How to Use the Dataiku DSS MCP in OpenAI Agents SDK

Q: How do I handle multi-agent handoffs in OpenAI Agents SDK when a Dataiku DSS job fails?

You set up one agent to monitor jobs with listjobs and hand off to a troubleshooting agent if a failure occurs. The troubleshooting agent then calls getjob to dissect the error logs.

Q: What is the performance impact of loading 14 Dataiku DSS tools into OpenAI Agents SDK?

Setting the cacheToolsList parameter to true ensures the SDK doesn't fetch the tool definitions on every turn. This keeps your agent latency low while maintaining access to all Dataiku operations.

Run safe, production-grade Dataiku DSS operations directly inside your OpenAI Agents SDK workflows using this MCP Server.

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 OpenAI Agents SDK

Create your Vinkius account to connect Dataiku DSS to OpenAI Agents SDK 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 OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Control Dataiku DSS Pipelines with Safe Agent Handoffs

The `run_scenario` tool lets your OpenAI Agents SDK system trigger DSS automation scenarios like model retraining or data pipeline rebuilds. When a scenario fails, a specialized monitoring agent takes over, calling `get_job` to inspect the exact failure logs and execution steps. This multi-agent setup ensures that raw execution tasks stay separated from debugging tasks. OpenAI's safety guardrails intercept these calls, confirming the agent has the correct DSS permissions before hitting your production pipelines.

Real-Time Model Validation via OpenAI Agents SDK

The `get_model` tool exposes training algorithms and performance metrics directly to your validation agents. Your system queries this data to compare newly trained model metrics against your production baseline before allowing a deployment. By keeping this logic inside the OpenAI Agents SDK, you can write deterministic guardrails that block the agent from promoting a model if accuracy drops. You get full execution tracing on your OpenAI dashboard for every model check.

Map Schema Changes Using this MCP Server

The `dataset_schema` tool pulls column names and data types directly into your agent's context window. If a database migration alters a table, your agent calls `list_datasets` and `get_recipe` to trace how the change impacts downstream Dataiku recipes. Running this MCP Server through the OpenAI SDK means your agents automatically discover these schema tools without manual configuration. You get structured, safe data access without writing custom API connectors.

Setup guide

Set up Dataiku DSS MCP in OpenAI Agents SDK

Prerequisites

Python 3.10+ installed
openai-agents package (pip install openai-agents)
Active Vinkius subscription with a valid endpoint token

1

Install the SDK

Run pip install openai-agents to install the OpenAI Agents SDK. The MCP integration is built-in — no extra dependencies needed.
2

Connect via SSE transport

Use MCPServerSse with your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. The SDK auto-discovers all Dataiku DSS tools at runtime.
3

Create your Agent

Pass the MCP to Agent(mcp_servers=[server]). The agent receives Dataiku DSS tools as native definitions — JSON schemas resolve automatically.
4

Run the agent

Call Runner.run(agent, prompt) to execute. The agent invokes the appropriate Dataiku DSS tools and returns structured results. Copy the full example on the right to get started.

agent.py

import asyncio
from agents import Agent, Runner
from agents.mcp import MCPServerSse

async def main():
    async with MCPServerSse(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ) as server:
        agent = Agent(
            name="Dataiku DSS Agent",
            instructions="You have access to Dataiku DSS tools.",
            mcp_servers=[server],
        )
        result = await Runner.run(agent, "List recent transactions")
        print(result.final_output)

asyncio.run(main())

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 OpenAI Agents SDK

You register the Dataiku DSS MCP Server using the HTTP streamable server parameters in your Python code. The OpenAI Agents SDK auto-discovers the 14 tools, allowing your agents to query schemas and trigger jobs.

Yes, you control this at the agent definition level or by limiting the API key permissions. The SDK's built-in guardrails intercept tool calls like `run_scenario` before they execute, keeping your production pipelines safe.

You set up one agent to monitor jobs with `list_jobs` and hand off to a troubleshooting agent if a failure occurs. The troubleshooting agent then calls `get_job` to dissect the error logs.

Setting the `cacheToolsList` parameter to true ensures the SDK doesn't fetch the tool definitions on every turn. This keeps your agent latency low while maintaining access to all Dataiku operations.

The MCP Server runs inside an isolated sandbox, keeping your API connection details and database credentials secure. Only the schema definitions and job statuses fetched by `list_connections` pass to your OpenAI runtime, never your raw database passwords.

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