How to Use the DataRobot MCP in AutoGen

Q: Does this MCP server allow agents to create new DataRobot projects?

No. The available tools—listprojects, getproject, listmodels, etc.—are all for observation. The server provides read-only access to your DataRobot environment.

Let AI agents debate and manage your DataRobot models using AutoGen's multi-agent conversation framework.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect DataRobot MCP to AutoGen

Create your Vinkius account to connect DataRobot 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 DataRobot with AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Run Multi-Agent Model Audits

Equip your agents with tools to inspect your DataRobot work, like `list_deployments` and `get_model`. You can set up one agent as an 'Auditor' and another as an 'Operator' to create a system of checks and balances. Here's how it plays out in AutoGen: The Auditor agent uses `list_models` to find models with drift warnings. It presents its findings. The Operator agent then discusses the findings and proposes a monitoring plan. They converse until they agree on a resolution.

Debate Project Configurations with AutoGen

This MCP Server provides the raw information your agent team needs, with tools to see projects and datasets (`list_projects`, `list_datasets`). This becomes the shared context for their conversation. Instead of one agent making a decision, you can have a 'Data Hygiene' agent use `list_datasets` to find unused data. It can then start a conversation with a 'Project Manager' agent to decide if those datasets should be flagged for archival. The final decision comes from their collaboration.

Achieve Consensus on MLOps Issues

Give a team of agents visibility into your DataRobot deployments. They can check what’s running and how it’s configured with tools like `get_deployment`. In an AutoGen setup, this gets interesting. You could have one agent focused on performance and another on cost. The performance agent uses `get_deployment` to check prediction latency, while the cost agent checks the instance type. They then debate whether the resource allocation makes sense, reaching a consensus instead of a unilateral decision.

Setup guide

Set up DataRobot 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 DataRobot 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="DataRobot_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

result = await agent.run("List recent DataRobot 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="DataRobot_assistant",
        model_client=OpenAIChatCompletionClient(model="gpt-4o"),
        workbench=workbench,
    )

    result = await agent.run("List recent DataRobot 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 DataRobot. 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 DataRobot 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 DataRobot MCP in AutoGen

First, provide the DataRobot tools from this MCP server to both agents. Then, define their roles in their system messages—one as an analyst, one as a reviewer. Finally, give them a task like, 'Review the active deployments and report any issues.'

Yes. While the agent can't make changes itself, it can use tools like `get_project` to analyze a project's state. It can then formulate a detailed plan for a human to execute, like recommending a model for retraining, and present it as the outcome of its conversation.

It's best for problems without a single right answer. Use it for tasks like root cause analysis of a failing deployment, debating the priority of different projects, or having agents with different roles (e.g., security, performance) audit your setup.

No. The available tools—`list_projects`, `get_project`, `list_models`, etc.—are all for observation. The server provides read-only access to your DataRobot environment.

Only the agents you configure. This server passes DataRobot deployment metadata to your agents inside Vinkius's secure sandbox. Each tool call is an isolated, ephemeral process, and access is gated by your private token.

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