Dataiku DSS

Dataiku DSS MCP Connector for Claude

A+

Manage data science via Dataiku — list projects and datasets, track pipeline jobs, run automation scenarios, and monitor ML models directly from any AI agent.

14 tools Official Updated Jun 28, 2026 Official Vinkius Partner

Connect your Dataiku DSS instance to any AI agent and take full control of your enterprise AI and collaborative data science workflows through natural conversation.

What you can do

  • Project & Dataset Exploration — List all accessible DSS projects and retrieve structural extraction of dataset column schemas and types
  • Pipeline Orchestration — Monitor build tasks and training runs by listing pipeline jobs and analyzing execution states and timing
  • Transformation Auditing — Retrieve explicit configuration structures parsing precise Dataiku recipes (Python, SQL, Visual) to verify data logic
  • Automation & Scenarios — List automation scenarios and trigger execution commands to rebuild pipelines or retrain models securely
  • Model Monitoring — Identify saved ML models and retrieve detailed performance metrics defining specific trained schema layers
  • Admin Oversight — Enumerate installed plugins and data connections (SQL, Cloud Storage, APIs) to verify organizational constraints

How it works

  1. Subscribe to this server
  2. Enter your Dataiku Instance URL and API Key (Personal, Project, or Global key)
  3. Start managing your data science workflows from Claude, Cursor, or any MCP-compatible client

Who is this for?

  • Data Scientists — monitor model training and compare dataset schemas without leaving the research flow
  • Data Engineers — track pipeline jobs and verify recipe configurations using natural language
  • MLOps Teams — trigger automation scenarios and monitor deployed models in real-time
  • Analytics Managers — audit project metadata and data connections across the organization
data-scienceml-opspipeline-orchestrationpredictive-modelingdata-pipelinesautomation

14 tools expose this connector's capabilities to your AI agent.

list_projects

List all DSS projects accessible to the API key

get_project

Get project metadata, settings, and tags

list_datasets

List all datasets in a project

dataset_schema

Get the schema (columns, types) of a specific dataset

list_recipes

List all recipes (data transformations) in a project

list_jobs

List pipeline jobs in a project (build tasks, training runs)

get_job

Get job state, timing, and outputs

list_scenarios

List automation scenarios in a project

list_models

List deployed/saved ML models in a project

get_model

Get saved model metadata, algorithm, and performance metrics

run_scenario

Trigger a scenario execution (build pipeline, retrain model)

list_plugins

List installed DSS plugins

list_connections

List all DSS data connections (databases, cloud storage, APIs)

get_recipe

Get recipe configuration and settings

See how to talk to your AI agent using Dataiku DSS.

List all projects in my Dataiku instance

I found 5 projects: 'Churn-Prediction-Q1', 'Customer-Segmentation', 'Fraud-Detection-Live', 'Sales-Forecasting', and 'Staging-Sandbox'. Which one would you like to explore?

What is the schema for dataset 'raw_logs' in project 'FRAUD'?

Retrieving schema for 'raw_logs'... It contains 12 columns including 'timestamp' (date), 'user_id' (string), 'ip_address' (string), and 'action_type' (string). I can provide the full type mapping if you'd like.

Run scenario 'REBUILD_PIPELINE' in project 'SALES'

Scenario triggered! 'REBUILD_PIPELINE' is now executing in project 'SALES'. The system is rebuilding the underlying datasets and recipes. I will notify you once the run is complete.

Yes. Use the 'run_scenario' tool. 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.

Related Connectors