How to Use the Newslit MCP in Vercel AI SDK

Q: How do I stream Newslit media tracking data using Vercel AI SDK?

You pass the tools from createMCPClient directly into the tools parameter of streamText. This lets your Next.js frontend render live press updates using the liststories tool. The client handles the connection automatically and streams the JSON payloads.

Q: What is the best way to handle UI updates when deleting reports?

You execute deletereport within a server action and trigger a shallow router refresh. This removes the stale tracking data from the React layout immediately. The client handles the underlying API call.

Build Next.js apps that stream real-time media intelligence reports to users live 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 Newslit MCP to Vercel AI SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Stream live media coverage feeds with Vercel AI SDK

The `list_stories` tool pulls current press coverage directly into your streaming UI components. Your application renders live updates as stories hit the wire, so you don't deal with stale data. It's a direct connection via the MCP Server that bypasses slow middleware. Next.js developers pass this tool directly into `streamText` to construct dynamic feeds. Users watch their media impact metrics populate line-by-line on the edge. This approach eliminates the loading spinners that ruin modern web interfaces.

Build interactive report editors in React

The `update_report` tool allows your AI client to modify active media tracking parameters on the fly based on user chat inputs. This lets communications teams adjust their tracking filters inside a conversational interface without refreshing the browser. The MCP connection handles the state changes behind the scenes. You hook this tool into the `ai-sdk` client-side state to update the UI instantly. The dashboard adapts immediately as the user refines their search criteria. It makes managing media briefs feel like a natural conversation.

Instantly generate press summaries on the edge

The `create_report` tool generates a structured news tracking document directly from an edge function execution. This allows your application to spin up custom media briefs on demand when a user requests a fresh brand audit. The MCP protocol ensures the payload format matches your database schema exactly. By combining this tool with the streaming capabilities of the SDK, your front-end displays raw press data as structured reports in real-time. It eliminates cold-start delays and keeps communication teams engaged during fast-moving PR crises.

Setup guide

Set up Newslit 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 Newslit 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 Newslit 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 Newslit. 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 Newslit 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 Newslit MCP in Vercel AI SDK

You pass the tools from `createMCPClient` directly into the `tools` parameter of `streamText`. This lets your Next.js frontend render live press updates using the `list_stories` tool. The client handles the connection automatically and streams the JSON payloads.

Yes, this setup works with edge runtimes. You initialize the client in your API route and call `get_report` to fetch coverage metrics without cold-start penalties. The lightweight transport ensures your media intelligence dashboards load instantly.

The SDK reads the tool definitions directly from the server endpoint. When your agent calls `create_report`, the SDK validates the JSON payload before executing the call. You do not need to write manual schemas.

You execute `delete_report` within a server action and trigger a shallow router refresh. This removes the stale tracking data from the React layout immediately. The client handles the underlying API call.

Your press stories and tracking configurations are processed in isolated V8 sandboxes. Vinkius secures this connection with single-token authentication, ensuring your internal communication strategies never leak to public networks.

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