By cliftonc
Claude Code plugin for Drizzle Cube - type-safe analytics and dashboards with Drizzle ORM. Includes MCP tools, slash commands, and agent skills.
Add a new chart/portlet to an existing Drizzle Cube dashboard
Use AI-powered tools to build and execute analytics queries from natural language
Create a new Drizzle Cube definition with measures, dimensions, and security context
Create a new Drizzle Cube dashboard configuration
Debug a Drizzle Cube query using dry-run and explain endpoints
Create and configure AnalysisConfig objects for query, funnel, and flow analysis modes in Drizzle Cube dashboards.
Configure chart axis mappings and display options for all chart types in Drizzle Cube.
Create and configure Drizzle Cube semantic layer cube definitions with proper security context, measures, dimensions, and joins.
Create and configure dashboards with portlets (charts/widgets) using DashboardConfig in Drizzle Cube.
Build semantic queries with measures, dimensions, filters, and time dimensions for Drizzle Cube.
Admin access level
Server config contains admin-level keywords
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
A Claude Code plugin that provides MCP (Model Context Protocol) tools for interacting with Drizzle Cube semantic layer APIs.
This plugin registers two MCP servers for a complete Drizzle Cube integration:
| Tool | Description |
|---|---|
discover | Find relevant cubes by topic or natural language intent |
validate | Validate queries with auto-corrections |
load | Execute validated queries |
| Tool | Description |
|---|---|
drizzle_cube_meta | Fetch cube metadata (measures, dimensions, relationships) |
drizzle_cube_dry_run | Validate a query and preview generated SQL |
drizzle_cube_explain | Get query execution plan with performance analysis |
drizzle_cube_load | Execute a query directly via REST API |
drizzle_cube_batch | Execute multiple queries in parallel |
drizzle_cube_config | View current configuration status |
┌─────────────────────┐ ┌──────────────────────────────────┐
│ Claude Code │ │ Drizzle Cube Server │
│ │ │ │
│ MCP Servers: │ │ /mcp (MCP endpoint) │
│ - drizzle-cube-api ├────►│ - discover │
│ (HTTP to /mcp) │ │ - validate │
│ │ │ - load │
│ - drizzle-cube │ │ + prompts, resources │
│ (stdio plugin) │ │ │
│ - meta ├────►│ /cubejs-api/v1 (REST API) │
│ - dry_run │ │ - meta, dry-run, explain │
│ - explain │ │ - load, batch │
│ - load │ │ │
│ - batch │ └──────────────────────────────────┘
│ - config │
└─────────────────────┘
Why two servers?
/plugin install cliftonc/drizzle-cube-plugin
git clone https://github.com/cliftonc/drizzle-cube-plugin.git
cd drizzle-cube-plugin
npm install
npm run build
/plugin install ./drizzle-cube-plugin
The plugin works out of the box with the demo server at https://try.drizzle-cube.dev.
No configuration needed for the demo server. Just install and use:
/dc-ask "show me productivity by employee"
To use your own Drizzle Cube server, configure both the MCP server URL and REST API URL:
.mcp.json)The plugin's .mcp.json registers the real MCP server. Update the URL to point to your server:
{
"mcpServers": {
"drizzle-cube-api": {
"type": "url",
"url": "https://your-server.com/mcp"
},
"drizzle-cube": {
"command": "node",
"args": ["${CLAUDE_PLUGIN_ROOT}/dist/index.js"]
}
}
}
.drizzle-cube.json)Create .drizzle-cube.json in your project directory:
{
"serverUrl": "https://your-server.com",
"apiToken": "your-optional-token"
}
Or create a global config at ~/.drizzle-cube/config.json.
export DRIZZLE_CUBE_SERVER_URL="https://your-server.com"
export DRIZZLE_CUBE_API_TOKEN="your-token"
.drizzle-cube.json in current project directory~/.drizzle-cube/config.json (global)| Command | Description |
|---|---|
/dc-setup | Configure server URL and verify connectivity |
/dc-ask | Query data using natural language (AI-powered) |
/dc-query | Build queries with full schema awareness |
/dc-debug | Debug queries with SQL preview and execution plans |
/dc-create-cube | Create new cube definitions |
/dc-create-dashboard | Create dashboard configurations |
/dc-add-chart | Add charts to existing dashboards |
Ask questions in plain English:
/dc-ask "show me total revenue by product category for last month"
This uses the discover → validate → load workflow from the real MCP server.
When you know the cube structure:
/dc-query
This uses drizzle_cube_meta to show available cubes, then drizzle_cube_load to execute.
Preview the generated SQL without executing:
/dc-debug
This uses drizzle_cube_dry_run and drizzle_cube_explain for SQL preview and execution plans.
npx claudepluginhub cliftonc/drizzle-cube-plugin --plugin drizzle-cubeSkills library for reverse engineering: codebase analysis, service mapping, API discovery, and documentation generation
TypeScript quality enforcement with instant file-scoped checks and architectural review. Auto-activated skill runs typecheck and lint after each file write. Includes /ts-review command for comprehensive code analysis.
MCP Server for Metabase - 111 tools for SQL generation, dashboard management, and PostgreSQL integration
Skills and tools powered by the Honeydew MCP that help coding agents query data and build semantic models
Write SQL, explore datasets, and generate insights faster. Build visualizations and dashboards, and turn raw data into clear stories for stakeholders.
Semantic SQL compiler — compile .view.yml schema definitions into dialect-specific SQL. Unix-philosophy CLI designed as a tool-use interface for LLMs.
Connect to Looker and interact with your data using LookML.
The most comprehensive SAP Datasphere plugin for Claude. 18 specialized skills covering exploration, data modeling, integration, BW Bridge migration, security architecture, CLI automation, business content activation, catalog governance, performance optimization, and troubleshooting — all through natural language. Powered by 45 MCP tools with enterprise-grade security.