How to Use the Cube.dev MCP in Vercel AI SDK

Q: How do I connect the Vercel AI SDK to Cube.dev?

Install @ai-sdk/mcp and initialize createMCPClient. Point the MCP Server HTTP transport to your Vinkius endpoint.

Q: Can Vercel AI SDK agents read my Cube.dev schemas?

Yes. Call mcpClient.tools() to expose the MCP tools. The agent will read your dimensions automatically.

Q: Does this support Vercel Edge Functions?

It works perfectly on the Edge. Just remember to call mcpClient.close() when your stream finishes.

Stream live metrics from your semantic layer straight into React components using the Cube.dev MCP Server and Vercel AI SDK.

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 Vercel AI SDK

Create your Vinkius account to connect Cube.dev to Vercel AI SDK 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 Vercel AI SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Vercel AI SDK Data Streaming

`load_query` grabs aggregated data directly from your semantic layer. Your React frontend receives those results as a live stream through Vercel AI SDK, bypassing loading spinners entirely. End users watch the metrics appear on their dashboard in real-time. You can also run `convert_query` to flip SQL into REST API formats before hitting the client.

Dynamic Schema Discovery

`get_meta` pulls the exact dimensions and measures available in your cubes. Exposing this through an MCP Server lets your agent build correct queries without guessing schema names. If a user asks for revenue by region, the agent checks `list_entities` first. It maps the natural language request to actual data models before streaming the answer back.

On-Demand Pre-aggregations

`trigger_pre_aggregation_job` forces a rebuild of your cached data layers. You bind this to a button in your Next.js admin panel. When the user clicks refresh, the agent fires the job. It then polls `get_pre_aggregation_job_status` to update a progress bar on the screen.

Setup guide

Set up Cube.dev MCP in Vercel AI SDK

Prerequisites

Node.js 18+ and a TypeScript project
ai + @modelcontextprotocol/sdk packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies

Run npm install ai @modelcontextprotocol/sdk plus your preferred model provider (e.g. @ai-sdk/openai).
2

Create the Streamable HTTP transport

Use StreamableHTTPClientTransport with your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Discover and use tools

Call mcpClient.tools() to auto-discover all Cube.dev tools. Pass them directly to generateText() or streamText() — no manual schema definitions needed.
4

Works with any model provider

Swap openai("gpt-4o") for any AI SDK provider — Anthropic, Google, Mistral. The MCP tools work identically across all supported models.

index.ts

import { experimental_createMCPClient as createMCPClient } from "ai";
import { StreamableHTTPClientTransport } from "@modelcontextprotocol/sdk/client/streamableHttp";
import { generateText } from "ai";
import { openai } from "@ai-sdk/openai";

const transport = new StreamableHTTPClientTransport(
  new URL("https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp")
);

const mcpClient = await createMCPClient({ transport });
const tools = await mcpClient.tools();

const { text } = await generateText({
  model: openai("gpt-4o"),
  tools,
  prompt: "List recent Cube.dev transactions",
});

console.log(text);
await mcpClient.close();

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 Vercel AI SDK

Install `@ai-sdk/mcp` and initialize `createMCPClient`. Point the MCP Server HTTP transport to your Vinkius endpoint.

Yes. Call `mcpClient.tools()` to expose the MCP tools. The agent will read your dimensions automatically.

It works perfectly on the Edge. Just remember to call `mcpClient.close()` when your stream finishes.

Pass your Vinkius token in the transport headers. The managed MCP Server handles the actual Cube Cloud API keys.

This server processes SQL queries, schema metadata, and aggregated metric payloads. Vinkius runs the connection inside an ephemeral V8 Isolate Sandbox that destroys itself after the request. Nothing gets stored.

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