How to Use the Infura (Ethereum Node RPC Provider) MCP in Vercel AI SDK

Q: Can I stream historical log data from the Infura (Ethereum Node RPC Provider) using Vercel AI SDK?

Yes, you can. The agent uses ethgetLogs to grab historical event data and feeds it into your text stream to render tables on the fly.

Build live Ethereum dashboards with Vercel AI SDK streaming real-time block and gas data directly to your frontend.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Infura (Ethereum Node RPC Provider) MCP to Vercel AI SDK

Create your Vinkius account to connect Infura (Ethereum Node RPC Provider) 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 Infura (Ethereum Node RPC Provider) with Vercel AI SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Stream live chain state directly to UI components

The `eth_blockNumber` tool pulls the latest block from the Ethereum mainnet instantly. Your frontend displays this number while your agent uses `eth_getBalance` to fetch user funds in parallel. Instead of waiting for a full page reload, raw numbers feed straight into the Vercel AI SDK stream. This direct connection means users see state changes as they happen on-chain. You bypass intermediate databases by letting the agent run `eth_getCode` to verify smart contract deployments on the fly.

Run gas estimates inside edge functions

The `eth_estimateGas` tool calculates the exact gas units needed for any execution payload. By combining this with `get_suggested_gas_fees`, your application presents real-time EIP-1559 cost projections to the user. Vercel AI SDK processes these calculations inside edge functions to keep latency under 100ms. Your agent uses `eth_gasPrice` to determine if a transaction should wait for cheaper block space.

Track pending transactions via this MCP Server

The `eth_getTransactionReceipt` tool fetches execution logs and status codes once a transaction finishes. If a user submits a raw payload through `eth_sendRawTransaction`, the agent monitors its status without blocking the main UI thread. Polling is handled via `eth_getFilterChanges` to capture state updates without spamming the node. This keeps your API usage clean while giving the user instant feedback on their transaction progress.

Setup guide

Set up Infura (Ethereum Node RPC Provider) 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 Infura (Ethereum Node RPC Provider) 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 Infura (Ethereum Node RPC Provider) 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 Infura. 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 Infura (Ethereum Node RPC Provider) 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 Infura (Ethereum Node RPC Provider) MCP in Vercel AI SDK

Yes. You initialize the MCP client inside your Next.js route handler and call the tools directly from the edge runtime.

Your frontend signs the transaction locally to protect private keys. The agent then takes the hex payload and broadcasts it using the `eth_sendRawTransaction` tool.

Yes, you can. The agent uses `eth_getLogs` to grab historical event data and feeds it into your text stream to render tables on the fly.

The SDK handles the error gracefully. You can catch exceptions from tools like `eth_call` and return a clean fallback message inside the text stream.

All requests to the Infura endpoint run through the secure Vinkius sandbox. Your client-side code never sees the API key or raw transaction payloads sent to the backend.

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