Cube MCP server

The Snowflake Cube Server implements MCP (Model Context Protocol) functionality for interacting with Cube semantic layers. It allows you to query data from Cube deployments and retrieve information about the available data structure.

Installation

To use the Snowflake Cube Server, you'll need to set it up through Smithery. You can access this server using the Smithery platform at:

https://smithery.ai/server/@isaacwasserman/mcp_cube_server

Usage

The MCP Cube Server provides specific resources and tools for interacting with Cube semantic layers.

Available Resources

Context Description Resource

The server provides a resource for describing available data:

context://data_description

This resource contains a description of the data available in the Cube deployment and serves as an application-controlled version of the describe_data tool.

Data Resource

To access retrieved data in JSON format:

data://{data_id}

This resource contains data returned by a read_data call. It's particularly useful for MCP clients that need to format or process tool call outputs.

Available Tools

The server provides two main tools for interacting with Cube:

Reading Data

The read_data tool accepts queries to the Cube REST API and returns data in YAML format along with a unique identifier. This identifier can then be used to retrieve a JSON representation of the data.

Example usage:

# Use the read_data tool to query the Cube API
read_data <your-cube-query>

# Then access the JSON data using the returned ID
data://<returned-data-id>

Describing Data

The describe_data tool provides information about the data available in the Cube deployment. This is an interactive version of the context://data_description resource.

Example usage:

# Get information about available data structure
describe_data

This tool helps you understand what data is available before constructing your queries.

How to install this MCP server

For Claude Code

To add this MCP server to Claude Code, run this command in your terminal:

claude mcp add-json "mcp-cube-server" '{"command":"pip","args":["install","-U","mcp_cube_server"]}'

See the official Claude Code MCP documentation for more details.

For Cursor

There are two ways to add an MCP server to Cursor. The most common way is to add the server globally in the ~/.cursor/mcp.json file so that it is available in all of your projects.

If you only need the server in a single project, you can add it to the project instead by creating or adding it to the .cursor/mcp.json file.

Adding an MCP server to Cursor globally

To add a global MCP server go to Cursor Settings > Tools & Integrations and click "New MCP Server".

When you click that button the ~/.cursor/mcp.json file will be opened and you can add your server like this:

{
    "mcpServers": {
        "mcp-cube-server": {
            "command": "pip",
            "args": [
                "install",
                "-U",
                "mcp_cube_server"
            ]
        }
    }
}

Adding an MCP server to a project

To add an MCP server to a project you can create a new .cursor/mcp.json file or add it to the existing one. This will look exactly the same as the global MCP server example above.

How to use the MCP server

Once the server is installed, you might need to head back to Settings > MCP and click the refresh button.

The Cursor agent will then be able to see the available tools the added MCP server has available and will call them when it needs to.

You can also explicitly ask the agent to use the tool by mentioning the tool name and describing what the function does.

For Claude Desktop

To add this MCP server to Claude Desktop:

1. Find your configuration file:

• macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
• Windows: %APPDATA%\Claude\claude_desktop_config.json
• Linux: ~/.config/Claude/claude_desktop_config.json

2. Add this to your configuration file:

{
    "mcpServers": {
        "mcp-cube-server": {
            "command": "pip",
            "args": [
                "install",
                "-U",
                "mcp_cube_server"
            ]
        }
    }
}

3. Restart Claude Desktop for the changes to take effect