Can the AI query databases connected to Superset, such as Presto or Redshift?

Yes. The `execute_sql_query` tool runs queries through Superset's SQL Lab API, which routes them to whichever database engine you have configured — Presto, Redshift, PostgreSQL, and others.

Are dashboard access permissions enforced when using the MCP server?

Yes. All requests are authenticated with your `SUPERSET_ACCESS_TOKEN`, so only the dashboards, charts, and datasets your token has access to will be visible to the AI.

Can the AI run write queries (INSERT, UPDATE, DELETE) via SQL Lab?

It depends on your Superset database connection settings. By default, SQL Lab connections are read-only. Write access must be explicitly enabled per database in the Superset admin panel.

Apache Superset MCP Server for OpenAI Agents SDK 7 tools — connect in under 2 minutes

Name: Apache Superset
Availability: InStock
Author: Vinkius

openai.github.io/openai-agents-python/mcp

Built by Vinkius GDPR 7 Tools SDK

The OpenAI Agents SDK enables production-grade agent workflows in Python. Connect Apache Superset through Vinkius and your agents gain typed, auto-discovered tools with built-in guardrails. no manual schema definitions required.

Get MCP Server for AI Agents

ASK AI ABOUT THIS MCP SERVER

Open in ChatGPT Open in Claude Open in Perplexity

Vinkius supports streamable HTTP and SSE.

python

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

async def main():
    # Your Vinkius token. get it at cloud.vinkius.com
    async with MCPServerStreamableHttp(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ) as mcp_server:

        agent = Agent(
            name="Apache Superset Assistant",
            instructions=(
                "You help users interact with Apache Superset. "
                "You have access to 7 tools."
            ),
            mcp_servers=[mcp_server],
        )

        result = await Runner.run(
            agent, "List all available tools from Apache Superset"
        )
        print(result.final_output)

asyncio.run(main())

Fully ManagedVinkius Servers

60%Token savings

High SecurityEnterprise-grade

IAMAccess control

EU AI ActCompliant

DLPData protection

V8 IsolateSandboxed

Ed25519Audit chain

<40msKill switch

Stream every event to Splunk, Datadog, or your own webhook in real-time

* Every MCP server runs on Vinkius-managed infrastructure inside AWS - a purpose-built runtime with per-request V8 isolates, Ed25519 signed audit chains, and sub-40ms cold starts optimized for native MCP execution. See our infrastructure

About Apache Superset MCP Server

Empower your conversational AI with deep Business Intelligence access by integrating the Apache Superset MCP connector. Seamlessly navigating complex data ecosystems natively from your LLM text-interface, your agent can comprehensively index your analytical infrastructure—spanning from high-level operational dashboards down to specific raw database connections. Instantly run ad-hoc data investigations utilizing internal SQL Lab queries, retrieve explicit graph metadata, and dynamically aggregate critical business insights without abandoning your development environment.

The OpenAI Agents SDK auto-discovers all 7 tools from Apache Superset through native MCP integration. Build agents with built-in guardrails, tracing, and handoff patterns. chain multiple agents where one queries Apache Superset, another analyzes results, and a third generates reports, all orchestrated through Vinkius.

What you can do

Discover Analytics Surfaces — Audit your entire BI portal intuitively by executing list_dashboards and retrieve exact metric configurations invoking get_dashboard_details.
Graph & Dataset Inspection — Inventory active metrics logic seamlessly via list_charts (or specify via get_chart_details) and map semantic layers dynamically performing list_datasets.
Uncover Data Architectures — Examine exact backend storage clusters accurately parsing data availability via list_databases natively.
Direct SQL Processing — Interface with your central storage matrices seamlessly by generating raw extractions securely via execute_sql_query targeting specific analytic connections.

The Apache Superset MCP Server exposes 7 tools through the Vinkius. Connect it to OpenAI Agents SDK in under two minutes — no API keys to rotate, no infrastructure to provision, no vendor lock-in. Your configuration, your data, your control.

How to Connect Apache Superset to OpenAI Agents SDK via MCP

Follow these steps to integrate the Apache Superset MCP Server with OpenAI Agents SDK.

Install the SDK

Run pip install openai-agents in your Python environment

Replace the token

Replace [YOUR_TOKEN_HERE] with your Vinkius token from cloud.vinkius.com

Run the script

Save the code above and run it: python agent.py

Explore tools

The agent will automatically discover 7 tools from Apache Superset

Why Use OpenAI Agents SDK with the Apache Superset MCP Server

OpenAI Agents SDK provides unique advantages when paired with Apache Superset through the Model Context Protocol.

Native MCP integration via `MCPServerSse`, pass the URL and the SDK auto-discovers all tools with full type safety

Built-in guardrails, tracing, and handoff patterns let you build production-grade agents without reinventing safety infrastructure

Lightweight and composable: chain multiple agents and MCP servers in a single pipeline with minimal boilerplate

First-party OpenAI support ensures optimal compatibility with GPT models for tool calling and structured output

Apache Superset + OpenAI Agents SDK Use Cases

Practical scenarios where OpenAI Agents SDK combined with the Apache Superset MCP Server delivers measurable value.

Automated workflows: build agents that query Apache Superset, process the data, and trigger follow-up actions autonomously

Multi-agent orchestration: create specialist agents. one queries Apache Superset, another analyzes results, a third generates reports

Data enrichment pipelines: stream data through Apache Superset tools and transform it with OpenAI models in a single async loop

Customer support bots: agents query Apache Superset to resolve tickets, look up records, and update statuses without human intervention

Apache Superset MCP Tools for OpenAI Agents SDK (7)

These 7 tools become available when you connect Apache Superset to OpenAI Agents SDK via MCP:

execute_sql_query

Provide a database ID and the SQL statement. Executes a SQL query via SQL Lab

get_chart_details

Retrieves details for a specific chart

get_dashboard_details

Retrieves details for a specific dashboard

list_charts

Lists all charts (slices) in Superset

list_dashboards

Lists all available dashboards in Apache Superset

list_databases

Lists connected data source connections

list_datasets

Lists all datasets available for analysis

Example Prompts for Apache Superset in OpenAI Agents SDK

Ready-to-use prompts you can give your OpenAI Agents SDK agent to start working with Apache Superset immediately.

"List all my Superset dashboards and tell me which one was updated most recently."

"Check our database connections to see if our Postgres 'SalesDB' is active."

"Run a SQL Lab query to show the top 5 product categories by revenue in SalesDB."

Troubleshooting Apache Superset MCP Server with OpenAI Agents SDK

Common issues when connecting Apache Superset to OpenAI Agents SDK through the Vinkius, and how to resolve them.

MCPServerStreamableHttp not found

Ensure you have the latest version: pip install --upgrade openai-agents

Agent not calling tools

Make sure your prompt explicitly references the task the tools can help with.

Apache Superset + OpenAI Agents SDK FAQ

Common questions about integrating Apache Superset MCP Server with OpenAI Agents SDK.

How does the OpenAI Agents SDK connect to MCP?

Use MCPServerSse(url=...) to create a server connection. The SDK auto-discovers all tools and makes them available to your agent with full type information.