Provides full access to Apache Superset instances, enabling AI assistants to manage dashboards, charts, datasets, databases, and execute SQL queries through Superset's API.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@superset-mcp show me the top 5 dashboards by view count"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
MCP (Model Context Protocol) server for Apache Superset. Gives AI assistants full access to your Superset instance — dashboards, charts, datasets, databases, and SQL execution.
uv — Python package manager
Access to a running Apache Superset instance
Related MCP server: Zaturn
git clone <repo-url>
cd superset-mcpcp .env.example .envEdit .env:
SUPERSET_URL=http://your-superset-host:8088
SUPERSET_USERNAME=your-username
SUPERSET_PASSWORD=your-passworduv run superset-mcpYou should see the MCP server start without errors. Press Ctrl+C to stop.
Replace /ABSOLUTE/PATH/TO/superset-mcp with the actual path where you cloned the repo.
Add to ~/.claude/settings.json (or project-level .claude/settings.json):
{
"mcpServers": {
"superset": {
"command": "uv",
"args": ["--directory", "/ABSOLUTE/PATH/TO/superset-mcp", "run", "superset-mcp"],
"env": {
"SUPERSET_URL": "http://your-superset-host:8088",
"SUPERSET_USERNAME": "your-username",
"SUPERSET_PASSWORD": "your-password"
}
}
}
}Or run in terminal:
claude mcp add superset -- uv --directory /ABSOLUTE/PATH/TO/superset-mcp run superset-mcpAdd to ~/Library/Application Support/Claude/claude_desktop_config.json (macOS)
or %APPDATA%\Claude\claude_desktop_config.json (Windows):
{
"mcpServers": {
"superset": {
"command": "uv",
"args": ["--directory", "/ABSOLUTE/PATH/TO/superset-mcp", "run", "superset-mcp"],
"env": {
"SUPERSET_URL": "http://your-superset-host:8088",
"SUPERSET_USERNAME": "your-username",
"SUPERSET_PASSWORD": "your-password"
}
}
}
}Add to .cursor/mcp.json in your project or ~/.cursor/mcp.json globally:
{
"mcpServers": {
"superset": {
"command": "uv",
"args": ["--directory", "/ABSOLUTE/PATH/TO/superset-mcp", "run", "superset-mcp"],
"env": {
"SUPERSET_URL": "http://your-superset-host:8088",
"SUPERSET_USERNAME": "your-username",
"SUPERSET_PASSWORD": "your-password"
}
}
}
}Tool | Description |
| List all dashboards (with optional search) |
| Get a dashboard by ID or slug |
| Get all charts in a dashboard |
| Get all datasets used by a dashboard |
| Create a new dashboard |
| Update title, layout, metadata |
| Publish a draft dashboard |
| Duplicate a dashboard |
| Delete a dashboard |
Tool | Description |
| List all charts (with optional search) |
| Get a chart by ID or UUID |
| Fetch the latest data for a chart |
| Create a new chart |
| Update chart properties |
| Delete a chart |
Tool | Description |
| List all datasets |
| Get a dataset by ID or UUID |
| Create from a table or SQL query |
| Get existing or create new |
| Sync columns from source table |
| Update dataset properties |
| See which charts/dashboards use it |
| Delete a dataset |
Tool | Description |
| List all database connections |
| Get a database connection by ID |
| List schemas in a database |
| List tables in a schema |
| Get column info for a table |
| Get a SELECT * template for a table |
Tool | Description |
| Run a SQL query and get results |
| Pretty-print a SQL query |
| Estimate query cost (if supported) |
| List saved SQL queries |
| Save a SQL query |
Once connected to your AI assistant:
"List all published dashboards"
"Create a new dashboard called 'Sales Overview'"
"Show me all charts in dashboard 11"
"Run a SQL query on database 2: SELECT count() FROM orders"*
"What datasets are used by the 'Revenue' dashboard?"
"Create a bar chart using dataset 5 showing sales by region"
Create a copy of a dashboard.
Inputs: id_or_slug (required). Returns: object
Create a new chart.
Inputs: slice_name (required), viz_type (required), datasource_id (required), datasource_type, +3 more. Returns: object
Create a new dashboard.
Inputs: title (required), slug, published, json_metadata, +1 more. Returns: object
Create a dataset from a table or SQL query.
Inputs: database_id (required), table_name (required), schema, sql, +1 more. Returns: object
Delete a chart by ID.
Inputs: pk (required). Returns: object
Delete a dashboard by ID.
Inputs: pk (required). Returns: object
Delete a dataset by ID.
Inputs: pk (required). Returns: object
Estimate the cost of running a SQL query (supported databases only).
Inputs: database_id (required), sql (required), schema. Returns: object
Execute a SQL query and return results.
Inputs: database_id (required), sql (required), schema, limit. Returns: object
Format/pretty-print a SQL query.
Inputs: sql (required). Returns: object
Get a chart by ID or UUID.
Inputs: id_or_uuid (required). Returns: object
Fetch the latest data for a chart.
Inputs: pk (required). Returns: object
Get a single dashboard by ID or slug.
Inputs: id_or_slug (required). Returns: object
Get all charts in a dashboard.
Inputs: id_or_slug (required). Returns: object
Get all datasets used by a dashboard.
Inputs: id_or_slug (required). Returns: object
Get a database connection by ID.
Inputs: pk (required). Returns: object
Get a dataset by ID or UUID.
Inputs: id_or_uuid (required). Returns: object
Get an existing dataset or create it if it doesn't exist.
Inputs: database_id (required), table_name (required), schema. Returns: object
Get a SELECT * query for a table (with schema).
Inputs: database_id (required), table_name (required), schema. Returns: object
Get column metadata for a table.
Inputs: database_id (required), table_name (required), schema. Returns: object
List charts. Optionally filter by name.
Inputs: page, page_size, search. Returns: object
List dashboards. Optionally filter by title with search.
Inputs: page, page_size, search. Returns: object
List all database connections configured in Superset.
Inputs: page, page_size. Returns: object
List datasets (virtual or physical tables).
Inputs: page, page_size, search. Returns: object
List saved SQL queries.
Inputs: page, page_size. Returns: object
List all schemas in a database.
Inputs: database_id (required). Returns: object
List tables in a database schema.
Inputs: database_id (required), schema. Returns: object
Set a dashboard as published.
Inputs: pk (required). Returns: object
Refresh the dataset's columns and metrics from the source.
Inputs: pk (required). Returns: object
Save a SQL query.
Inputs: label (required), sql (required), database_id (required), schema, +1 more. Returns: object
Update a chart's properties.
Inputs: pk (required), slice_name, description, viz_type, +2 more. Returns: object
Update an existing dashboard.
Inputs: pk (required), title, published, json_metadata, +1 more. Returns: object
Update a dataset's properties.
Inputs: pk (required), table_name, description, sql, +3 more. Returns: object
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Scored across 34 tools
Every tool has a clearly distinct purpose targeting specific resources (charts, dashboards, datasets, databases, queries) and actions (create, get, list, update, delete, execute, format, etc.), with no apparent overlap or ambiguity. For example, get_chart, get_chart_data, and list_charts serve different functions without confusion.
Tool names follow a highly consistent verb_noun pattern throughout, such as create_chart, delete_dashboard, list_datasets, and update_dataset, with no deviations in style or convention. This predictability makes the tool set easy to navigate and understand.
With 34 tools, the count is borderline high for typical MCP server scopes, which often range from 3-15 tools. While it covers a comprehensive Superset domain, it may feel heavy and potentially overwhelming for agents, though not extreme like 50+ tools.
The tool surface provides complete CRUD/lifecycle coverage for charts, dashboards, datasets, and queries, along with execution, formatting, and metadata operations. There are no obvious gaps; agents can perform all core workflows from creation to deletion and analysis without dead ends.
MCP server that lets AI assistants use all OneSchema features exposed via the public API.
Hosted MCP server connecting AI assistants to 9,000+ apps and 40,000+ actions via Zapier.
MCP server that lets your AI assistant build and deploy apps, hosting each one at a live URL.
MCP server for building and testing AI agents with multi-model experimentation and insights.
