Superset MCP Server
Provides tools for reviewing Apache Superset dashboards, retrieving chart data, executing SQL through SQL Lab, and creating or updating saved queries.
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 Server show me my dashboards"
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.
Superset MCP Server
Local stdio MCP server for reviewing Apache Superset dashboards, retrieving chart data, executing SQL through SQL Lab, and creating or updating saved queries.
The server only calls Superset's public REST API. It does not connect directly to an analytical database. No delete, dashboard mutation, chart mutation, dataset mutation, database-administration, screenshot, or generic arbitrary-request tools are exposed.
Superset's built-in MCP server
Superset 5.0+ also includes an official MCP service that an administrator can run alongside the Superset deployment:
superset mcp run --host 127.0.0.1 --port 5008That service is the preferred option when your Superset version includes it and you have deployment access. It provides native RBAC enforcement, audit logging, chart/dashboard creation, SQL execution, and saved-query creation at an HTTP /mcp endpoint. See the official MCP deployment guide and available tools.
This repository remains useful when:
the Superset administrator has not deployed the built-in MCP process;
only the public REST URL and a normal Superset login are available;
a local stdio MCP server is required; or
saved-query inspection and update support are needed in addition to the built-in server's documented
save_sql_querycreation tool.
Do not deploy both integrations under the same MCP server name without intentionally choosing which one future projects should use.
Related MCP server: Superset MCP Server
Requirements
Python 3.11 or newer (Python 3.13 is supported by this project)
Network access from this machine to your Superset URL
A dedicated Superset account with only the roles and database permissions the MCP server needs
execute_sql deliberately passes SQL through unchanged. Superset's database configuration and the underlying database user are therefore the security boundary for DML, DDL, CTAS, and other statements. Use a least-privilege account.
Windows setup
Run these commands from super_set_mcp in PowerShell:
python -m venv .venv
.\.venv\Scripts\Activate.ps1
python -m pip install --upgrade pip
python -m pip install -e ".[dev]"
Copy-Item .env.example .envEdit .env with the real connection values. Do not commit .env.
SUPERSET_URL=https://superset.example.com
SUPERSET_USERNAME=mcp-service-user
SUPERSET_PASSWORD=replace-me
SUPERSET_PROVIDER=db
SUPERSET_VERIFY_SSL=trueThe URL must be the Superset base URL without /api/v1. SUPERSET_PROVIDER can be changed to ldap when that is how the Superset login endpoint is configured.
Run and validate
Run the server over stdio:
.\.venv\Scripts\python.exe -m superset_mcp.serverThe process waits silently for MCP protocol messages; that is normal for a stdio server. Before using any data or write tool, call superset_status. It checks login and current-user access and, by default, probes Superset's OpenAPI endpoint.
Run the mocked test suite without contacting Superset:
.\.venv\Scripts\python.exe -m pytestMCP client configuration
Use an absolute path so future projects can launch the same server regardless of their working directory:
{
"mcpServers": {
"superset": {
"command": "C:\\path\\to\\super_set_mcp\\.venv\\Scripts\\python.exe",
"args": ["-m", "superset_mcp.server"],
"cwd": "C:\\path\\to\\super_set_mcp"
}
}
}Keeping cwd set to this folder allows pydantic-settings to load its local .env. If a client supports an env map, secrets may instead be injected by the client or a secret manager; do not place real credentials in shared project configuration.
Tools
Tool | Purpose |
| Validate settings, JWT login, current user, and optional OpenAPI availability |
| Search and paginate dashboards |
| Read dashboard metadata by ID or slug |
| Read a dashboard's chart definitions and form data |
| Read datasets used by a dashboard |
| Read chart metadata |
| Retrieve data for a saved chart query |
| Find accessible database IDs for SQL Lab and saved queries |
| Execute SQL unchanged through SQL Lab |
| Inspect query history or asynchronous status |
| Retrieve asynchronous results using |
| Search and paginate saved queries |
| Read one saved query |
| Preview/create a saved query; requires |
| Preview/update while preserving unspecified fields; requires |
There is no saved-query delete tool.
Recommended first-use sequence
Configure the real URL and credentials locally.
Call
superset_status.Call
list_databases,list_dashboards, andlist_saved_queriesto validate read permissions.Review a dashboard through
get_dashboard,get_dashboard_charts, andget_dashboard_datasets.Retrieve chart data only when needed;
force=truebypasses Superset's cache and may increase database load.Execute SQL only after verifying the selected database ID and role. Long-running deployments can use
run_async=true, thenget_query/get_sql_result.Call create/update first with the default
confirm=false, inspect the preview, and call again withconfirm=trueonly when the payload is correct.
Troubleshooting
configured: false: one or more requiredSUPERSET_*settings are missing or the URL is invalid.HTTP 401: check username, password, provider, and whether REST login is enabled.
HTTP 403: the Superset role lacks access to the dashboard, chart, database, SQL Lab, or saved-query resource.
TLS/transport error: keep
SUPERSET_VERIFY_SSL=trueand install/configure the organization's trusted CA. Disable verification only for a controlled temporary diagnostic.OpenAPI unavailable: the deployment may not expose
/api/v1/_openapi; normal tools can still work. Superset's Swagger UI may also requireFAB_API_SWAGGER_UI = True.Result expired (HTTP 410): rerun the asynchronous query because its result key is no longer retained by Superset.
Response too large: increase
SUPERSET_MAX_RESPONSE_BYTEScautiously or reduce query/page limits.
Security behavior
Passwords and JWTs remain in environment configuration and process memory; they are never returned by tools.
On HTTP 401, the client tries the refresh token and then performs one fresh login if refresh fails.
API error output includes method, public API path, status, and safe error fields, but excludes request headers and credentials.
Page sizes, query limits, request timeouts, and response bytes are bounded by environment settings.
Saved-query updates fetch the existing record and preserve fields not supplied by the caller.
Optional update fields set to
nullare treated as omitted by the MCP tool. This version does not expose field-clearing semantics.
API references
Available Tools
25 toolsadd_chart_to_dashboardA
Preview or add a chart to one or more dashboards; confirm=true is required to write.
Inputs: chart_id (required), dashboard_ids (required), confirm.
create_chartA
Preview or create a chart on a Superset dataset; confirm=true is required to write.
Inputs: params (required), viz_type (required), slice_name (required), datasource_id (required), +5 more.
create_dashboardB
Preview or create a dashboard; confirm=true is required to write.
Inputs: dashboard_title (required), slug, owners, confirm, +1 more.
create_saved_queryA
Preview or create a saved query. No write occurs unless confirm is true.
Inputs: sql (required), db_id (required), label (required), schema, +5 more.
create_virtual_datasetA
Preview or create a SQL-backed virtual dataset; confirm=true is required to write.
Inputs: sql (required), table_name (required), database_id (required), owners, +2 more.
execute_sqlB
Execute SQL unchanged through SQL Lab; Superset/database permissions are the safety boundary.
Inputs: sql (required), database_id (required), schema, catalog, +2 more.
get_chartA
Get chart metadata by ID or UUID.
Inputs: id_or_uuid (required).
get_chart_dataA
Run the stored chart query and return its data; force bypasses the Superset cache.
Inputs: chart_id (required), force.
get_dashboardA
Get dashboard metadata by numeric ID or slug.
Inputs: id_or_slug (required).
get_dashboard_chartsC
Get chart definitions and form data for a dashboard.
Inputs: id_or_slug (required).
get_dashboard_datasetsC
Get datasets referenced by a dashboard.
Inputs: id_or_slug (required).
get_datasetB
Get dataset metadata by numeric ID.
Inputs: dataset_id (required).
get_queryA
Get Superset query history/status details by query ID.
Inputs: query_id (required).
get_saved_queryA
Get one saved query by ID.
Inputs: query_id (required).
get_sql_resultA
Retrieve an asynchronous SQL Lab result using the resultsKey returned by execute_sql.
Inputs: result_key (required).
list_dashboardsA
List dashboards with optional title search and bounded pagination.
Inputs: page, search, page_size.
list_databasesB
List accessible Superset databases and their IDs.
Inputs: page, search, page_size.
list_datasetsA
List datasets with optional name search and bounded pagination.
Inputs: page, search, page_size.
list_saved_queriesB
List saved SQL queries with optional label search.
Inputs: page, search, page_size.
refresh_datasetA
Preview or refresh dataset columns from its SQL; confirm=true is required.
Inputs: dataset_id (required), confirm.
superset_statusA
Validate configuration, JWT authentication, current-user access, and optional OpenAPI availability.
Inputs: check_openapi. Returns: object
update_chartA
Preview or update chart parameters/query context/dashboard links; confirm=true is required.
Inputs: chart_id (required), params, confirm, slice_name, +3 more.
update_dashboardB
Preview or update dashboard layout/metadata/publication; confirm=true is required.
Inputs: dashboard_id (required), confirm, metadata, position, +1 more.
update_dataset_sqlA
Preview or replace SQL for an existing virtual dataset; confirm=true is required.
Inputs: sql (required), dataset_id (required), confirm.
update_saved_queryA
Preview or update a saved query, preserving unspecified fields; confirm=true is required to write.
Inputs: query_id (required), sql, db_id, label, +6 more.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 25 tools
Most tools have clear, distinct purposes targeting specific resources and actions. The only potential confusion is between get_sql_result (async result retrieval) and get_query (query history/status), and between get_chart_data and get_chart, but descriptions are sufficiently clear.
The vast majority follow a consistent verb_noun snake_case pattern (list_, get_, create_, update_, execute_). The single outlier is superset_status, which is not verb-first but still readable and not disruptive.
At 25 tools, this is at the heavy end of the borderline range. Each tool has a purpose, but the granularity is excessive in places (e.g., four dashboard-related getters), making the surface feel larger than necessary.
The set covers most core workflows for dashboards, charts, datasets, saved queries, and SQL execution, but there are notable gaps: no list_charts, no delete operations for any resource, and no get_database by ID. These missing operations will require workarounds.
Related MCP Connectors
MCP server for interacting with the Supabase platform
An MCP server for search and retrieval over a local LanceDB database
Query, join, profile, clean and convert CSV/JSON/Parquet with server-side DuckDB over MCP.
Remote MCP server for supportsheep: run AI interviews and manage support content for your blog.
Related MCP Servers
- AlicenseBqualityDmaintenanceMCP server enabling AI agents to programmatically connect to and control Apache Superset instances, allowing users to manage dashboards, charts, databases, datasets, and run SQL queries through natural language interactions.60195MIT
- AlicenseNot gradedqualityDmaintenanceAn MCP server for Apache Superset that enables AI models to manage dashboards, create charts with auto-detection, and execute SQL queries programmatically. It utilizes stateless HTTP transport to ensure compatibility with integration tools like Open WebUI.MIT
- FlicenseBqualityDmaintenanceAn MCP server that provides AI assistants with full access to Apache Superset instances, enabling interaction with dashboards, charts, datasets, databases, and SQL execution capabilities.34-
- AlicenseBqualityDmaintenanceMCP server for Preset (managed Apache Superset). Manage dashboards, charts, and datasets from Claude Code and other LLM agents.591MIT