How to Use the H2O.ai MCP in Vercel AI SDK

Q: How do I hook up H2O.ai to Vercel AI SDK?

Install the @ai-sdk/mcp package and initialize the client using createMCPClient. You then pass the tools from your client directly into your generateText or streamText function call. Always call close() once the streaming session completes.

Get real-time H2O.ai cluster jobs and data frame metrics directly inside your Vercel AI SDK frontend with 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 H2O.ai MCP to Vercel AI SDK

Create your Vinkius account to connect H2O.ai 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 H2O.ai with Vercel AI SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Stream H2O.ai cluster status to Vercel AI SDK

The `cloud_status` tool lets your Next.js application pull live data straight from your H2O.ai clusters over a secure MCP connection. Stop making users stare at boring loading spinners while waiting for heavy ML cluster updates. By passing the status directly to your streaming text generation, you let your agent write out active node counts and memory pressure as they happen. You don't have to write complex API polling logic or websocket handlers. The SDK streams the raw cluster states directly into your React components. Your users get immediate visibility into active jobs without lag.

Live model tracking via Vercel AI SDK

The `list_models` tool lets your agent inspect model registry changes on the fly. When a user asks about model performance, the agent calls `get_model` to fetch hyperparameters and validation metrics immediately. The tool results feed straight into your UI components using the Edge-compatible client. You can render interactive charts or comparison tables of different model versions without blocking the main execution thread.

Instant data frame inspection

The `list_frames` tool locates your target dataset so your agent can inspect massive datasets without opening a separate dashboard. Your agent uses `get_frame` to pull down column summaries and row previews. This setup lets your frontend display data distributions directly inside the chat interface. You get raw schema details and row counts rendered in real-time, helping you debug training inputs without switching contexts.

Setup guide

Set up H2O.ai 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 H2O.ai 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 H2O.ai 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 H2O.ai. 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 H2O.ai 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 H2O.ai MCP in Vercel AI SDK

Install the `@ai-sdk/mcp` package and initialize the client using `createMCPClient`. You then pass the tools from your client directly into your `generateText` or `streamText` function call. Always call `close()` once the streaming session completes.

Yes, the SDK excels at streaming live updates from long-running tasks. Your agent can run `list_jobs` to poll the cluster and stream the active status block by block. This means your frontend updates incrementally as the training progress changes.

It is fully compatible with Edge runtimes. Because this MCP Server routes requests through a single secure endpoint, you avoid heavy client-side SDK footprints. Your Edge functions stay lightweight and highly responsive.

No custom parsers are required. The server returns clean JSON payloads from `get_model` that your agent interprets naturally. You can map these structured outputs directly to your React UI components.

All communications run inside a secure V8 sandbox on Vinkius. Your data frame names, schemas, and row previews accessed via `get_frame` are never stored or exposed to external networks. The server acts as an ephemeral proxy, keeping your training data isolated.

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