Cube.dev MCP Connector for Claude

Connect your Cube.dev instance to any AI agent to bridge the gap between natural language and your data warehouse. This server allows your agent to interact with Cube's semantic layer, ensuring consistent metrics and high-performance data retrieval.

What you can do

• Data Querying — Execute complex REST API queries using load_query to fetch aggregated data with measures, dimensions, and filters.
• SQL Inspection — Use get_sql and execute_cube_sql to debug or run raw queries against the SQL API for deep data investigation.
• Metadata Exploration — Retrieve cube definitions, views, and segments via get_meta to understand your data model without leaving the chat.
• Performance Management — Trigger and monitor background pre-aggregation builds with trigger_pre_aggregation_job to ensure your dashboards stay fast.
• Cloud Management — List deployments and environments if using Cube Cloud to manage your infrastructure context.

How it works

1. Subscribe to this server
2. Provide your Cube API URL and Secret Token
3. Start asking questions about your data metrics and model structure

Who is this for?

• Data Engineers — quickly verify data models and trigger cache refreshes via CLI or AI interface.
• Analytics Engineers — debug generated SQL and inspect metadata to ensure metric consistency.
• Product Managers — get instant answers to data questions by letting the AI query the semantic layer directly.