Superset
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.
What is Superset?
Superset is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to 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 natura...
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.
This server falls under the Analytics category on MCPgee, the world's largest MCP server directory with 33,000+ servers.
Features
- MCP server enabling AI agents to programmatically connect to
Use Cases
Maintainer
Works with
Installation
Manual Installation
npx superset-mcp-integrationConfiguration
Configuration Details
claude_desktop_config.json
Performance
Response Metrics
Resource Usage
How to Set Up and Use Superset
The Superset MCP Integration connects AI assistants directly to Apache Superset, an open-source data visualization platform, enabling programmatic control of dashboards, charts, databases, datasets, and SQL Lab through natural language. It authenticates against your Superset instance and exposes a broad set of operations covering the entire Superset API surface — from creating and updating charts to running SQL queries and managing tags. Developers and data teams use this server to automate BI workflows, generate dashboards from prompts, and explore data without leaving their AI assistant.
Prerequisites
- Python 3.10+ and the uv package manager installed
- A running Apache Superset instance (local Docker or remote) accessible at a known URL
- Superset credentials (username and password) with sufficient permissions
- An MCP-compatible client such as Claude Desktop or Claude Code
Start an Apache Superset instance
If you do not already have Superset running, clone the repo and launch it with Docker Compose. The default URL will be http://localhost:8088.
git clone --branch 4.1.1 --depth 1 https://github.com/apache/superset
cd superset
docker compose -f docker-compose-image-tag.yml upInstall the MCP server
Clone the superset-mcp repository and install it with uv, then register it with your MCP client.
git clone https://github.com/aptro/superset-mcp
cd superset-mcp
uv pip install .
mcp install main.pySet environment variables
Create a .env file in the superset-mcp directory with your Superset connection details. SUPERSET_BASE_URL defaults to http://localhost:8088 if omitted.
SUPERSET_BASE_URL=http://localhost:8088
SUPERSET_USERNAME=admin
SUPERSET_PASSWORD=adminConfigure your MCP client
Add the server to your Claude Desktop or Claude Code configuration file so the AI assistant can connect to it.
Verify the connection
Ask your AI assistant to list available dashboards. If the server is running and credentials are correct, it will return the dashboards from your Superset instance.
Superset Examples
Client configuration
Add this block to your claude_desktop_config.json (macOS: ~/Library/Application Support/Claude/claude_desktop_config.json) to register the Superset MCP server.
{
"mcpServers": {
"superset": {
"command": "uv",
"args": ["run", "python", "main.py"],
"cwd": "/path/to/superset-mcp",
"env": {
"SUPERSET_BASE_URL": "http://localhost:8088",
"SUPERSET_USERNAME": "admin",
"SUPERSET_PASSWORD": "admin"
}
}
}
}Prompts to try
Example natural language prompts that exercise the server's capabilities across dashboards, SQL, and metadata.
- "Show me all my Superset dashboards"
- "Create a new dashboard titled 'Q2 Sales Overview'"
- "Run this SQL query on database 1: SELECT * FROM orders LIMIT 20"
- "What tables are available in database with ID 1?"
- "List all charts and tell me which ones belong to the Sales dashboard"
- "Format this SQL and estimate its cost: SELECT * FROM users WHERE created_at > '2024-01-01'"Troubleshooting Superset
Authentication fails with 401 Unauthorized
Verify SUPERSET_USERNAME and SUPERSET_PASSWORD are correct and the account has the Admin or Alpha role in Superset. Also confirm SUPERSET_BASE_URL does not have a trailing slash.
Connection refused when reaching Superset
Confirm the Superset Docker containers are all healthy with 'docker compose ps'. The web service on port 8088 must be in the 'running' state before the MCP server can connect.
SQL queries return permission errors
The Superset user must have the 'can_run_async' and 'can_read' permissions on the relevant databases. Grant these through Superset's Security > List Roles menu.
Frequently Asked Questions about Superset
What is Superset?
Superset is a Model Context Protocol (MCP) server that 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. It connects AI assistants to external tools and data sources through a standardized interface.
How do I install Superset?
Follow the installation instructions on the Superset GitHub repository. Clone the repo, install dependencies, and add the server config to your AI client.
Which AI clients work with Superset?
Superset works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.
Is Superset free to use?
Yes, Superset is open source and available under the MIT License license. You can use it freely in both personal and commercial projects.
Superset Alternatives — Similar Analytics Servers
Looking for alternatives to Superset? Here are other popular analytics servers you can use with Claude, Cursor, and VS Code.
OpenMetadata
★ 14.0kOpenMetadata is a unified metadata platform for data discovery, data observability, and data governance powered by a central metadata repository, in-depth column level lineage, and seamless team collaboration.
Superset
★ 10.9kAn MCP server that provides AI assistants with full access to Apache Superset instances, enabling interaction with dashboards, charts, datasets, databases, and SQL execution capabilities.
Horizon
★ 4.4k📡 Your own AI-powered news radar. Generates daily briefings in English & Chinese. | 用 AI 构建你专属的新闻雷达
MCP Server Chart
★ 4.1kEnables generation of 25+ types of charts and data visualizations using AntV, including bar charts, line charts, maps, mind maps, and specialized diagrams like fishbone and sankey charts. Supports both statistical charts and geographic visualizations
Muapi CLI
★ 997Official CLI for muapi.ai — generate images, videos & audio from the terminal. MCP server, 14 AI models, npm + pip installable.
Weather MCP Server
★ 907Weather Data Fetcher MCP server built with Node.js, MCP SDK, and Zod. Provides weather details like temperature and forecast for cities such as Noida and Delhi via a registered tool. Simplifies API integration, enabling structured responses for clien
Browse More Analytics MCP Servers
Explore all analytics servers available in the MCPgee directory. Each server includes setup guides for Claude, Cursor, and VS Code.
Set Up Superset in Your Editor
Choose your AI client for step-by-step setup instructions.
Quick Config Preview
Add this to your claude_desktop_config.json or .cursor/mcp.json
Ready to use Superset?
Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.