What kind of API keys does this MCP support?

This MCP works with Personal, Project, or Global API keys from your Dataiku instance.

Can I trigger actual data transformations?

Yes, you can use the run_scenario capability to trigger execution commands that rebuild pipelines or retrain models.

Which AI clients can I use with this MCP?

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

Does this MCP host the data?

No, Vinkius hosts the MCP itself, but it connects directly to your existing Dataiku DSS instance to perform actions.

Can I see the logic inside my Dataiku recipes?

Yes, the get_recipe capability allows your agent to retrieve the specific configuration and settings for your recipes.

Can my agent trigger a Dataiku automation scenario?

Yes. Use the 'run_scenario' capability. Provide the project key and the scenario ID. The agent will command the backend to orchestrate the absolute workflow rules, triggering a new execution run for your pipeline or model retraining.

How do I check the schema of a specific dataset via chat?

Provide the project key and dataset name to the 'dataset_schema' capability. Your agent will validate the API arrays structurally and return the dataset column names and types natively, helping you understand your data boundaries.

Can I monitor the performance of saved ML models?

Absolutely. Use the 'get_model' capability. Your agent retrieves the metadata and performance metrics defining specific trained schema layers, allowing you to audit model quality and drift without opening the DSS UI.

An astronaut overseeing a futuristic data hub

Download PDF Markdown Version

Connect Dataiku Dss to ChatGPT, Claude and Gemini

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. Manage your entire machine learning lifecycle through natural conversation.

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 · 14 capabilities

We ship only the actions that matter.

Capability set01 / 04

01-04

4 capabilities in this set.

Part of 14 available through Dataiku.

01
Get project
This capability fetches metadata, settings, and tags for a designated project.
02
List datasets
This capability provides a list of all datasets available within a project.
03
List scenarios
Use this to view all automation scenarios set up in a project.
04
Dataset schema
This capability retrieves the column names and data types for a specific dataset.

Capability set02 / 04

05-08

4 capabilities in this set.

Part of 14 available through Dataiku.

05
List projects
This capability lists every DSS project that your API key has permission to access.
06
List recipes
This capability returns a list of all data transformation recipes in a project.
07
Get recipe
Use this to pull the specific configuration and settings for a Dataiku recipe.
08
Run scenario
This capability triggers the execution of a specific automation scenario, such as rebuilding a pipeline or retraining a model.

Capability set03 / 04

09-11

3 capabilities in this set.

Part of 14 available through Dataiku.

09
List models
This capability lists all deployed or saved machine learning models in a project.
10
Get model
Use this to get metadata, the algorithm used, and performance metrics for a saved ML model.
11
List plugins
Use this to see which plugins are currently installed in your DSS instance.

Capability set04 / 04

12-14

3 capabilities in this set.

Part of 14 available through Dataiku.

12
List connections
Use this to see all data connections, such as databases, cloud storage, or APIs, configured in DSS.
13
Get job
This capability retrieves the current state, timing data, and outputs for a specific job.
14
List jobs
This capability lists all active or completed pipeline jobs within a specific project, including build tasks and training runs.

Real work

What teams actually run

Automated Model Retraining

Trigger a scenario to retrain a model immediately after you verify new data has arrived in a dataset.

Rapid Data Auditing

Ask your agent for the schema of a specific dataset to quickly verify if upstream changes broke your pipeline.

Pipeline Health Checks

Monitor the execution state and timing of long-running build tasks to ensure they are progressing as expected.

Environment Verification

Check which data connections and plugins are active to ensure your project has the necessary permissions and capabilities.

Automate a task

Put Dataiku 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

Dataiku 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 Dataiku 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

917ms average. Fast in production.

Dataiku is checked daily against the live service.

Daily averagePeak 1009ms

Oct 7Today

Fastest day: 751ms
Slowest day: 1009ms
14-day trend: Slowing+32%

Connect your client

One URL. Every client.

Activate the Connector, copy your link, and paste it into the client you already use. 14 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 Dataiku, so you can see the experience inside your AI.

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

Dataiku Connector

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

Connector linkhttps://edge.vinkius.com/vk_preview_omB2MsN4Y1V0ZX0dD6ibopTA1n2aAb9aFGAtDQOY/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 — Dataiku capabilities are ready to use.

Configuration · claude_desktop_config.jsonCopy

{
  "mcpServers": {
    "dataiku-dss-mcp": {
      "url": "https://edge.vinkius.com/vk_preview_omB2MsN4Y1V0ZX0dD6ibopTA1n2aAb9aFGAtDQOY/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 Dataiku in Claude and other AIs

See all the AI clients this connector works with ↑

Who it's for

Built for the work Dataiku owners hand off.

This MCP is built for technical teams managing end-to-end machine learning and data engineering lifecycles.

01
Data Scientists
They use the agent to monitor model training and check dataset schemas without leaving their research capabilities.
02
Data Engineers
They use the agent to track pipeline jobs and verify recipe configurations using natural language.
03
MLOps Teams
They use the agent to trigger automation scenarios and monitor deployed models in real time.

FAQ

Questions Dataiku owners ask.

01
What kind of API keys does this MCP support?
This MCP works with Personal, Project, or Global API keys from your Dataiku instance.
02
Can I trigger actual data transformations?
Yes, you can use the run_scenario capability to trigger execution commands that rebuild pipelines or retrain models.
03
Which AI clients can I use with this MCP?
You can use any MCP-compatible client, including Claude, Cursor, and Windsurf.
04
Does this MCP host the data?
No, Vinkius hosts the MCP itself, but it connects directly to your existing Dataiku DSS instance to perform actions.
05
Can I see the logic inside my Dataiku recipes?
Yes, the get_recipe capability allows your agent to retrieve the specific configuration and settings for your recipes.
06
Can my agent trigger a Dataiku automation scenario?
Yes. Use the 'run_scenario' capability. Provide the project key and the scenario ID. The agent will command the backend to orchestrate the absolute workflow rules, triggering a new execution run for your pipeline or model retraining.
07
How do I check the schema of a specific dataset via chat?
Provide the project key and dataset name to the 'dataset_schema' capability. Your agent will validate the API arrays structurally and return the dataset column names and types natively, helping you understand your data boundaries.
08
Can I monitor the performance of saved ML models?
Absolutely. Use the 'get_model' capability. Your agent retrieves the metadata and performance metrics defining specific trained schema layers, allowing you to audit model quality and drift without opening the DSS UI.

Explore

More in AI Frontier

Connect Dataiku 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

Get project

List datasets

List scenarios

Dataset schema

05-08

List projects

List recipes

Get recipe

Run scenario

09-11

List models

Get model

List plugins

12-14

List connections

Get job

List jobs

What teams actually run

Automated Model Retraining

Rapid Data Auditing

Pipeline Health Checks

Environment Verification

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

Dataiku Connector

Claude Desktop

Data Scientists

Data Engineers

MLOps Teams

What kind of API keys does this MCP support?

Can I trigger actual data transformations?

Which AI clients can I use with this MCP?

Does this MCP host the data?

Can I see the logic inside my Dataiku recipes?

Can my agent trigger a Dataiku automation scenario?

How do I check the schema of a specific dataset via chat?

Can I monitor the performance of saved ML models?

Hevo Data (ETL & Data Pipeline) AI Connector

DataRobot AI Connector

Integrate.io (ETL & Data Integration) AI Connector

Data.gov Catalog AI Connector

Suggestions

Data Pipeline Prover AI Connector

MindsDB (AI Database & Predictors) AI Connector

Open Data Euskadi AI Connector

Amsterdam Open Data Explorer AI Connector