How to Use the Dataiku DSS MCP in Claude Code

Q: Can I monitor Dataiku DSS pipeline jobs in Claude Code?

Yes. Claude Code uses listjobs and getjob to track active builds. You can run these checks directly from your terminal session or embed them in automated shell scripts.

Q: How does Claude Code fetch Dataiku DSS dataset details?

The CLI agent uses datasetschema to retrieve column names and data types. It prints this structured schema directly to your terminal screen.

Q: Can I list active Dataiku DSS connections using Claude Code?

Yes, Claude Code calls listconnections to see all database and cloud storage connections. This lets your terminal agent verify where your DSS project is reading and writing data.

Q: How do I add this server to my CLI?

Run claude mcp add --transport http dataiku-dss-mcp -- in your terminal. Use claude mcp list to verify that all 14 tools are registered.

Control Dataiku DSS pipelines and query dataset schemas directly from your terminal using Claude Code.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Dataiku DSS MCP to Claude Code

Create your Vinkius account to connect Dataiku DSS to Claude Code and route execution through our secure gateway. The platform manages server hosting, runtime updates, and security layers. Configuration requires no manual server provisioning.

GDPR Free for Subscribers

Setup Dataiku DSS with Claude Code

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Run Dataiku DSS pipelines from the CLI

`run_scenario` triggers your Dataiku DSS automation scenarios directly through Claude Code. The terminal agent kicks off your model retraining or data build pipelines without requiring you to open a web browser. You can pipe the terminal output into other command-line tools. This MCP integration allows you to build bash scripts that trigger DSS runs and process the results locally.

Audit your ML models via Claude Code

`list_models` retrieves all deployed machine learning models in your Dataiku DSS project. Claude Code uses this tool alongside `get_model` to print algorithm details and performance metrics directly to your standard output. This MCP Server gives your terminal client the ability to inspect your model registry. You can instantly check which version of a model is live and verify its drift metrics without leaving your shell.

Map DSS projects and datasets in your shell

`list_projects` lists every Dataiku DSS project your API key can access. Claude Code uses this to navigate your DSS instance, then uses `list_datasets` and `dataset_schema` to map out table structures. This maps your remote data lake straight to your local terminal. Your CLI agent can quickly inspect schema definitions and generate SQL migration scripts that match your remote tables.

Setup guide

Set up Dataiku DSS MCP in Claude Code

Prerequisites

Claude Code CLI installed (npm install -g @anthropic-ai/claude-code)
Active Vinkius subscription with a valid endpoint token

1

Run the add command

Open your terminal and run the command shown on the right. Replace [YOUR_TOKEN_HERE] with your endpoint token from cloud.vinkius.com. Use --scope user to make it available across all projects.
2

Verify the connection

Start a Claude Code session and type /mcp to list connected servers. You should see dataiku-dss-mcp with a green status indicator.
3

Start using tools

Ask Claude Code something like "Check my latest Dataiku DSS transactions." It will automatically discover and invoke the available Dataiku DSS tools.

Terminal

claude mcp add --transport http dataiku-dss-mcp https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp

Get your connection token →

Prerequisites

Claude Code CLI installed
Active Vinkius subscription with a valid endpoint token

1

Open the config file

Create or edit .mcp.json in your project root for project-level scope, or ~/.claude.json for user-level scope.
2

Add the Dataiku DSS MCP

Paste the JSON snippet shown on the right into the mcpServers object. Replace [YOUR_TOKEN_HERE] with your endpoint token from cloud.vinkius.com.
3

Restart Claude Code

Start a new Claude Code session. Type /mcp to confirm the server is connected. The tools will be automatically available in your conversation.

.mcp.json

{
  "mcpServers": {
    "dataiku-dss-mcp": {
      "type": "url",
      "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    }
  }
}

Get your connection token →

Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by Dataiku. All third-party trademarks, logos, and brand names are the property of their respective owners. Their use on this website is strictly for informational purposes to identify service compatibility and interoperability.

Why Choose Vinkius

Vinkius connects your tools to AI with real-time monitoring and automatic cost savings — all from one dashboard.

Connect Dataiku DSS now

Real-time monitoring

Live

visibility into every interaction

Connect your favorite tools to your AI and see exactly what's happening — every request, every response, in real time.

Built-in savings

60%

lower AI costs

Vinkius compresses data between your apps and your AI automatically. Lower bills every month — no configuration required.

Single dashboard

One

place for every integration

Every tool your AI connects to, managed from a single screen. One account, complete control.

Common questions about Dataiku DSS MCP in Claude Code

Yes. Claude Code uses `list_jobs` and `get_job` to track active builds. You can run these checks directly from your terminal session or embed them in automated shell scripts.

The CLI agent uses `dataset_schema` to retrieve column names and data types. It prints this structured schema directly to your terminal screen.

Yes, Claude Code calls `list_connections` to see all database and cloud storage connections. This lets your terminal agent verify where your DSS project is reading and writing data.

Run `claude mcp add --transport http dataiku-dss-mcp -- ` in your terminal. Use `claude mcp list` to verify that all 14 tools are registered.

No. This server only exposes metadata like project configurations, dataset schemas, and job statuses. Your actual raw database rows and training records never pass through the MCP link.

Use it with your favorite AI tools

Connect this server to Cursor, Claude, VS Code, and more.

OpenAI Agents SDK sdk-python

Google ADK sdk-python

Pydantic AI sdk-python

Vercel AI SDK sdk-typescript