How to Use the Cube.dev MCP in AutoGen

Q: Can AutoGen agents manage multiple Cube.dev environments?

Yes. With a CUBECLOUDAPIKEY, your agents can call listenvironments and listdeployments to find the correct instance. This MCP Server lets your agents call these endpoints dynamically.

Q: How do AutoGen agents handle Cube.dev pre-aggregation failures?

An AutoGen monitoring agent checks getpreaggregationjobstatus. If it detects a failure, it alerts a recovery agent to call triggerpreaggregationjob and restart the Cube.dev build process.

Q: What security controls protect my Cube.dev data inside AutoGen?

Your JWT tokens generated via generatemetatoken and raw SQL executions remain local. The MCP server handles all authentication over ephemeral, secure channels, ensuring no analytical schemas are exposed.

Deploy AutoGen agents that debate query plans, verify schemas, and trigger Cube.dev pre-aggregations in parallel.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Cube.dev MCP to AutoGen

Create your Vinkius account to connect Cube.dev 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 Cube.dev with AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Debate query strategies using this MCP Server

Let your AutoGen agents argue over the best way to fetch a Cube.dev metric. One agent can call `list_entities` to find candidate Cube.dev cubes, while another uses `get_entity` to audit the dimensions. The AutoGen agents deliberate over the Cube.dev schema definitions before writing a single query. This AutoGen consensus loop prevents bad requests and ensures your agents use the correct, pre-defined Cube.dev business logic.

Validate SQL performance through AutoGen consensus

Avoid running heavy, unoptimized queries on your database through this Cube.dev MCP Server. An AutoGen performance agent can call `get_sql` to inspect the raw Cube.dev query plan, while an AutoGen data agent runs `convert_query` to check the REST format. If the Cube.dev query looks slow, the AutoGen agents refuse to run it. Once they agree it is safe, the executive AutoGen agent runs `execute_cube_sql` or `load_query` to fetch the clean, aggregated Cube.dev results.

Coordinate Cube.dev pre-aggregation builds in AutoGen

Manage complex Cube.dev cache builds with a team of AutoGen agents. One AutoGen agent monitors build status using `get_pre_aggregation_job_status`, while another triggers Cube.dev jobs via `trigger_pre_aggregation_job`. If a Cube.dev job fails, an AutoGen developer agent can inspect `list_data_sources` to check if a database connection is down. The AutoGen agents work together to resolve the Cube.dev issue before notifying the user.

Setup guide

Set up Cube.dev 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 Cube.dev 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="Cube.dev_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

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

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

One agent translates the user request into a query format using `convert_query`. A second agent reviews the Cube.dev schema via `get_meta` to ensure it is valid before executing `load_query`.

Yes. With a CUBE_CLOUD_API_KEY, your agents can call `list_environments` and `list_deployments` to find the correct instance. This MCP Server lets your agents call these endpoints dynamically.

An AutoGen monitoring agent checks `get_pre_aggregation_job_status`. If it detects a failure, it alerts a recovery agent to call `trigger_pre_aggregation_job` and restart the Cube.dev build process.

Yes. You can register specific tools, like giving only the supervisor AutoGen agent access to `execute_cube_sql` while keeping other agents limited to read-only metadata tools.

Your JWT tokens generated via `generate_meta_token` and raw SQL executions remain local. The MCP server handles all authentication over ephemeral, secure channels, ensuring no analytical schemas are exposed.

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