How to Use the Dataiku DSS MCP in LlamaIndex

Q: How do I add Dataiku DSS tools to LlamaIndex?

Grab the llama-index-tools-mcp package. Initialize BasicMCPClient with your Vinkius URL, then pass it to McpToolSpec. Run totoollistasync() to get the functions for your agent.

Q: Can LlamaIndex search through my Dataiku DSS datasets?

It searches the metadata, not the raw rows. You use listdatasets and datasetschema to index column names and types. Users can then ask which dataset contains specific fields.

Q: What connection details are exposed?

The listconnections tool returns your available data connections. This tells your agent which databases, cloud storage buckets, or APIs are hooked up to the workspace.

Q: Does LlamaIndex run Dataiku DSS scenarios?

It can. Pass the runscenario tool to a FunctionAgent. The agent can trigger a build pipeline or retrain a model based on the context it retrieves from your vector store.

Index Dataiku DSS metadata into LlamaIndex for grounded RAG applications.

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 LlamaIndex

Create your Vinkius account to connect Dataiku DSS to LlamaIndex 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 LlamaIndex

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Index Dataiku DSS models in LlamaIndex

Stop guessing what algorithms your team deployed. By calling `list_models` and `get_model`, your agent pulls down exact performance metrics. LlamaIndex takes those raw API responses and embeds them directly into your vector store. Users can then query your knowledge base to find out which project has the highest accuracy. The answers come straight from the indexed MCP tool outputs, meaning zero hallucinations about your production machine learning state.

Vectorize pipeline configurations

Data transformations get complicated fast. You can point your agent at `list_recipes` and `get_recipe` to extract the exact configuration of every data prep step. Those settings become searchable text. If a data engineer asks how the customer churn dataset is built, LlamaIndex queries the embedded recipe data. It retrieves the exact SQL or visual prep steps used in that specific project.

Query historical build logs

Troubleshooting requires context. Run `list_jobs` and `get_job` to gather timing and state data for past pipeline executions. LlamaIndex indexes this operational history alongside your documentation. When someone asks why the nightly build failed last Tuesday, your RAG application has the answer. It cross-references the indexed job outputs with known error patterns to explain the failure.

Setup guide

Set up Dataiku DSS MCP in LlamaIndex

Prerequisites

Python 3.10+ installed
llama-index-tools-mcp package
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install llama-index-tools-mcp llama-index-llms-openai. The MCP tools package provides BasicMCPClient and McpToolSpec.
2

Connect with BasicMCPClient
Point BasicMCPClient to your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. Supports SSE and Streamable HTTP transports.
3

Convert to LlamaIndex tools
Call mcp_tool_spec.to_tool_list_async() to convert all Dataiku DSS MCP tools into native FunctionTool objects that any LlamaIndex agent can use.
4

Run with any LLM
Create a FunctionAgent with the tools and your preferred LLM. Swap OpenAI for Anthropic, Gemini, or any LlamaIndex-supported provider.

agent.py

from llama_index.tools.mcp import BasicMCPClient, McpToolSpec
from llama_index.core.agent.workflow import FunctionAgent
from llama_index.llms.openai import OpenAI

# Connect to the MCP
mcp_client = BasicMCPClient(
    "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)
mcp_tool_spec = McpToolSpec(client=mcp_client)

# Convert MCP tools to LlamaIndex tools
tools = await mcp_tool_spec.to_tool_list_async()

# Create and run the agent
agent = FunctionAgent(
    tools=tools,
    llm=OpenAI(model="gpt-4o"),
    system_prompt="You have access to Dataiku DSS tools.",
)
response = await agent.run("List recent Dataiku DSS data")

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 LlamaIndex

Grab the `llama-index-tools-mcp` package. Initialize `BasicMCPClient` with your Vinkius URL, then pass it to `McpToolSpec`. Run `to_tool_list_async()` to get the functions for your agent.

It searches the metadata, not the raw rows. You use `list_datasets` and `dataset_schema` to index column names and types. Users can then ask which dataset contains specific fields.

The `list_connections` tool returns your available data connections. This tells your agent which databases, cloud storage buckets, or APIs are hooked up to the workspace.

It can. Pass the `run_scenario` tool to a `FunctionAgent`. The agent can trigger a build pipeline or retrain a model based on the context it retrieves from your vector store.

Vinkius operates on a zero-trust architecture. The MCP Server processes your project configurations, recipe settings, and connection lists in memory only. Once the connection drops, the isolated environment vanishes completely.

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