Dataiku DSS MCP Server

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