Superset MCP Server

Superset MCP Server is an MCP server that connects AI assistants like Claude Desktop and Cursor to Apache Superset instances. It is designed for data analysts, business intelligence engineers, and developers who need to interact with their visualization layer programmatically through natural language. The server enables users to perform full CRUD operations on datasets, manage metric definitions, and configure calculated columns without navigating the web UI manually. Users can inspect chart visualization parameters, modify chart filters, and manage dashboard layouts and configurations directly from their LLM client. Additionally, it provides tools for listing configured database connections and running direct SQL queries against connected databases via the Superset backend. By exposing Superset metadata as MCP resources and operational tools, the integration allows AI agents to inspect query contexts, update analytical models, and automate dashboard maintenance workflows directly inside the development environment.

Category: Data & Analytics

Tags: bi, dashboards, data-visualization, SQL, superset

Visit Superset MCP Server

How to install and configure Superset MCP Server

1. Ensure Node.js 18+ is installed on your machine and you have access credentials for an Apache Superset instance. 2. Open your MCP client configuration file (such as Claude Desktop or Cursor settings). 3. Add the server entry under the mcpServers block: json { "mcpServers": { "superset-mcp": { "command": "npx", "args": ["-y", "superset-mcp"], "env": { "SUPERSET_BASE_URL": "your-superset-url", "SUPERSET_USERNAME": "your_username", "SUPERSET_PASSWORD": "your_password" } } } } 4. Alternatively, replace SUPERSET_USERNAME and SUPERSET_PASSWORD with "SUPERSET_ACCESS_TOKEN": "your_access_token". 5. Save the configuration and restart your client.

What you can do with Superset MCP Server

• Creating, updating, or deleting physical and virtual datasets within Apache Superset directly through natural language requests. - Defining new metrics and calculated columns with SQL expressions without opening the Superset web interface. - Inspecting dashboard layouts, native filters, and chart query contexts to troubleshoot visualization parameters. - Executing SQL queries across configured database connections and reviewing paginated result sets inside the LLM interface. - Automating chart updates by modifying chart visualization parameters, datasources, and persistent filter conditions.

Key facts

• https://github.com/Winding2020/superset-mcp
• Data & Analytics, Databases & Data Stores
• bi, dashboards, data-visualization, SQL, superset

Part of MCP Servers

How do I install Superset MCP Server?

You can run it using npx superset-mcp. Add it to your Claude Desktop or Cursor configuration under the mcpServers object, providing your Apache Superset base URL along with either username and password or a valid access token in the env settings.

What can Superset MCP Server do?

It provides tools for dataset CRUD operations, managing calculated columns and metrics, executing SQL queries, managing chart parameters and filters, viewing dashboard layouts, and listing configured databases inside your Superset instance.

Which MCP clients work with Superset MCP Server?

It works with any Model Context Protocol client that supports standard npx command execution and environment variable configuration, including Claude Desktop and Cursor.

What authentication methods does Superset MCP Server support?

The server supports basic authentication using a Superset username and password, or authentication via a dedicated Superset access token configured in the environment variables.