Using AI with Superset

Superset supports AI assistants through the Model Context Protocol (MCP). Connect Claude, ChatGPT, or other MCP-compatible clients to explore your data, build charts, create dashboards, and run SQL -- all through natural language.

info

Requires Superset 5.0+. Your admin must enable and deploy the MCP server before you can connect. See the MCP Server admin guide for setup instructions.

---

What Can AI Do with Superset?

Explore Your Data

Ask your AI assistant to browse what's available in your Superset instance:

• List datasets -- see all datasets you have access to, with filtering and search
• Get dataset details -- column names, types, available metrics, and filters
• List charts and dashboards -- find existing visualizations by name or keyword
• Get chart and dashboard details -- understand what a chart shows, its query, and configuration

Example prompts:

"What datasets are available?" "Show me the columns in the sales_orders dataset" "Find dashboards related to revenue"

Build Charts

Describe the visualization you want and AI creates it for you:

• Create charts from natural language -- describe what you want to see and AI picks the right chart type, metrics, and dimensions
• Preview before saving -- generate_chart defaults to save_chart=False, showing the chart in Explore before it's committed. Ask AI to save once you're satisfied.
• Modify existing charts -- update_chart also supports preview mode so you can review changes before saving
• Get Explore links -- open any chart in Superset's Explore view for further refinement

Example prompts:

"Create a bar chart showing monthly revenue by region from the sales dataset" "Update chart 42 to use a line chart instead" "Give me a link to explore this chart further"

Create Dashboards

Build dashboards from a collection of charts:

• Generate dashboards -- create a new dashboard with a set of charts, automatically laid out
• Add charts to existing dashboards -- place a chart on an existing dashboard with automatic positioning

Example prompts:

"Create a dashboard called 'Q4 Sales Overview' with charts 10, 15, and 22" "Add the revenue trend chart to the executive dashboard"

Run SQL Queries

Execute SQL directly through your AI assistant:

• Run queries -- execute SQL with full Superset RBAC enforcement (you can only query data your roles allow)
• Open SQL Lab -- get a link to SQL Lab pre-populated with a query, ready to run and explore

Example prompts:

"Run this query: SELECT region, SUM(revenue) FROM sales GROUP BY region" "Open SQL Lab with a query to show the top 10 customers by order count"

Analyze Chart Data

Pull the raw data behind any chart:

• Get chart data -- retrieve the data a chart displays, with support for JSON, CSV, and Excel export formats
• Inspect results -- useful for verifying what a visualization shows or feeding data into other tools

Example prompts:

"Get the data behind chart 42" "Export chart 15 data as CSV"

Check Instance Status

• Health check -- verify your Superset instance is up and the MCP connection is working
• Instance info -- get high-level statistics about your Superset instance (number of datasets, charts, dashboards)

Example prompts:

"Is Superset healthy?" "How many dashboards are in this instance?"

---

Connecting Your AI Client

Once your admin has deployed the MCP server, connect your AI client using the instructions below.

Claude Desktop

Edit your Claude Desktop config file:

• macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
• Windows: %APPDATA%\Claude\claude_desktop_config.json
• Linux: ~/.config/Claude/claude_desktop_config.json

{
  "mcpServers": {
    "superset": {
      "url": "http://localhost:5008/mcp"
    }
  }
}

Restart Claude Desktop. The hammer icon in the chat bar confirms the connection.

If your admin has enabled JWT authentication, you may need to include a token:

{
  "mcpServers": {
    "superset": {
      "command": "npx",
      "args": [
        "-y",
        "mcp-remote@latest",
        "http://your-superset-host:5008/mcp",
        "--header",
        "Authorization: Bearer YOUR_TOKEN"
      ]
    }
  }
}

Claude Code (CLI)

Add to your project's .mcp.json:

{
  "mcpServers": {
    "superset": {
      "type": "url",
      "url": "http://localhost:5008/mcp"
    }
  }
}

ChatGPT

1. Click your profile icon > Settings > Apps and Connectors
2. Enable Developer Mode in Advanced Settings
3. In the chat composer, press + > Add sources > App > Connect more > Create app
4. Enter a name and your MCP server URL
5. Click I understand and continue

info

ChatGPT MCP connectors require a Pro, Team, Enterprise, or Edu plan.

Ask your admin for the MCP server URL and any authentication tokens you need.

---

Tips for Best Results

• Be specific -- "Create a bar chart of monthly revenue by region from the sales dataset" works better than "Make me a chart"
• Start with exploration -- ask what datasets and charts exist before creating new ones
• Review AI-generated content -- always check chart configurations and SQL before saving or sharing
• Use Explore for refinement -- ask AI for an Explore link, then fine-tune interactively in the Superset UI
• Check permissions if you get errors -- AI respects Superset's RBAC, so you can only access data your roles allow

---

Available Tools Reference

Exploration & Discovery

Tool	Description
health_check	Verify the MCP server is running and connected
get_instance_info	Get instance statistics (dataset, chart, dashboard counts)
get_home_page_info	Get a summary of home page resources
get_superset_config_info	Expose active Superset configuration details
get_schema	Discover available charts, datasets, and dashboards with schema info
list_recent_activity	List recent activity from the activity feed
list_chart_types	Enumerate available chart types

Datasets

Tool	Description
list_datasets	List datasets with filtering and search
get_dataset_info	Get dataset metadata (columns, metrics, filters)
get_dataset_by_name	Look up a dataset by name

Charts

Tool	Description
list_charts	List charts with filtering and search
get_chart_info	Get chart metadata and configuration
get_chart_by_name	Look up a chart by name
get_chart_data	Retrieve chart data (JSON, CSV, or Excel)
get_chart_data_by_url	Retrieve chart data from a chart URL
get_chart_data_by_explore_url	Retrieve chart data from an Explore URL
get_chart_preview	Generate a chart preview (URL, ASCII, table, or Vega-Lite)
get_chart_thumbnail	Fetch the cached thumbnail image for a chart
generate_chart	Create a new chart from a specification (defaults to preview mode — review before saving)
update_chart	Modify an existing chart's configuration (supports save_chart=False for preview mode)
update_chart_preview	Update a cached chart preview without saving
delete_chart	Delete a chart
list_chart_owners	List the owners of a chart
generate_explore_link	Generate an Explore URL for interactive visualization
get_explore_link	Get an Explore link from MCP context
get_explore_link_by_url	Get an Explore link from a chart URL
get_explore_thumbnail	Fetch the cached thumbnail for an Explore view
open_explore_link	Open an Explore link in the browser

Dashboards

Tool	Description
list_dashboards	List dashboards with filtering and search
get_dashboard_info	Get dashboard metadata and layout
get_dashboard_by_name	Look up a dashboard by name
get_dashboard_thumbnail	Fetch the cached thumbnail image for a dashboard
generate_dashboard	Create a new dashboard with specified charts
update_dashboard	Modify an existing dashboard's metadata
delete_dashboard	Delete a dashboard
add_chart_to_existing_dashboard	Add a chart to an existing dashboard
remove_chart_from_dashboard	Remove a chart from a dashboard
move_chart_to_dashboard	Move a chart from one dashboard to another
update_chart_position	Reposition a chart within a dashboard
list_charts_in_dashboard	List all charts within a specific dashboard
list_dashboard_owners	List the owners of a dashboard
open_dashboard	Open a dashboard in the browser
add_filter_to_dashboard	Add a native filter to a dashboard
list_dashboard_filters	List native filters on a dashboard
update_dashboard_filter	Update a native filter on a dashboard
delete_dashboard_filter	Remove a native filter from a dashboard
get_dashboard_filter_info	Get details about a specific dashboard filter
set_tab_order	Reorder tabs in a tabbed dashboard
create_tab	Add a new tab to a tabbed dashboard
delete_tab	Remove a tab from a tabbed dashboard
rename_tab	Rename a dashboard tab

SQL & Saved Queries

Tool	Description
execute_sql	Run a SQL query with RBAC enforcement
open_sql_lab_with_context	Open SQL Lab with a pre-populated query
open_sql_in_browser	Open a SQL query in the browser
list_saved_queries	List saved SQL queries from SQL Lab
create_saved_query	Create a new saved query
update_saved_query	Update an existing saved query
delete_saved_query	Delete a saved query

Databases

Tool	Description
list_databases	List configured database connections
get_database_info	Get details about a specific database connection
get_database_dialect_info	Get dialect details for a database

Reports & Alerts

Tool	Description
list_reports	List configured alerts and reports
create_report	Create a new alert or report
update_report	Update an existing alert or report
delete_report	Delete a report
get_report_info	Get details about a specific report

Users, Roles & Permissions

Tool	Description
get_users	List users in the Superset instance
list_roles	List all roles
get_role_info	Get details and permissions for a specific role
list_permissions	List all available permissions
get_permission_info	Get details about a specific permission

---

Troubleshooting

"Connection refused" or "Cannot connect"

• Confirm the MCP server URL with your admin
• For Claude Desktop: fully quit the app (not just close the window) and restart after config changes
• Check that the URL path ends with /mcp (e.g., http://localhost:5008/mcp)

"Permission denied" or missing data

• Superset's RBAC controls what you can access through AI, just like in the Superset UI
• Ask your admin to verify your roles and permissions
• Try accessing the same data through the Superset web UI to confirm your access

"Response too large"

• Ask for smaller result sets: use filters, reduce page_size, or request specific columns
• Example: "Show me the top 10 rows from the sales dataset" instead of "Show me all sales data"

AI doesn't see Superset tools

• Verify the connection in your AI client (e.g., the hammer icon in Claude Desktop)
• Ask the AI "What Superset tools are available?" to confirm the connection
• Restart your AI client if you recently changed the configuration