Integrate Cube.dev with Claude, Cursor, Chatbots & AI Agents MCP Server

Q: Can I see the exact SQL that Cube generates for a specific query?

Yes. You can use the get_sql tool. By providing the query JSON, the agent will return the generated SQL string, which is perfect for debugging or verifying your data logic.

Access your Cube semantic layer — execute queries, inspect generated SQL, manage pre-aggregations, and explore data metadata directly.

GDPR Free for Subscribers

Compatible with every major AI agent and IDE

Claude

ChatGPT

Cursor

Gemini

Windsurf

VS Code

JetBrains

Vercel

+ other MCP clients

check

Check live on Cube.dev

Check if Cube deployment is live

check

Check ready on Cube.dev

Check if Cube deployment is ready

convert

Convert query on Cube.dev

Convert a SQL query to a REST API query format

execute

Execute cube sql on Cube.dev

Execute a raw SQL query against the SQL API

generate

Generate meta token on Cube.dev

Requires CUBE_CLOUD_API_KEY. Generate a JWT for the Metadata API

get

Get entity on Cube.dev

Get detailed metadata for a specific entity

get

Get meta on Cube.dev

Get metadata for cubes and views

get

Get pre aggregation job status on Cube.dev

Get status of pre-aggregation jobs

get

Get sql on Cube.dev

Useful for debugging. Get generated SQL for a Cube query

list

List data sources on Cube.dev

List configured data sources

list

List deployments on Cube.dev

Requires CUBE_CLOUD_API_KEY. List all Cube Cloud deployments

list

List entities on Cube.dev

List all cubes and views

list

List environments on Cube.dev

Requires CUBE_CLOUD_API_KEY. List environments for a deployment

load

Load query on Cube.dev

Use this to get aggregated data. Execute a Cube query and return results

trigger

Trigger pre aggregation job on Cube.dev

Trigger a pre-aggregation build job

Security & Code Integrity Audit

Every tool in the Cube.dev MCP Server is continuously audited by the Vinkius Security Engine. We guarantee zero-trust payload isolation, strict data boundaries, and deterministic execution for enterprise-grade AI agents.

FScore: 3.6

How Vinkius protects your data

Can I audit what my AI agents are doing with this integration?

Yes, Vinkius provides an immutable, HMAC-chained audit log. Every tool execution, payload, and response is tracked in real-time on your dashboard, giving you complete visibility into your agent's actions.

Can I see the exact SQL that Cube generates for a specific query?

Yes. You can use the get_sql tool. By providing the query JSON, the agent will return the generated SQL string, which is perfect for debugging or verifying your data logic.

What happens if the underlying API rate limits my agent?

Our edge infrastructure automatically handles backoffs, queueing, and throttling. If an AI agent sends too many erratic requests, Vinkius manages the rate limits gracefully, ensuring your backend doesn't crash.

How does the AI access my passwords and credentials?

It simply doesn't. On Vinkius, your passwords, API keys, and login details are kept in a secure vault. The AI (like ChatGPT or Claude) merely "asks" Vinkius to perform the task. Vinkius opens the door, does the work, and hands the result back to the AI. Your credentials are never seen, read, or learned by the artificial intelligence.

What can AI Agents do with Cube.dev?

The Cube.dev integration provides comprehensive execution endpoints, allowing AI models to orchestrate tasks reliably.

Autonomous semantic layer Strategies

Integrate Cube.dev to access native semantic layer capabilities. This allows LLMs to perform secure, deterministic execution of brain trust tasks without hard-coded API scripts.

Secure data modeling Access for Agents

Add Cube.dev to your workspace to support data modeling automation. The integration processes the required parameters for brain trust execution by LLMs.