Does this MCP let me see the underlying database structure?

Yes. You can use the list_databases capability to see all connected data sources, and then use list_datasets to inventory the specific tables available for analysis.

Is this just a dashboard viewer, or can I run custom code?

It's much more than a viewer. You can run raw SQL queries using execute_sql_query. This lets you perform ad-hoc data investigations that aren't covered by existing dashboards.

What kind of data can I query?

The data depends on what's connected to your Superset instance. You first need to use the capabilities to list available databases and datasets to know what's there.

Do I need to be a developer to use this?

No. You just need to know what data you're looking for. You can ask your agent to audit the system, and then ask it to run the query for you.

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

Yes. The execute_sql_query capability 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.

An astronaut overseeing a futuristic data hub

Download PDF Markdown Version

Connect Apache Superset to ChatGPT, Claude and Gemini

Set it up once and it works in ChatGPT, Claude, Cursor, and any other client you love. It all runs safely in the background, so you can relax and focus on what really matters. Run complex data queries without leaving your chat environment.

Ask AI about this Connector

Developed, maintained, and hosted by Vinkius.

MCP VERIFIED · PRODUCTION READY · VINKIUS GUARANTEED

Waiting for input…

Works with modern AI clients that support MCP, including ChatGPT, Claude, Cursor, and more.

Your AI does the work. We keep it safe and sound.

No other AI tool gives you this. Your workflow runs in the client you already love, your account stays protected, and you decide what the agent can and cannot do. It is the whole reason to make the switch.

Each Connector lives inside our infrastructure, the same place where your workflow runs. The three things below are already part of it, working quietly in the background so you never have to think about them. Nothing to add, nothing to set up, nothing to worry about.

V8 Isolate01

Each Connector runs inside its own sealed environment.

Each Connector runs inside its own sealed V8 runtime — no access to your files, your system, or other servers. A Connector never sees past its own request.

Kill Switch02

One switch stops every agent. Instantly.

One action deactivates every Connector, revokes every token, and ends every session at once. AI Governance keeps the record.

FinOps per User03

Spending limits that pause instead of surprise.

Every user keeps their own connections and credentials, isolated from everyone else. Anything that would cross your spending limit is held for your approval, not billed.

Three controls, built into the layer your AI connects through.

Curated set · 7 capabilities

We ship only the actions that matter.

Capability set01 / 02

01-04

4 capabilities in this set.

Part of 7 available through Apache Superset.

01
Execute SQL query
Provide a database ID and the SQL statement. Executes a SQL query via SQL Lab
02
Get chart details
Retrieves details for a specific chart
03
Get dashboard details
Retrieves details for a specific dashboard
04
List charts
Lists all charts (slices) in Superset

Capability set02 / 02

05-07

3 capabilities in this set.

Part of 7 available through Apache Superset.

05
List dashboards
Lists all available dashboards in Apache Superset
06
List databases
Lists connected data source connections
07
List datasets
Lists all datasets available for analysis

Real work

What teams actually run

Debugging a Metric

A data scientist needs to know why a dashboard number is wrong. They ask the AI to get the chart details, pinpointing the exact metric calculation.

Pre-Report Data Check

A product manager needs to know if a new feature will affect sales. They ask the AI to run a SQL query filtering for the specific date range.

Inventory Audit

A data engineering lead needs to know what data sources are available. They ask the AI to list all connected databases and datasets.

Quick Market Analysis

A business analyst wants to see the top 5 product categories by revenue. They simply ask the AI to execute the necessary SQL query.

Automate a task

Put Apache Superset to work on one thing.

Step-by-step automations your AI runs through this Connector: the workflow, the prompts to start with, and the exact capabilities behind each move.

How to inventory data sources

One connector, every AI

Apache Superset works with the most popular AI clients.

These are the most popular clients, each with a step-by-step guide: one link, set up once, with governance and visibility built in. And because everything runs on the MCP standard, the same connection also works in any other compatible client — nothing to rebuild.

Building your own app? The connector is yours to use.

You don't need a client to put Apache Superset to work: the same hosted connection plugs into your own applications and agent code, with the same governance on every request. Build with it, chat with it — one connection for both.

Observed, not estimated

861ms average. Fast in production.

Apache Superset is checked daily against the live service.

Daily averagePeak 1037ms

Oct 3Today

Fastest day: 641ms
Slowest day: 1037ms
14-day trend: Stable+2%

Connect your client

One URL. Every client.

Activate the Connector, copy your link, and paste it into the client you already use. 7 capabilities arrive ready to run.

Preview access · not provider authentication

The vk_preview_* token belongs to Vinkius preview infrastructure. It lets Claude discover and display the capabilities of Apache Superset, so you can see the experience inside your AI.

It does not authenticate your account with Apache Superset. Actions requiring credentials or live account data may not run until you activate the Connector and authorize the service.

Apache Superset Connector

You're all set. Choose your MCP client and follow the setup instructions.

Connector linkhttps://edge.vinkius.com/vk_preview_gwYe1NYA9B8gFp8lQ7hoG8Zq04EdrBNzR1eq1ypu/mcp

Claude Desktop

Follow the steps below to connect in seconds.

1In Claude Desktop, open Settings → Connectors.
2Click “Add custom connector” and paste the connector link above as the remote MCP server URL.
3Click Add and start a new chat — Apache Superset capabilities are ready to use.

Configuration · claude_desktop_config.jsonCopy

{
  "mcpServers": {
    "apache-superset-mcp": {
      "url": "https://edge.vinkius.com/vk_preview_gwYe1NYA9B8gFp8lQ7hoG8Zq04EdrBNzR1eq1ypu/mcp"
    }
  }
}

Claude
ChatGPT
Cursor
VS Code
Windsurf
Claude Code
JetBrains
Cline

Step-by-step instructions for each client are in the guide. How to connect

Guided setup for Claude? Set up Apache Superset in Claude and other AIs

See all the AI clients this connector works with ↑

Who it's for

Built for the work Apache Superset owners hand off.

This MCP is essential for data teams who need to audit, test, or extract data without logging into the Superset UI. It lets you treat your entire BI platform like a queryable API, speeding up analysis and debugging.

01
Data Analysts
Use it to quickly compose complex SQL checks and extract dataset contexts for reports.
02
Product Managers
Check dashboard parameters and inspect metric shifts conversationally, without needing to learn the BI navigation.
03
Data Engineering Leads
Audit operational reports safely, probing exact table usage or testing semantic datasets to isolate anomalies.

FAQ

Questions Apache Superset owners ask.

01
Does this MCP let me see the underlying database structure?
Yes. You can use the list_databases capability to see all connected data sources, and then use list_datasets to inventory the specific tables available for analysis.
02
Is this just a dashboard viewer, or can I run custom code?
It's much more than a viewer. You can run raw SQL queries using execute_sql_query. This lets you perform ad-hoc data investigations that aren't covered by existing dashboards.
03
What kind of data can I query?
The data depends on what's connected to your Superset instance. You first need to use the capabilities to list available databases and datasets to know what's there.
04
Do I need to be a developer to use this?
No. You just need to know what data you're looking for. You can ask your agent to audit the system, and then ask it to run the query for you.
05
Can the AI query databases connected to Superset, such as Presto or Redshift?
Yes. The execute_sql_query capability runs queries through Superset's SQL Lab API, which routes them to whichever database engine you have configured. Presto, Redshift, PostgreSQL, and others.
06
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.
07
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.

Explore

More in Brain Trust

Connect Apache Superset to Claude, Cursor, ChatGPT & more

Your AI does the work. We keep it safe and sound.

Each Connector runs inside its own sealed environment.

One switch stops every agent. Instantly.

Spending limits that pause instead of surprise.

We ship only the actions that matter.

01-04

Execute SQL query

Get chart details

Get dashboard details

List charts

05-07

List dashboards

List databases

List datasets

What teams actually run

Debugging a Metric

Pre-Report Data Check

Inventory Audit

Quick Market Analysis

Building your own app? The connector is yours to use.

Apache Superset Connector

Claude Desktop

Data Analysts

Product Managers

Data Engineering Leads

Does this MCP let me see the underlying database structure?

Is this just a dashboard viewer, or can I run custom code?

What kind of data can I query?

Do I need to be a developer to use this?

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

Are dashboard access permissions enforced when using the MCP server?

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

Metabase (Business Intelligence & Analytics) AI Connector

Looker (Business Intelligence & Data) AI Connector

Mode (Collaborative Data Platform) AI Connector

data.world AI Connector

Suggestions

Data Pipeline Prover AI Connector

Databox AI Connector

Tableau AI Connector

Hevo Data (ETL & Data Pipeline) AI Connector