How to Use the Dataiku DSS MCP in Google ADK

Q: Can my Google ADK agent query Dataiku DSS schemas alongside BigQuery tables?

Yes, your agent can combine tools. It uses datasetschema to pull DSS metadata and compares it directly with BigQuery schemas using native Google ADK tools.

Q: How do I configure the Dataiku DSS MCP Server inside a Google ADK project?

You initialize the toolset using McpToolset with the streamable HTTP parameters pointing to the Vinkius endpoint. You then pass this toolset directly to your LlmAgent configuration.

Q: How do I restrict a Google ADK agent to read-only Dataiku DSS actions?

Use the toolnames filter when setting up your McpToolset. Exclude runscenario and only expose metadata tools like listdatasets and getrecipe to keep your system read-only.

Give your Gemini-powered Google ADK agents direct access to Dataiku DSS datasets, models, and pipelines via 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 Google ADK

Create your Vinkius account to connect Dataiku DSS to Google ADK 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 Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Context-Rich Dataiku DSS Inspections in Google ADK

The `list_datasets` tool feeds your Gemini agent the complete inventory of your DSS project tables. Because Google ADK supports Gemini's million-token context window, your agent can analyze every single dataset schema returned by `dataset_schema` simultaneously. This massive context allows the agent to find structural mismatches across hundreds of tables. You don't have to chunk the schema data or write complex filtering logic to keep the agent from forgetting previous tables.

Automating BigQuery and Dataiku DSS Pipelines

The `run_scenario` tool bridges the gap between your Google Cloud data warehouse and your DSS workflows. When a BigQuery export finishes, your Google ADK agent detects the new data and triggers the corresponding Dataiku scenario. By configuring this MCP Server within your Gemini agent loop, you automate the entire retraining pipeline. The agent monitors the run using `get_job` and posts status updates directly to your cloud logging console.

Audit Dataiku DSS Plugins via Google ADK

The `list_plugins` tool exposes all installed DSS extensions to your Google ADK security agents. Your agent scans this list to check for outdated or unapproved plugins that violate your enterprise security policies. You can limit the agent's scope using the tool_names filter during initialization. This ensures the agent only inspects configurations via `list_projects` and cannot trigger destructive actions.

Setup guide

Set up Dataiku DSS MCP in Google ADK

Prerequisites

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

1

Install Google ADK

Run pip install google-adk to install the Agent Development Kit. MCP support is included via the McpToolset class.
2

Connect via SSE transport

Use McpToolset.from_server() with SseServerParams pointing to your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Create an LlmAgent

Pass the returned mcp_tools list directly to LlmAgent(tools=mcp_tools). The ADK maps each MCP tool to a native Gemini function call — no manual schema definitions required.
4

Run with any Gemini model

The agent works with any Gemini model (gemini-2.0-flash, gemini-2.5-pro, etc.). Copy the full example on the right to get started with Dataiku DSS tools in your ADK agent.

agent.py

from google.adk.agents import LlmAgent
from google.adk.tools.mcp_tool.mcp_toolset import McpToolset
from google.adk.tools.mcp_tool.mcp_session_manager import SseServerParams

# Connect to the MCP via SSE
mcp_tools, exit_stack = await McpToolset.from_server(
    connection_params=SseServerParams(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    )
)

# Create your agent with auto-discovered tools
agent = LlmAgent(
    name="Dataiku DSS_agent",
    model="gemini-2.0-flash",
    instruction="You have access to Dataiku DSS tools via MCP.",
    tools=mcp_tools,
)

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 Google ADK

Yes, your agent can combine tools. It uses `dataset_schema` to pull DSS metadata and compares it directly with BigQuery schemas using native Google ADK tools.

You initialize the toolset using `McpToolset` with the streamable HTTP parameters pointing to the Vinkius endpoint. You then pass this toolset directly to your `LlmAgent` configuration.

Yes, this server runs on Vinkius over secure HTTP, which Google ADK handles natively. You pass the endpoint URL to the toolset initializer to establish the connection.

Use the `tool_names` filter when setting up your `McpToolset`. Exclude `run_scenario` and only expose metadata tools like `list_datasets` and `get_recipe` to keep your system read-only.

The MCP Server runs in a zero-trust sandbox where your master API keys are hidden. Only pipeline configurations and project metadata are queried via the endpoint; your raw connection passwords remain completely hidden.

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