How to Use the Cube.dev MCP in Mastra AI

Q: How do I install the Cube.dev MCP Server in Mastra AI?

Run npm install @mastra/mcp@latest. Add the Vinkius URL to your MCPClient configuration block.

Q: How do I restrict access to destructive tools?

Use requireToolApproval in your Mastra config. This forces a human to click yes before triggering aggregation jobs.

Build self-healing data workflows that manage semantic layers automatically with Mastra AI and this MCP Server.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Cube.dev MCP to Mastra AI

Create your Vinkius account to connect Cube.dev to Mastra AI and route execution through our secure gateway. The platform manages server hosting, runtime updates, and security layers. Configuration requires no manual server provisioning.

GDPR Free for Subscribers

Setup Cube.dev with Mastra AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Automated Query Auditing

`get_sql` extracts the exact database query generated by your semantic model. Mastra AI takes that string and evaluates it against your internal performance rules before execution. If the query looks expensive, your workflow branches to a rejection state. Otherwise, it passes the raw string to `execute_cube_sql` and returns the payload.

Mastra AI Infrastructure Checks

`check_ready` verifies your Cube deployment is actively accepting connections. This MCP Server gives your agent the ability to pause operations if the data layer goes offline. Workflows can loop through `list_deployments` to find healthy environments. The agent applies exponential backoff until the target system reports a live status.

Human-in-the-Loop Caching

`trigger_pre_aggregation_job` starts building rollups for complex dashboards. You configure Mastra to require human approval before running this on production clusters. Once approved, the workflow fires the job and enters a waiting state. It repeatedly checks `get_pre_aggregation_job_status` until completion, then sends a Slack alert.

Setup guide

Set up Cube.dev MCP in Mastra AI

Prerequisites

Node.js 18+ and a TypeScript project
@mastra/mcp + @mastra/core packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run npm install @mastra/mcp @mastra/core plus your preferred model provider (e.g. @ai-sdk/openai).
2

Configure the MCPClient
Create an MCPClient with your Vinkius endpoint as a URL object. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Discover and inject tools
Call mcpClient.listTools() and spread the result into your agent's tools object. All Cube.dev tools become native Mastra tools.
4

Run with any model
Swap openai("gpt-4o") for any AI SDK-compatible provider. Call agent.generate() and the agent routes tool calls through MCP automatically.

agent.ts

import { MCPClient } from "@mastra/mcp";
import { Agent } from "@mastra/core/agent";
import { openai } from "@ai-sdk/openai";

const mcpClient = new MCPClient({
  id: "cubedev-mcp-client",
  servers: {
    "cubedev-mcp": {
      url: new URL(
        "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
      ),
    },
  },
});

const agent = new Agent({
  name: "Cube.dev Agent",
  model: openai("gpt-4o"),
  instructions: "You have access to Cube.dev tools.",
  tools: {
    ...(await mcpClient.listTools()),
  },
});

const result = await agent.generate(
  "List recent Cube.dev transactions"
);
console.log(result.text);

Get your connection token →

Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by Cube.dev. All third-party trademarks, logos, and brand names are the property of their respective owners. Their use on this website is strictly for informational purposes to identify service compatibility and interoperability.

Why Choose Vinkius

Vinkius connects your tools to AI with real-time monitoring and automatic cost savings — all from one dashboard.

Connect Cube.dev now

Real-time monitoring

Live

visibility into every interaction

Connect your favorite tools to your AI and see exactly what's happening — every request, every response, in real time.

Built-in savings

60%

lower AI costs

Vinkius compresses data between your apps and your AI automatically. Lower bills every month — no configuration required.

Single dashboard

One

place for every integration

Every tool your AI connects to, managed from a single screen. One account, complete control.

Common questions about Cube.dev MCP in Mastra AI

Run `npm install @mastra/mcp@latest`. Add the Vinkius URL to your `MCPClient` configuration block.

Yes. The workflow engine handles exponential backoff natively. If a query times out, the agent tries again.

Use `requireToolApproval` in your Mastra config. This forces a human to click yes before triggering aggregation jobs.

Auto-detection handles the transport layer for you. The client switches between SSE and Streamable HTTP based on the endpoint.

The server touches raw SQL strings, pre-aggregation statuses, and environment IDs. Every execution happens inside a zero-trust V8 sandbox that drops all state the moment the workflow step ends.

Use it with your favorite AI tools

Connect this server to Cursor, Claude, VS Code, and more.

OpenAI Agents SDK sdk-python

Google ADK sdk-python

Pydantic AI sdk-python

Vercel AI SDK sdk-typescript