MCP Cube Server
MCP Server for Interacting with Cube Semantic Layers
What is MCP Cube Server?
MCP Cube Server is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to mcp server for interacting with cube semantic layers
MCP Server for Interacting with Cube Semantic Layers
This server falls under the Databases category on MCPgee, the world's largest MCP server directory with 33,000+ servers.
Features
- MCP Server for Interacting with Cube Semantic Layers
Use Cases
Maintainer
Works with
Installation
Manual Installation
npx mcp-cube-serverConfiguration
Configuration Details
claude_desktop_config.json
Performance
Response Metrics
Resource Usage
How to Set Up and Use MCP Cube Server
MCP Cube Server is a Python MCP server that connects AI assistants to Cube semantic layer deployments, enabling natural-language queries over your business data. It exposes tools for querying the Cube REST API and describing available data models, returning results in YAML and JSON formats. Data analysts and engineers can use it to let AI models explore and query Cube-defined metrics without writing raw SQL.
Prerequisites
- Python 3.10 or higher installed
- A running Cube deployment (cloud or self-hosted) with REST API access
- Cube REST API endpoint URL and a valid API token
- uv or pip package manager installed
- An MCP client such as Claude Desktop
Clone the repository
Clone the mcp_cube_server repository from GitHub.
git clone https://github.com/isaacwasserman/mcp_cube_server.git
cd mcp_cube_serverInstall the package
Install the Python package and its dependencies using pip or uv.
pip install -e .Obtain your Cube API credentials
Log in to your Cube deployment, navigate to the API section, and copy the REST API base URL and your API token. You will need these for the MCP client configuration.
Configure your MCP client
Add the MCP Cube Server to your client's configuration with your Cube API URL and token passed as environment variables or arguments.
Test the connection
Ask your MCP client to describe the available data in your Cube deployment. The describe_data tool will return a list of available cubes and their dimensions/measures.
MCP Cube Server Examples
Client configuration
Add MCP Cube Server to Claude Desktop pointing to your Cube deployment.
{
"mcpServers": {
"cube": {
"command": "python",
"args": ["-m", "mcp_cube_server"],
"env": {
"CUBE_API_URL": "https://your-cube-deployment.cubecloudapp.dev/cubejs-api/v1",
"CUBE_API_TOKEN": "your-cube-api-token"
}
}
}
}Prompts to try
Example prompts to explore and query your Cube semantic layer.
- "Describe all available data in my Cube deployment."
- "Query total orders by product category for the last 30 days."
- "What metrics and dimensions are available in the Sales cube?"
- "Get daily revenue for the past week and format it as a table."Troubleshooting MCP Cube Server
Authentication errors when querying the Cube REST API
Verify that CUBE_API_TOKEN is set correctly and that the token has not expired. In Cube Cloud, regenerate the token from the API Credentials section if needed.
read_data returns no results for a valid query
Use describe_data first to confirm the cube name, measure names, and dimension names are correct. Cube's REST API is case-sensitive and requires exact member names as defined in your schema.
Server fails to start with ModuleNotFoundError
Ensure the package was installed in the same Python environment used to run the server. Run 'pip install -e .' inside the cloned directory and verify with 'python -c "import mcp_cube_server"'.
Frequently Asked Questions about MCP Cube Server
What is MCP Cube Server?
MCP Cube Server is a Model Context Protocol (MCP) server that mcp server for interacting with cube semantic layers It connects AI assistants to external tools and data sources through a standardized interface.
How do I install MCP Cube Server?
Follow the installation instructions on the MCP Cube Server GitHub repository. Clone the repo, install dependencies, and add the server config to your AI client.
Which AI clients work with MCP Cube Server?
MCP Cube Server works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.
Is MCP Cube Server free to use?
Yes, MCP Cube Server is open source and available under the GPL-3.0 license. You can use it freely in both personal and commercial projects.
MCP Cube Server Alternatives — Similar Databases Servers
Looking for alternatives to MCP Cube Server? Here are other popular databases servers you can use with Claude, Cursor, and VS Code.
Excelize
★ 20.6kGo language library for reading and writing Microsoft Excel™ (XLAM / XLSM / XLSX / XLTM / XLTX) spreadsheets
MCP Toolbox for Databases
★ 15.3kOpen source MCP server specializing in easy, fast, and secure tools for Databases.
DBHub
★ 2.8kA universal database gateway MCP server that enables AI assistants to connect to and query multiple databases (PostgreSQL, MySQL, MariaDB, SQL Server, SQLite) with support for schema exploration, SQL execution, and secure connections via SSH tunnels.
Tabularis
★ 2.1kA lightweight, cross-platform database client for developers. Supports MySQL, PostgreSQL and SQLite. Hackable with plugins. Built for speed, security, and aesthetics.
Postgres AI Guide
★ 1.7kMCP server and Claude plugin for Postgres skills and documentation. Helps AI coding tools generate better PostgreSQL code.
Anyquery
★ 1.7k🏎️ 🏠 ☁️ - Query more than 40 apps with one binary using SQL. It can also connect to your PostgreSQL, MySQL, or SQLite compatible database. Local-first and private by design.
Browse More Databases MCP Servers
Explore all databases servers available in the MCPgee directory. Each server includes setup guides for Claude, Cursor, and VS Code.
Set Up MCP Cube Server 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 MCP Cube Server?
Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.