Dataiku Factory

What it does

Dataiku Factory connects AI assistants to Dataiku DSS, allowing them to interact directly with data science workflows. It provides a bridge for managing the entire data pipeline lifecycle—from recipe creation and dataset building to scenario automation—directly via the Model Context Protocol.

Tools

• create_recipe / update_recipe / delete_recipe: Manage the lifecycle of data processing recipes.
• create_dataset / build_dataset / inspect_dataset_schema: Provision and execute dataset builds.
• create_scenario / run_scenario / add_scenario_trigger: Automate workflows and manage execution schedules.
• get_recipe_code: Extract Python/SQL code from recipes for analysis.
• get_project_flow: Map the complete data pipeline structure of a project.
• get_dataset_sample: Retrieve sample data for validation and exploration.
• get_recent_runs / get_job_details: Monitor job history and debug failures.

Installation

Add the following to your claude_desktop_config.json:

{
  "mcpServers": {
    "dataiku-factory": {
      "command": "python",
      "args": ["/path/to/dataiku_factory/scripts/mcp_server.py"],
      "env": {
        "DSS_HOST": "https://your-dss-instance.com:10000",
        "DSS_API_KEY": "your-api-key-here",
        "DSS_INSECURE_TLS": "true"
      }
    }
  }
}

Supported hosts

• Claude Desktop
• Claude Code