How to Use the ISO New England MCP in Vercel AI SDK

Q: How do I connect the ISO New England MCP Server to my Vercel AI SDK project?

Install @ai-sdk/mcp and set up the transport pointing to your Vinkius endpoint URL. Call mcpClient.tools() to grab the grid tools and pass them directly into streamText. Remember to call mcpClient.close() once the stream finishes to avoid leaking connections.

Q: Can I stream real-time price changes from ISO New England using Vercel AI SDK?

Yes. By combining getlmp with streamText, the LLM fetches the 5-minute locational marginal pricing and streams the formatted numbers directly into your React components. The UI updates in real-time as the tokens arrive.

Feed real-time ISO New England grid metrics and market prices directly into your React frontends using the 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 ISO New England MCP to Vercel AI SDK

Create your Vinkius account to connect ISO New England 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 ISO New England with Vercel AI SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Live pricing updates on your MCP Server dashboard

The ISO New England MCP Server exposes real-time grid status and local marginal pricing through `get_system_load` and `get_lmp`. Your frontend displays these numbers as they shift. The Vercel AI SDK streams the raw numbers right into your UI components without making the user wait for a full page reload. When prices spike in Boston, your app reacts instantly. The agent pulls the latest megawatt data and formats it into a clean table. You get a fast, responsive interface that updates before the grid operator even updates their public HTML pages.

Carbon tracking for green applications

Environmental tracking happens instantly when your Vercel AI SDK client calls `get_fuel_mix` via the MCP. This tool returns the exact percentage of coal, gas, nuclear, and renewables running the grid right now. Your user-facing dashboard can render a live carbon footprint gauge based on actual generation. You don't have to build complex cron jobs to pull this data. Your user asks the chat interface about current clean energy levels, and the agent uses this MCP tool to fetch the exact breakdown. It's direct, fast, and runs entirely on edge functions to keep latency low.

7-day grid planning with Vercel AI SDK

Your Vercel AI SDK application maps out future grid demand using `get_seven_day_forecast`. This tool gives your client the expected consumption trends for the upcoming week. It lets you build interactive charts that show users when peak hours will hit. The agent digests the raw megawatt projections and spits out clean JSON for your charting library. Instead of writing custom parsing code for ISO New England data, you let the LLM handle the transformation on the fly.

Setup guide

Set up ISO New England 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 ISO New England 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 ISO New England 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 ISO New England. 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 ISO New England 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 ISO New England MCP in Vercel AI SDK

Install `@ai-sdk/mcp` and set up the transport pointing to your Vinkius endpoint URL. Call `mcpClient.tools()` to grab the grid tools and pass them directly into `streamText`. Remember to call `mcpClient.close()` once the stream finishes to avoid leaking connections.

Yes. By combining `get_lmp` with `streamText`, the LLM fetches the 5-minute locational marginal pricing and streams the formatted numbers directly into your React components. The UI updates in real-time as the tokens arrive.

It does. The server runs in a secure V8 sandbox on Vinkius, meaning your edge functions only need to make a standard HTTP call to fetch the data. This keeps your Next.js edge runtimes light and fast.

Vinkius handles the credentials on its side. Your code only needs the single authorization token provided in your dashboard, removing the need to manage complex ISO New England API keys in your local environment variables.

This server only reads public ISO New England grid and energy market data, including fuel mix percentages and locational prices. No private user information or database credentials are ever touched or exposed to the external network.

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