How to Use the News MCP in Vercel AI SDK

Q: How do I handle API rate limits when searching News with the Vercel AI SDK?

You should cache the results of gettopheadlines at your edge route level. For heavy research tasks using searcheverything, implement debounce mechanisms on your frontend input to prevent users from firing off too many rapid requests.

Q: Can I stream News articles directly into a React component using Vercel AI SDK?

Yes, that is the main benefit of this setup. You call mcpClient.tools() and pass them to streamText, which allows the model to search articles and render them live in your UI component as the chunks arrive.

Q: Does the News MCP server support OAuth when used with Vercel AI SDK?

Yes, you can configure the client using the authProvider option. This ensures that only authenticated users on your React frontend can trigger the underlying news search tools.

Q: How do I clean up the MCP connection after fetching articles?

You must call mcpClient.close() once your streaming session ends. If you don't close it in your Next.js API route, you'll leave dangling HTTP sockets which eventually exhaust your serverless environment resources.

Stream real-time global headlines and search articles directly into your Next.js or React frontend 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 News MCP to Vercel AI SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Live headline streams for your Vercel AI SDK UI

Feed breaking news straight to your users without making them stare at a loading spinner using `get_top_headlines`. By coupling the Vercel AI SDK with this MCP Server, your app calls the tool to pull live updates and render them instantly on the client side. You just pass the server tools directly to `streamText`. The JSON payload streams chunk by chunk, so your interface populates the latest global events as soon as the model processes the incoming feed.

Advanced news search with boolean logic

Stop relying on static feeds and let your users hunt down specific stories with `search_everything`. The tool supports operators like AND, OR, and NOT, allowing your Vercel AI SDK agent to build highly targeted queries across 150,000 sources. Since this Next.js edge setup runs fine on edge functions, you can execute these complex news searches globally with minimal latency. It keeps your article search interface fast while digging through millions of indexed articles.

Dynamic source filtering for cleaner data

Avoid messy feeds by letting your React or Next.js app filter out unreliable publishers with `list_sources`. Your agent uses the tool to check which news outlets are active before fetching their top stories. This prevents the model from hallucinating dead links or scanning low-quality blogs. You get a clean list of publishers that your frontend can display as toggle options for the user.

Setup guide

Set up News 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 News 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 News 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 NewsAPI. 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 News 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 News MCP in Vercel AI SDK

You should cache the results of `get_top_headlines` at your edge route level. For heavy research tasks using `search_everything`, implement debounce mechanisms on your frontend input to prevent users from firing off too many rapid requests.

Yes, that is the main benefit of this setup. You call `mcpClient.tools()` and pass them to `streamText`, which allows the model to search articles and render them live in your UI component as the chunks arrive.

Yes, you can configure the client using the `authProvider` option. This ensures that only authenticated users on your React frontend can trigger the underlying news search tools.

You must call `mcpClient.close()` once your streaming session ends. If you don't close it in your Next.js API route, you'll leave dangling HTTP sockets which eventually exhaust your serverless environment resources.

Vinkius runs this tool inside an isolated V8 sandbox, meaning your search queries are never stored or logged on our infrastructure. The fetched news headlines pass directly through an ephemeral memory layer and are completely wiped the second your session closes.

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