← Back to Superset MCP Server

Install Superset MCP Server

Pick your client, copy the command, done.

database
Manual setup required. The maintainer's config contains paths only you know - edit the placeholders below before adding it to Claude Code.
1

Prepare the server locally

Run this once before adding it to Claude Code.

git clone <repository-url>
cd superset-mcp
npm install
npm run build
2

Register it in Claude Code

claude mcp add -e "SUPERSET_URL=${SUPERSET_URL}" -e "SUPERSET_USERNAME=${SUPERSET_USERNAME}" -e "SUPERSET_PASSWORD=${SUPERSET_PASSWORD}" superset-mcp -- node /path/to/superset-mcp/dist/index.js

Replace any placeholder paths in the command with the real path on your machine.

Required:SUPERSET_URLSUPERSET_USERNAMESUPERSET_PASSWORD+ 1 optional

Environment Variables

Set these before running Superset MCP Server.

VariableDescriptionRequired
SUPERSET_URLURL of the Superset instanceYes
SUPERSET_USERNAMEUsername for Superset authenticationYes
SUPERSET_PASSWORDPassword for Superset authenticationYes
MCP_PORTPort for the MCP serverNo

Available Tools (14)

Once configured, Superset MCP Server gives your AI agent access to:

list_dashboardsGet all available dashboards.
get_dashboardGet detail of a dashboard including its charts.
dashboard_id
create_dashboardCreate a new dashboard.
title
add_chart_to_dashboardAdd a single chart to a dashboard.
dashboard_idchart_id
add_charts_to_dashboardAdd multiple charts to a dashboard.
dashboard_idchart_ids
list_chartsGet all available charts.
get_chartGet detail configuration of a chart.
chart_id
get_chart_dataFetch data from a chart.
chart_id
create_chartCreate a new chart with manual configuration.
dataset_idchart_typeconfig
create_chart_autoCreate a chart with auto-detection schema.
dataset_iddescription
list_datasetsGet all datasets or tables.
get_dataset_schemaGet column definitions of a dataset.
dataset_id
list_databasesGet all database connections.
execute_sqlExecute a SQL query against a database.
database_idsql

Try It Out

After setup, try these prompts with your AI agent:

→Create a bar chart for the sales_data dataset showing total revenue per month.
→Create a new dashboard named 'Sales Overview' and add a line chart for revenue and a pie chart by category.
→List all available datasets and get the schema for the 'customer_transactions' table.
→Execute a SQL query to find the top 10 products by sales volume from the database.
Prerequisites & system requirements
  • An MCP-compatible client (Claude Code, Cursor, Windsurf, Claude Desktop, or Codex)
  • Node.js 18+ with npm/npx installed
  • SUPERSET_URL — URL of the Superset instance
  • SUPERSET_USERNAME — Username for Superset authentication
  • SUPERSET_PASSWORD — Password for Superset authentication
Conare · memory for coding agents

Keep this setup from going cold

Save the docs, env vars, and workflow around Superset MCP Server in Conare so Claude Code, Codex, and Cursor remember it next time.

Remember this setup$npx conare@latest
← Superset MCP Server overview Browse database servers →