How to Use the Apache Superset MCP in OpenAI Agents SDK

Q: How do I handle performance when listing large numbers of charts?

Use listcharts and listdatasets to get high-level lists first. The agent can then target specific IDs with getchartdetails rather than pulling all visual data at once.

Run safe SQL queries and pull BI dashboards directly inside your OpenAI Agents SDK workflows.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Apache Superset MCP to OpenAI Agents SDK

Create your Vinkius account to connect Apache Superset to OpenAI Agents SDK 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 Apache Superset with OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Query data securely via SQL Lab

Your agent can write and run queries directly against your warehouse using `execute_sql_query`. It bypasses manual exports, letting the model pull raw numbers right when a decision depends on them. Because this runs through your secure database connections, you control the access. The agent queries only what is allowed, pulling raw tables into the context window for immediate analysis.

Inspect live dashboards from your MCP Server

Instead of guessing where the data lives, your agent uses `list_dashboards` and `list_datasets` to map out your Superset workspace. It pinpoints the exact slices of data it needs without human hand-holding. Once it finds the right asset, the agent calls `get_dashboard_details` or `get_chart_details` to read the actual layout and metrics. This saves hours of manual dashboard digging.

Coordinate multi-agent BI workflows in OpenAI Agents SDK

Build dedicated data-analyst agents that hand off tasks to your visualization agents. One agent lists the connections with `list_databases`, while another runs the heavy analytical lifting. This setup works natively with the SDK's built-in guardrails and our MCP Server. You can intercept a call to `execute_sql_query` to verify the syntax or check permissions before the agent hits your database.

Setup guide

Set up Apache Superset MCP in OpenAI Agents SDK

Prerequisites

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

1

Install the SDK

Run pip install openai-agents to install the OpenAI Agents SDK. The MCP integration is built-in — no extra dependencies needed.
2

Connect via SSE transport

Use MCPServerSse with your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. The SDK auto-discovers all Apache Superset tools at runtime.
3

Create your Agent

Pass the MCP to Agent(mcp_servers=[server]). The agent receives Apache Superset tools as native definitions — JSON schemas resolve automatically.
4

Run the agent

Call Runner.run(agent, prompt) to execute. The agent invokes the appropriate Apache Superset tools and returns structured results. Copy the full example on the right to get started.

agent.py

import asyncio
from agents import Agent, Runner
from agents.mcp import MCPServerSse

async def main():
    async with MCPServerSse(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ) as server:
        agent = Agent(
            name="Apache Superset Agent",
            instructions="You have access to Apache Superset tools.",
            mcp_servers=[server],
        )
        result = await Runner.run(agent, "List recent transactions")
        print(result.final_output)

asyncio.run(main())

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 Apache Superset. 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 Apache Superset 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 Apache Superset MCP in OpenAI Agents SDK

Install the package, then configure your MCP connection with your Vinkius HTTP endpoint. Pass this server instance inside the `mcp_servers` list when initializing your agent. Set `cacheToolsList=True` to speed up tool discovery.

Yes. You enforce this at two levels: database permissions in Superset and validation guardrails inside your Python code. The agent can only execute what its Superset credentials allow, and you can intercept `execute_sql_query` calls before they run.

It does. You can have a router agent identify a data request, hand it off to a specialized SQL analyst agent that uses `execute_sql_query`, and then return the results to a summarizer agent.

Use `list_charts` and `list_datasets` to get high-level lists first. The agent can then target specific IDs with `get_chart_details` rather than pulling all visual data at once.

Your database credentials never leave Superset. The server only passes SQL statements to the Superset API and returns raw query results, which run inside Vinkius's isolated sandbox environment.

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