Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@DB-MCPWhat was the total revenue by region for the last quarter?"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
DB-MCP
A Model Context Protocol (MCP) server that provides governed semantic analytics queries through Cube.js.
What is this?
DB-MCP acts as a bridge between AI assistants and your data warehouse, enabling natural language queries while enforcing governance policies. It exposes your Cube.js semantic layer as MCP tools that AI models can use safely.
Architecture
Components
MCP Server (/src)
Tools exposed via MCP:
catalog.search- Search available measures, dimensions, segmentscatalog.describe- Get details about a specific memberquery.semantic- Execute governed queries against the semantic layer
Governance (
/src/policy) - Enforces limits, blocks PII, validates membersCatalog (
/src/catalog) - Indexes Cube metadata with fuzzy searchQuery (
/src/query) - Executes validated queries through Cube.js
Admin UI (/admin)
Backend (
/admin/backend) - Express API for managementFrontend (
/admin/frontend) - React admin dashboard with:Database schema browser
Governance configuration
Query playground
AI chat interface (uses MCP tools)
Cube.js (/cube)
Semantic layer definitions (cubes, measures, dimensions)
Connects to your data warehouse
Quick Start
Configuration
Copy .env.example to .env and configure:
MCP Integration
Use with Claude Desktop or any MCP-compatible client:
License
MIT