How to Use the Dataiku DSS MCP in LangChain

Q: How do I connect Dataiku DSS to my LangChain agents?

Install langchain-mcp-adapters. Then pass the Vinkius endpoint token to MultiServerMCPClient. Call client.gettools() and hand those directly to your ReAct agent.

Q: Can LangChain trigger Dataiku DSS automation scenarios?

Yes. The MCP Server exposes the runscenario tool. Your agent can decide when a model needs retraining and fire the scenario automatically based on intermediate chain results.

Q: What models can I inspect with this server?

You can pull metadata for any saved ML model. The getmodel tool returns algorithm details and performance metrics from your deployed projects.

Q: Will LangSmith trace Dataiku DSS tool calls?

Every single one. When your agent calls listrecipes or getjob, LangSmith logs the exact inputs, outputs, latency, and token usage for that specific MCP tool call.

Build multi-step Dataiku DSS reasoning pipelines with LangChain ReAct agents.

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 LangChain

Create your Vinkius account to connect Dataiku DSS to LangChain 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 LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Map Dataiku DSS projects in LangChain

Your agent needs context before it acts. Calling `list_projects` pulls down the available workspaces. From there, the chain can hit `list_datasets` and `dataset_schema` to map out the exact column types and structures your data science team built. ReAct agents use this metadata to decide what to do next. If a column type looks wrong, the agent spots it. The output from that schema check becomes the input for the next step in your LangChain pipeline.

Trace pipeline execution paths

Data science workflows break. When they do, your agent can fire `list_jobs` to find the failed build. Digging deeper, it runs `get_job` to pull the exact timing and output logs. All these MCP tool calls show up in LangSmith. You see exactly how many tokens the agent burned while checking `get_model` for performance metrics. You get full visibility into the agent's reasoning process.

Trigger retraining scenarios

Reading data is fine, but fixing things is better. Once your chain identifies a stale model via `list_models`, it can execute `run_scenario` to kick off a fresh training run. The agent doesn't just fire and forget. It loops back with `get_job` to monitor the execution state. Everything stays within the LangChain loop until the task finishes.

Setup guide

Set up Dataiku DSS MCP in LangChain

Prerequisites

Python 3.10+ installed
langchain-mcp-adapters + langgraph packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install langchain-mcp-adapters langgraph langchain-openai. The MCP adapters package converts MCP tools into native LangChain BaseTool objects.
2

Connect via HTTP transport
Use MultiServerMCPClient with "transport": "http" pointing to your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Create a ReAct agent
Pass the discovered tools to create_react_agent() from LangGraph. The agent automatically routes Dataiku DSS tool calls through the MCP protocol.
4

Run with any LLM
Swap ChatOpenAI for ChatAnthropic, ChatGoogleGenerativeAI, or any LangChain-compatible model. The MCP tools work identically across all providers.

agent.py

from langchain_mcp_adapters.client import MultiServerMCPClient
from langgraph.prebuilt import create_react_agent
from langchain_openai import ChatOpenAI

async with MultiServerMCPClient({
    "dataiku-dss-mcp": {
        "transport": "http",
        "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp",
    }
}) as client:
    tools = client.get_tools()

    agent = create_react_agent(
        ChatOpenAI(model="gpt-4o"),
        tools,
    )
    result = await agent.ainvoke({
        "messages": "List recent Dataiku DSS transactions"
    })
    print(result["messages"][-1].content)

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 LangChain

Install `langchain-mcp-adapters`. Then pass the Vinkius endpoint token to `MultiServerMCPClient`. Call `client.get_tools()` and hand those directly to your ReAct agent.

Yes. The MCP Server exposes the `run_scenario` tool. Your agent can decide when a model needs retraining and fire the scenario automatically based on intermediate chain results.

You can pull metadata for any saved ML model. The `get_model` tool returns algorithm details and performance metrics from your deployed projects.

Every single one. When your agent calls `list_recipes` or `get_job`, LangSmith logs the exact inputs, outputs, latency, and token usage for that specific MCP tool call.

Vinkius runs this integration inside a V8 Isolate Sandbox that is destroyed after the session. Your dataset schemas, model metrics, and job logs pass through an ephemeral environment. We hold zero persistent data.

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