Superset MCP Integration

MCP server for interacting with Apache Superset, enabling AI agents to connect to and control a Superset instance programmatically.

Setup Instructions

Installing via Smithery

To install Superset Integration for Claude Desktop automatically via Smithery:

npx -y @smithery/cli install @aptro/superset-mcp --client claude

Manual Installation

1. Set Up Superset Locally

   Run this script to start Superset locally:

   git clone --branch 4.1.1 --depth 1 https://github.com/apache/superset && \
   cd superset && \
   docker compose -f docker-compose-image-tag.yml up
   

   Once Superset is running, you should be able to access it at http://localhost:8088 with default credentials:

   • Username: admin
   • Password: admin

2. Clone This Repository

   Clone this repository to your local machine.

3. Configure Environment Variables

   Create a .env file in the root directory with your Superset credentials:

   SUPERSET_BASE_URL=http://localhost:8088  # Change to your Superset URL
   SUPERSET_USERNAME=your_username
   SUPERSET_PASSWORD=your_password
   

4. Install Dependencies

   uv pip install .
   

5. Install MCP Config for Claude

   To use with Claude Desktop app:

   mcp install main.py
   

Usage with Claude

After setup, you can interact with your Superset instance via Claude using natural language requests. Here are some examples:

Dashboard Management

• View dashboards: "Show me all my Superset dashboards"
• Get dashboard details: "Show me the details of dashboard with ID 5"
• Create dashboard: "Create a new dashboard titled 'Sales Overview'"
• Update dashboard: "Update dashboard 3 to have the title 'Updated Sales Report'"
• Delete dashboard: "Delete dashboard with ID 7"

Chart Management

• List all charts: "What charts do I have in my Superset instance?"
• View chart details: "Show me the details of chart with ID 10"
• Create chart: "Create a new bar chart using dataset 3"
• Update chart: "Update chart 5 to use a line visualization instead of bar"
• Delete chart: "Delete chart with ID 12"

Database and Dataset Operations

• List databases: "Show me all databases connected to Superset"
• List datasets: "What datasets are available in my Superset instance?"
• Get database tables: "What tables are available in database with ID 1?"
• Execute SQL: "Run this SQL query on database 1: SELECT * FROM users LIMIT 10"
• Create dataset: "Create a new dataset from table 'customers' in database 2"
• Update database: "Update the connection settings for database 3"
• Delete database: "Delete database connection with ID 4"
• Validate SQL: "Is this SQL valid for database 2: SELECT * FROM customers JOIN orders"
• Get database catalogs: "Show me the catalogs available in database 1"
• Get database functions: "What functions are available in database 2?"
• Check related objects: "What dashboards and charts use database 1?"

SQL Lab Features

• Execute queries: "Run this SQL query: SELECT COUNT(*) FROM orders"
• Format SQL: "Format this SQL query: SELECT id,name,age FROM users WHERE age>21"
• Estimate query cost: "Estimate the cost of this query: SELECT * FROM large_table"
• Get saved queries: "Show me all my saved SQL queries"
• Get query results: "Get the results of query with key 'abc123'"

User and System Information

• View user info: "Who am I logged in as?"
• Get user roles: "What roles do I have in Superset?"
• View recent activity: "Show me recent activity in my Superset instance"
• Get menu data: "What menu items do I have access to?"
• Get base URL: "What is the URL of the Superset instance I'm connec

... View full README on GitHub