How to Use the Databox MCP in AutoGen

Q: How do my AutoGen agents get access to Databox tools?

Use the mcpservertools function from the autogen-ext package. It fetches all available Databox tools and prepares them to be passed directly into an AssistantAgent constructor.

Let multiple AutoGen agents debate and manage your Databox account. Build consensus for complex data operations.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Databox MCP to AutoGen

Create your Vinkius account to connect Databox 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 Databox with AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Debate changes before they happen

This isn't a single agent following orders. With AutoGen, you create a team of agents that discuss the best way to manage Databox. One agent might propose creating a new dataset with `create_dataset` for a marketing campaign. A second 'finance' agent could then challenge that idea, using `get_storage_statistics` to argue about costs. They converse, propose alternatives, and reach a consensus before any action is taken. You're building a system that thinks before it acts.

Let AutoGen agents audit each other's work

Set up a "worker" agent with permission to `push_metrics_data` and an "auditor" agent with access to `list_activity_logs`. The worker reports its actions to the group chat. The auditor agent can then independently check the logs to confirm the worker's report. This creates a self-policing system right within your AutoGen conversation, making your Databox interactions more reliable.

Find problems through conversation

Have one agent periodically call `list_dataset_metrics` for key datasets. It posts the results to the group. A second, specialized "analyst" agent reviews these metrics. If it spots a sudden drop or an unusual spike, it can flag the anomaly in the chat and suggest another agent investigate further using `get_dataset_details`. The agents work together to find issues you might miss.

Setup guide

Set up Databox 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 Databox 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="Databox_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

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

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

Use the `mcp_server_tools` function from the `autogen-ext` package. It fetches all available Databox tools and prepares them to be passed directly into an `AssistantAgent` constructor.

Yes, and that's the point. You can create one agent and only give it the `list_datasets` tool, and create a second 'admin' agent with access to `delete_dataset`. They then have to convince each other to act.

An agent proposes a plan in the group chat, like "I need to create a new data source for our project." If other agents agree or a human user approves, it will then select and call the `create_data_source` tool.

Yes. The conversation log in AutoGen shows which agent called which tool and with what arguments. The McpToolAdapter handles the call, and the results are posted back into the chat for all agents to see.

Vinkius uses a zero-trust model for this MCP Server. Every API call from your AutoGen agents to access Databox user profiles or metrics data is individually authenticated, and the server itself runs in a completely isolated instance.

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