How do I connect this MCP to my AI client?

You subscribe through Vinkius and then connect your client, such as Claude or Cursor, in one click. Vinkius handles the hosting and credential management for you.

Do I need to provide my Kaggle credentials?

Yes, you will need to enter your Kaggle API Token, which consists of your username and API key, to allow the MCP to act on your behalf.

Can my agent actually post replies on Kaggle?

Yes, the MCP includes capabilities that allow your agent to post replies to discussion threads and share notebooks or datasets.

What AI clients can I use with this MCP?

You can use any MCP-compatible client, including Claude, Cursor, Windsurf, and VS Code.

Is this just a way to search Kaggle?

No, it goes beyond searching. It allows for active engagement, such as pushing notebooks, creating datasets, and monitoring competition leaderboards.

How do I find my Kaggle API Token?

Go to your Kaggle account settings. Scroll down to the API section and click 'Create New API Token'. This will download a kaggle.json file containing your username and key.

Can the agent post replies automatically?

Yes. Using the engagement capabilities, your agent can write and post Markdown replies directly into community discussions.

How does the dataset scanning work?

The capability iterates through recent discussions in specific datasets or competitions, filtering for exact keywords like 'alternative', 'error', or 'help'. It's highly efficient for finding interception points.

An astronaut overseeing a futuristic data hub

Download PDF Markdown Version

Connect Kaggle Market Intelligence to ChatGPT and Claude

Set it up once and it works in ChatGPT, Claude, Cursor, and any other client you love. It all runs safely in the background, so you can relax and focus on what really matters. Turn Kaggle into a real-time intelligence and growth engine.

Ask AI about this Connector

Developed, maintained, and hosted by Vinkius.

MCP VERIFIED · PRODUCTION READY · VINKIUS GUARANTEED

Waiting for input…

Works with modern AI clients that support MCP, including ChatGPT, Claude, Cursor, and more.

Your AI does the work. We keep it safe and sound.

No other AI tool gives you this. Your workflow runs in the client you already love, your account stays protected, and you decide what the agent can and cannot do. It is the whole reason to make the switch.

Each Connector lives inside our infrastructure, the same place where your workflow runs. The three things below are already part of it, working quietly in the background so you never have to think about them. Nothing to add, nothing to set up, nothing to worry about.

V8 Isolate01

Each Connector runs inside its own sealed environment.

Each Connector runs inside its own sealed V8 runtime — no access to your files, your system, or other servers. A Connector never sees past its own request.

Kill Switch02

One switch stops every agent. Instantly.

One action deactivates every Connector, revokes every token, and ends every session at once. AI Governance keeps the record.

FinOps per User03

Spending limits that pause instead of surprise.

Every user keeps their own connections and credentials, isolated from everyone else. Anything that would cross your spending limit is held for your approval, not billed.

Three controls, built into the layer your AI connects through.

Curated set · 10 capabilities

We ship only the actions that matter.

Capability set01 / 03

01-04

4 capabilities in this set.

Part of 10 available through Kaggle.

01
Create dataset
This capability creates a new Kaggle dataset. Use it to share processed or synthesized data directly with the community.
02
Push notebook
This capability pushes a notebook or script to Kaggle. It is the primary way to share code and analysis with other users.
03
Search competitions
This capability searches Kaggle competitions. Use it to find active groups of engaged data scientists.
04
Get competition leaderboard
This capability retrieves a competition leaderboard. Use it to analyze top performers and winning scores.

Capability set02 / 03

05-07

3 capabilities in this set.

Part of 10 available through Kaggle.

05
Get notebook status
This capability checks the execution status of a Kaggle notebook. Use it to monitor whether a script has finished running.
06
List dataset files
This capability lists the files inside a Kaggle dataset. Use it to inspect data schemas before starting an analysis.
07
Search datasets
This capability searches for Kaggle datasets. Use it to find specific data or niche communities.

Capability set03 / 03

08-10

3 capabilities in this set.

Part of 10 available through Kaggle.

08
Search models
This capability searches for Kaggle models. Use it to identify which architectures are being deployed and by whom.
09
Search notebooks
This capability searches Kaggle notebooks. Use it to find code examples or winning competition strategies.
10
Pull notebook
This capability pulls code from a Kaggle notebook. Use it to read and learn from other developers' implementations.

Real work

What teams actually run

Growth Hacking

Find users asking about deployment issues and suggest your infrastructure via technical replies.

Market Research

Monitor which machine learning models are gaining traction by searching Kaggle models.

Competitor Analysis

Track competition leaderboards to see how top performers are scoring.

Technical Support

Identify discussions where users are struggling with data prep to offer solutions.

Automate a task

Put Kaggle to work on one thing.

Step-by-step automations your AI runs through this Connector: the workflow, the prompts to start with, and the exact capabilities behind each move.

One connector, every AI

Kaggle works with the most popular AI clients.

These are the most popular clients, each with a step-by-step guide: one link, set up once, with governance and visibility built in. And because everything runs on the MCP standard, the same connection also works in any other compatible client — nothing to rebuild.

Building your own app? The connector is yours to use.

You don't need a client to put Kaggle to work: the same hosted connection plugs into your own applications and agent code, with the same governance on every request. Build with it, chat with it — one connection for both.

Observed, not estimated

842ms average. Fast in production.

Kaggle is checked daily against the live service.

Daily averagePeak 975ms

Oct 3Today

Fastest day: 666ms
Slowest day: 975ms
14-day trend: Improving-11%

Connect your client

One URL. Every client.

Activate the Connector, copy your link, and paste it into the client you already use. 10 capabilities arrive ready to run.

Preview access · not provider authentication

The vk_preview_* token belongs to Vinkius preview infrastructure. It lets Claude discover and display the capabilities of Kaggle, so you can see the experience inside your AI.

It does not authenticate your account with Kaggle. Actions requiring credentials or live account data may not run until you activate the Connector and authorize the service.

Kaggle Connector

You're all set. Choose your MCP client and follow the setup instructions.

Connector linkhttps://edge.vinkius.com/vk_preview_D9qB4MVerPWx9BW5Z9tgoSaKlq533NU0W3PDjMbm/mcp

Claude Desktop

Follow the steps below to connect in seconds.

1In Claude Desktop, open Settings → Connectors.
2Click “Add custom connector” and paste the connector link above as the remote MCP server URL.
3Click Add and start a new chat — Kaggle capabilities are ready to use.

Configuration · claude_desktop_config.jsonCopy

{
  "mcpServers": {
    "kaggle-market-intelligence-mcp": {
      "url": "https://edge.vinkius.com/vk_preview_D9qB4MVerPWx9BW5Z9tgoSaKlq533NU0W3PDjMbm/mcp"
    }
  }
}

Claude
ChatGPT
Cursor
VS Code
Windsurf
Claude Code
JetBrains
Cline

Step-by-step instructions for each client are in the guide. How to connect

Guided setup for Claude? Set up Kaggle in Claude and other AIs

See all the AI clients this connector works with ↑

Who it's for

Built for the work Kaggle owners hand off.

This MCP is built for professionals who need to monitor and interact with the Kaggle data science community without manual browsing.

01
Founders & Growth Leads
They hand off the task of finding users who need better ML deployment infrastructure.
02
Developer Advocates
They use the agent to find and join discussions related to their specific data stack.
03
Sales Engineers
They delegate the auditing of trending datasets to uncover community pain points.

FAQ

Questions Kaggle owners ask.

01
How do I connect this MCP to my AI client?
You subscribe through Vinkius and then connect your client, such as Claude or Cursor, in one click. Vinkius handles the hosting and credential management for you.
02
Do I need to provide my Kaggle credentials?
Yes, you will need to enter your Kaggle API Token, which consists of your username and API key, to allow the MCP to act on your behalf.
03
Can my agent actually post replies on Kaggle?
Yes, the MCP includes capabilities that allow your agent to post replies to discussion threads and share notebooks or datasets.
04
What AI clients can I use with this MCP?
You can use any MCP-compatible client, including Claude, Cursor, Windsurf, and VS Code.
05
Is this just a way to search Kaggle?
No, it goes beyond searching. It allows for active engagement, such as pushing notebooks, creating datasets, and monitoring competition leaderboards.
06
How do I find my Kaggle API Token?
Go to your Kaggle account settings. Scroll down to the API section and click 'Create New API Token'. This will download a kaggle.json file containing your username and key.
07
Can the agent post replies automatically?
Yes. Using the engagement capabilities, your agent can write and post Markdown replies directly into community discussions.
08
How does the dataset scanning work?
The capability iterates through recent discussions in specific datasets or competitions, filtering for exact keywords like 'alternative', 'error', or 'help'. It's highly efficient for finding interception points.

Explore

More in Growth Engine

Connect Kaggle to Claude, Cursor, ChatGPT & more

Your AI does the work. We keep it safe and sound.

Each Connector runs inside its own sealed environment.

One switch stops every agent. Instantly.

Spending limits that pause instead of surprise.

We ship only the actions that matter.

01-04

Create dataset

Push notebook

Search competitions

Get competition leaderboard

05-07

Get notebook status

List dataset files

Search datasets

08-10

Search models

Search notebooks

Pull notebook

What teams actually run

Growth Hacking

Market Research

Competitor Analysis

Technical Support

Building your own app? The connector is yours to use.

Kaggle Connector

Claude Desktop

Founders & Growth Leads

Developer Advocates

Sales Engineers

How do I connect this MCP to my AI client?

Do I need to provide my Kaggle credentials?

Can my agent actually post replies on Kaggle?

What AI clients can I use with this MCP?

Is this just a way to search Kaggle?

How do I find my Kaggle API Token?

Can the agent post replies automatically?

How does the dataset scanning work?

Hevo Data (ETL & Data Pipeline) AI Connector

GitHub Market Intelligence AI Connector

Dataiku DSS AI Connector

Integrate.io (ETL & Data Integration) AI Connector

Suggestions

Data Pipeline Prover AI Connector

data.world AI Connector

Alation AI Connector

Data.gov Catalog AI Connector