How to Use the Dataiku DSS MCP in AutoGen

Q: How do I configure Dataiku DSS for AutoGen?

Install autogen-extmcp. Use mcpservertools with StreamableHttpServerParams pointing to your Vinkius endpoint. Pass the resulting tool list to your AssistantAgent constructor.

Q: What plugin information can the agents see?

Agents can call listplugins to see what extensions are installed. This helps them understand what custom code or connectors are available in the workspace.

Q: How does AutoGen handle the MCP tool schemas?

Automatically. The McpToolAdapter translates the server's JSON schemas into native AutoGen function definitions. Your agents know exactly what parameters runscenario requires without manual configuration.

Build AutoGen agent teams that debate and manage Dataiku DSS pipelines.

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 AutoGen

Create your Vinkius account to connect Dataiku DSS to AutoGen 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 AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Analyze models via AutoGen MCP Server

One agent rarely catches everything. You can assign an evaluator agent to call `list_models` and `get_model` to pull performance metrics. A separate risk agent reviews those exact same metrics. They argue over the results. The evaluator might push to deploy based on high accuracy, while the risk agent flags a drop in recall. They negotiate until they reach a consensus on whether the model is ready for production.

Collaborative job troubleshooting

Broken data pipelines require different perspectives. When a build fails, a diagnostic agent uses `list_jobs` and `get_job` to pull the execution logs. A data engineering agent reads that output and proposes a fix. The diagnostic agent double-checks the proposed fix against the `dataset_schema` to ensure column types match. The agents discuss the problem until they agree on the root cause.

Debate before triggering scenarios

Automation needs guardrails. Before kicking off a massive compute job, your agents review the current state. One checks `list_scenarios` to find the right automation path. Another agent verifies the project settings using `get_project`. Only when both agents agree that the environment is stable do they authorize the `run_scenario` tool. You get automated execution backed by multi-agent deliberation.

Setup guide

Set up Dataiku DSS MCP in AutoGen

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] package
Active Vinkius subscription with a valid endpoint token

1

Install AutoGen with MCP
Run pip install "autogen-ext[mcp]" autogen-agentchat. The MCP extension includes mcp_server_tools for stateless tool access.
2

Fetch tools from the MCP
Call mcp_server_tools(SseServerParams(url=...)) with your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Run your agent
Pass the tools to AssistantAgent and call agent.run(). The agent invokes Dataiku DSS tools and returns structured results.

agent.py

from autogen_ext.tools.mcp import SseServerParams, mcp_server_tools
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

server_params = SseServerParams(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

tools = await mcp_server_tools(server_params)

agent = AssistantAgent(
    name="Dataiku DSS_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

result = await agent.run("List recent Dataiku DSS data")
print(result.messages[-1].content)

Get your connection token →

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] + autogen-agentchat
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Same packages as above. McpWorkbench is ideal when your agent needs stateful sessions across multiple tool calls.
2

Use McpWorkbench as context manager
Wrap your agent in async with McpWorkbench(...) to maintain shared state and resources. The workbench manages the full MCP session lifecycle.
3

Run with workbench
Pass workbench=workbench to your agent. State is preserved across multiple tool calls within the same session.

agent.py

from autogen_ext.tools.mcp import McpWorkbench, SseServerParams
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

server_params = SseServerParams(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

async with McpWorkbench(server_params) as workbench:
    agent = AssistantAgent(
        name="Dataiku DSS_assistant",
        model_client=OpenAIChatCompletionClient(model="gpt-4o"),
        workbench=workbench,
    )

    result = await agent.run("List recent Dataiku DSS data")
    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 AutoGen

Install `autogen-ext[mcp]`. Use `mcp_server_tools` with `StreamableHttpServerParams` pointing to your Vinkius endpoint. Pass the resulting tool list to your `AssistantAgent` constructor.

Yes. The MCP Server handles concurrent requests. Your diagnostic agent can inspect `get_job` outputs while your metadata agent pulls `dataset_schema` details in the same conversation.

Agents can call `list_plugins` to see what extensions are installed. This helps them understand what custom code or connectors are available in the workspace.

Automatically. The `McpToolAdapter` translates the server's JSON schemas into native AutoGen function definitions. Your agents know exactly what parameters `run_scenario` requires without manual configuration.

We rely on ephemeral infrastructure. Your job logs, scenario configurations, and plugin lists are transmitted through a temporary V8 isolate. Vinkius never logs or retains the API payloads passing between your workspace and the agents.

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