Superset
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.
What is Superset?
Superset is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to mcp server that provides ai assistants with full access to apache superset instances, enabling interaction with dashboards, charts, datasets, databases, and sql execution capabilities.
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.
This server falls under the Analytics category on MCPgee, the world's largest MCP server directory with 33,000+ servers.
Features
- An MCP server that provides AI assistants with full access t
Use Cases
Maintainer
Works with
Installation
NPM
npx -y supersetManual Installation
npx -y supersetConfiguration
Configuration Details
claude_desktop_config.json
Performance
Response Metrics
Resource Usage
How to Set Up and Use Superset
The Superset MCP server connects AI assistants to Apache Superset instances, enabling full programmatic control over dashboards, charts, datasets, and databases through natural-language commands. It supports listing and creating dashboards and charts, running arbitrary SQL queries against connected databases, refreshing datasets, and fetching chart data — making it possible to automate analytics workflows or explore data without opening the Superset web UI. Teams running self-hosted or cloud Superset deployments can use this to let AI agents build and publish dashboards on their behalf.
Prerequisites
- A running Apache Superset instance (self-hosted or cloud) with known URL, username, and password
- Python with uv installed (recommended) or pip
- Git to clone the server repository
- Claude Desktop, Cursor, or another MCP-compatible client
Clone the superset-mcp repository
Clone the server code from GitHub — this is required because it runs as a local process connecting to your Superset instance.
git clone https://github.com/thedeceptio/superset-mcp.git
cd superset-mcpCreate the environment file
Copy the example environment file and fill in your Superset connection details: the instance URL, your username, and your password.
cp .env.example .env
# Edit .env and set:
# SUPERSET_URL=http://your-superset-host:8088
# SUPERSET_USERNAME=your-username
# SUPERSET_PASSWORD=your-passwordTest the server locally
Run the MCP server directly with uv to verify the connection to Superset works before wiring it into your AI client.
uv run superset-mcpAdd the server to your MCP client
Add the server block to your Claude Desktop or Cursor config file. Use the absolute path to the cloned repository directory.
{
"mcpServers": {
"superset": {
"command": "uv",
"args": ["--directory", "/absolute/path/to/superset-mcp", "run", "superset-mcp"],
"env": {
"SUPERSET_URL": "http://your-superset-host:8088",
"SUPERSET_USERNAME": "your-username",
"SUPERSET_PASSWORD": "your-password"
}
}
}
}Restart your MCP client
Restart Claude Desktop or reload your MCP client so it picks up the new server configuration and establishes the connection to Superset.
Superset Examples
Client configuration
Claude Desktop config for the Superset MCP server running from a locally cloned repository.
{
"mcpServers": {
"superset": {
"command": "uv",
"args": ["--directory", "/Users/you/superset-mcp", "run", "superset-mcp"],
"env": {
"SUPERSET_URL": "http://localhost:8088",
"SUPERSET_USERNAME": "admin",
"SUPERSET_PASSWORD": "your-password"
}
}
}
}Prompts to try
Use these prompts in Claude Desktop or Cursor after connecting the Superset MCP server.
- "List all published dashboards"
- "Show me all charts in dashboard 11"
- "Run SQL query on database 2: SELECT count(*) FROM orders"
- "Create a new dashboard called 'Sales Overview'"
- "What datasets power the Revenue dashboard?"
- "Refresh the orders dataset"Troubleshooting Superset
Authentication fails with 401 errors
Double-check SUPERSET_URL, SUPERSET_USERNAME, and SUPERSET_PASSWORD in your .env or MCP config. Ensure the URL has no trailing slash and the port matches your Superset deployment (default 8088).
uv command not found
Install uv with: curl -LsSf https://astral.sh/uv/install.sh | sh. Then restart your terminal and retry. Alternatively, use 'pip install superset-mcp' and replace 'uv run superset-mcp' with 'superset-mcp' in the config.
SQL queries fail or return permission errors
Ensure the Superset user has database query permissions. In Superset, check Security > List Users and assign the 'sql_lab' role or equivalent database access roles to the account used by the MCP server.
Frequently Asked Questions about Superset
What is Superset?
Superset is a Model Context Protocol (MCP) server that mcp server that provides ai assistants with full access to apache superset instances, enabling interaction with dashboards, charts, datasets, databases, and sql execution capabilities. It connects AI assistants to external tools and data sources through a standardized interface.
How do I install Superset?
Install via npm with the command: npx -y superset. Then add the server configuration to your AI client's JSON config file (e.g., claude_desktop_config.json or .cursor/mcp.json).
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 NOASSERTION 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.
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
AI Treasure Box
★ 806🤖 Automatically collected AI repos, tools, websites, papers & tutorials. 实用AI百宝箱 💎
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.