How to Use the Nodereal MCP in Vercel AI SDK

Q: How do I connect Nodereal to my app using the Vercel AI SDK?

Install the @ai-sdk/mcp package and create a client with your Vinkius endpoint URL. This MCP client connects your app to the Nodereal server. Pass the tools from mcpClient.tools() to the generateText or streamText function.

Q: What's the best way to show Aptos data from Nodereal in a Next.js app with the Vercel AI SDK?

Use streamText to have your agent call Aptos-specific tools like aptosgetaccountresources. As the data streams in, you can update your component's state. This way, your UI renders the resources one by one instead of all at once.

Use the Vercel AI SDK to stream live Aptos and EVM data from Nodereal directly into your React and Next.js apps.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Nodereal MCP to Vercel AI SDK

Create your Vinkius account to connect Nodereal 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 Nodereal with Vercel AI SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Stream On-Chain Data to Your UI

Stop making your users wait. This tool lets your agent fetch and stream data directly into your frontend components. When your agent, connected to this MCP Server, calls `eth_get_balance` or `nr_get_token_balance_20`, the Vercel AI SDK renders the balance in your UI the instant the numbers arrive, not after a loading spinner finishes. It's perfect for building live dashboards or portfolio trackers. You can show a user's NFT collection by streaming the output of `nr_get_nft_inventory`, populating the grid as each item is found. Your app feels alive because the data appears in real time.

Instant Transaction Pre-flight Checks

Let users see the outcome of a transaction before they sign it. Your agent can take user input and run it through `aptos_simulate_transaction` or `eth_estimate_gas`. The results stream back immediately, so your UI can display the expected cost and outcome without a page refresh. This isn't just for gas estimates. Use `eth_call` to test a contract interaction and show the return value directly in your app. Your users get immediate feedback, which means fewer failed transactions and less wasted gas.

Build a Real-Time Block Explorer with the Vercel AI SDK

This MCP Server gives you the raw ingredients to build your own specialized block explorer. Have your agent grab the latest block with `eth_get_block_by_number`. Then, you can use `nr_get_transaction_receipts_by_block_number` to get every single transaction inside it. Because the Vercel AI SDK streams the response, you can build a UI that populates the transaction list as it's being fetched. It's a much better experience than waiting for the entire block's data to load. This approach works for both EVM and Aptos chains, using tools like `aptos_get_blocks_by_height`.

Setup guide

Set up Nodereal 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 Nodereal 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 Nodereal 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 NodeReal. 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 Nodereal 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 Nodereal MCP in Vercel AI SDK

Install the `@ai-sdk/mcp` package and create a client with your Vinkius endpoint URL. This MCP client connects your app to the Nodereal server. Pass the tools from `mcpClient.tools()` to the `generateText` or `streamText` function.

Yes, the whole stack is edge-compatible. You can run your AI client in an Edge Function to fetch data from Nodereal with low latency. This keeps your data fetching close to your users and your app fast.

Use `streamText` to have your agent call Aptos-specific tools like `aptos_get_account_resources`. As the data streams in, you can update your component's state. This way, your UI renders the resources one by one instead of all at once.

Vinkius gives you a single endpoint token. You use this token to initialize the MCP client. The SDK handles passing the authentication header on every request to the Nodereal server, so you don't have to manage it manually.

Your requests, which contain data like wallet addresses or transaction hashes, are sent over HTTPS to your Vinkius-managed server. Vinkius isolates each server instance, and the environments are ephemeral. Your credentials are never stored on the server.

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