Skip to main content
Glama
Superset MCP Server

Superset MCP Server

by Amit-DAlal-1

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 5008

That 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_query creation 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 .env

Edit .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=true

The 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.server

The 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 pytest

MCP 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

superset_status

Validate settings, JWT login, current user, and optional OpenAPI availability

list_dashboards

Search and paginate dashboards

get_dashboard

Read dashboard metadata by ID or slug

get_dashboard_charts

Read a dashboard's chart definitions and form data

get_dashboard_datasets

Read datasets used by a dashboard

get_chart

Read chart metadata

get_chart_data

Retrieve data for a saved chart query

list_databases

Find accessible database IDs for SQL Lab and saved queries

execute_sql

Execute SQL unchanged through SQL Lab

get_query

Inspect query history or asynchronous status

get_sql_result

Retrieve asynchronous results using resultsKey

list_saved_queries

Search and paginate saved queries

get_saved_query

Read one saved query

create_saved_query

Preview/create a saved query; requires confirm=true to write

update_saved_query

Preview/update while preserving unspecified fields; requires confirm=true to write

There is no saved-query delete tool.

  1. Configure the real URL and credentials locally.

  2. Call superset_status.

  3. Call list_databases, list_dashboards, and list_saved_queries to validate read permissions.

  4. Review a dashboard through get_dashboard, get_dashboard_charts, and get_dashboard_datasets.

  5. Retrieve chart data only when needed; force=true bypasses Superset's cache and may increase database load.

  6. Execute SQL only after verifying the selected database ID and role. Long-running deployments can use run_async=true, then get_query/get_sql_result.

  7. Call create/update first with the default confirm=false, inspect the preview, and call again with confirm=true only when the payload is correct.

Troubleshooting

  • configured: false: one or more required SUPERSET_* 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=true and 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 require FAB_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_BYTES cautiously 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 null are treated as omitted by the MCP tool. This version does not expose field-clearing semantics.

API references

Available Tools

25 tools
add_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

    B3.4/5.0

    Scored across 25 tools

    Disambiguation4/5

    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.

    Naming Consistency4/5

    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.

    Tool Count3/5

    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.

    Completeness3/5

    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

    Related MCP Servers

    • A
      license
      B
      quality
      D
      maintenance
      MCP 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.
      60
      195
      MIT
    • A
      license
      Not graded
      quality
      D
      maintenance
      An 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
    • F
      license
      B
      quality
      D
      maintenance
      An 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
      -