use Kaggle to Authenticate.
  • Use Kaggle to Usage.
  • Use Kaggle to Datasets.

Frequently asked questions

It connects Kaggle to MCP-compatible AI assistants such as Claude and Cursor, exposing 4 tools (Authenticate, Usage, Datasets, and more) that the assistant can call on your behalf. Instead of copying data back and forth by hand, the assistant works with Kaggle directly.