How to Use the NREL Energy Data MCP in Vercel AI SDK

Q: How do I stream NREL Energy Data with the Vercel AI SDK?

Install the @ai-sdk/mcp package and initialize the MCP client. Then, pass the tools directly into streamText to let your agent call NREL endpoints and stream the results live to your UI.

Q: Can I filter the NREL Energy Data tools in my Vercel AI SDK setup?

Yes, you can select specific tools like getneareststations before passing them to your agent. This prevents the model from getting confused by tools you do not need for your specific UI.

Q: Which solar datasets can I access with this integration?

You can query availability via getsolardataquery to check what data exists for a region. From there, pull actual radiation metrics using getsolarresource to feed your frontend widgets.

Feed real-time NREL energy estimates and charging station maps directly into your React frontend with 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 NREL Energy Data MCP to Vercel AI SDK

Create your Vinkius account to connect NREL Energy Data 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 NREL Energy Data with Vercel AI SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Stream Solar Estimates using Vercel AI SDK

Your application calls `get_pvwatts_estimates` to calculate solar energy output based on specific geographic coordinates. Users get instant numbers on their screens without waiting for a full page reload or staring at a blank loading state. This Vinkius MCP server feeds raw solar radiation data from `get_solar_resource` straight to your streaming UI. Charts render live on the screen the second the numbers arrive.

Locate Alternative Fuel Stations Live

Finding charging options starts with `list_alt_fuel_stations` to fetch a raw list of nearby infrastructure. Your agent parses this dataset on the fly, matching it with user locations instantly. To get specific connector types or hours, the agent triggers `get_station_details` for deeper inspection. This setup runs inside Vercel Edge Functions, keeping latency low and responses snappy.

Calculate Utility Rates on the Fly

Retrieving average electricity rates with `get_utility_rates` lets your app calculate localized charging costs instantly. Clients compare regional pricing without manual lookup tables. By coupling this with `get_utility_companies`, your interface shows the exact service providers in any zip code. This MCP integration makes building cost-comparison tools straightforward.

Setup guide

Set up NREL Energy Data 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 NREL Energy Data 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 NREL Energy Data 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 NREL. 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 NREL Energy Data 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 NREL Energy Data MCP in Vercel AI SDK

Install the `@ai-sdk/mcp` package and initialize the MCP client. Then, pass the tools directly into `streamText` to let your agent call NREL endpoints and stream the results live to your UI.

Yes, you can select specific tools like `get_nearest_stations` before passing them to your agent. This prevents the model from getting confused by tools you do not need for your specific UI.

Vinkius manages the underlying API keys and handles the traffic queuing. Your serverless functions make standard calls to the MCP server, and we handle the connection stability.

You can query availability via `get_solar_data_query` to check what data exists for a region. From there, pull actual radiation metrics using `get_solar_resource` to feed your frontend widgets.

We run every connection in an isolated MCP sandbox environment. Your geographic coordinates, zip codes, and utility queries pass through temporary memory and are never stored or logged on our servers.

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