How to Use the Dataiku DSS MCP in Windsurf

Q: How does Windsurf Cascade run Dataiku DSS scenarios?

Cascade calls runscenario with your project and scenario IDs. It then continuously polls getjob to track the execution progress in real time without requiring your manual input.

Q: Can I inspect dataset structures in Windsurf from Dataiku DSS?

Yes. Cascade uses datasetschema to fetch column names and types directly. It uses this schema data to write precise local Python code that matches your remote DSS tables.

Q: Does this MCP Server let Windsurf manage DSS connections?

Yes, Cascade uses listconnections to see what databases and cloud storage buckets are linked to your Dataiku DSS instance. This lets your agent write code that targets the correct data sources.

Q: How do I install this server in my editor?

Add the server URL to your /.codeium/windsurf/mcpconfig.json file. Cascade automatically registers the 14 tools and starts using them in conversations.

Run and monitor your Dataiku DSS pipelines autonomously from Windsurf using Cascade to chain complex data workflows.

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 Windsurf

Create your Vinkius account to connect Dataiku DSS to Windsurf 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 Windsurf

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Run Dataiku DSS pipelines directly in Windsurf

`run_scenario` triggers your Dataiku DSS automation pipelines right inside Windsurf. When you tell Cascade to retrain a model, it runs the scenario, checks the pipeline status with `get_job`, and waits for completion. Cascade handles the entire loop without making you copy-paste job IDs. You get a direct feed of your DSS run status while you write code.

Map and inspect Dataiku DSS datasets with Cascade

`list_datasets` retrieves the full list of datasets in your active Dataiku DSS project. Cascade uses this tool to find the exact tables you need, then pulls their structures with `dataset_schema` to write your local processing scripts. This MCP Server removes the need to keep a browser tab open to DSS just to check column names. Cascade reads the schema, writes your pandas code, and tests it in one autonomous sequence.

Track ML model metrics inside your IDE

`list_models` finds all deployed machine learning models in your Dataiku DSS instance. Cascade uses `get_model` to grab performance metrics and algorithm types when you ask it to document your deployment pipeline. You do not need to hunt through the DSS UI to check which model version is live. The MCP integration feeds the exact training metrics directly to Windsurf so you can make immediate decisions on your code.

Setup guide

Set up Dataiku DSS MCP in Windsurf

Prerequisites

Windsurf IDE installed (macOS, Windows, or Linux)
Active Vinkius subscription with a valid endpoint token

1

Open MCP configuration

Click the Cascade assistant icon in the sidebar, then click the hammer icon (🔨) at the top of the panel. Select "Configure" to open ~/.codeium/windsurf/mcp_config.json.
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

Refresh MCPs

Go back to the hammer icon (🔨) in Cascade and click "Refresh". Windsurf will detect the new server. No full restart is needed — the connection is hot-reloaded.
4

Verify in Cascade

Start a new Cascade conversation and ask something like "Show my Dataiku DSS payment history." If connected, Cascade will call the Dataiku DSS tools directly. You will see a green dot next to the server name in the MCP panel.

mcp_config.json

{
  "mcpServers": {
    "dataiku-dss-mcp": {
      "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 Windsurf

Cascade calls `run_scenario` with your project and scenario IDs. It then continuously polls `get_job` to track the execution progress in real time without requiring your manual input.

Yes. Cascade uses `dataset_schema` to fetch column names and types directly. It uses this schema data to write precise local Python code that matches your remote DSS tables.

Yes, Cascade uses `list_connections` to see what databases and cloud storage buckets are linked to your Dataiku DSS instance. This lets your agent write code that targets the correct data sources.

Add the server URL to your `~/.codeium/windsurf/mcp_config.json` file. Cascade automatically registers the 14 tools and starts using them in conversations.

Vinkius runs this MCP Server in an isolated sandboxed environment. Only project metadata, dataset schemas, and job run statuses pass to Windsurf; your actual raw row-level training data never leaves your secure DSS instance.

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