How to Use the Diffbot MCP in Vercel AI SDK

Q: How do I stream Diffbot extraction results using the Vercel AI SDK?

You initialize the client using createMCPClient and pass the tools to streamText. This allows your UI to display live data from extractarticledata as it resolves. No more blockages or long loading screens.

Q: How does the Vercel AI SDK handle Diffbot MCP authentication?

You manage credentials using the authProvider configuration during client setup. This secures your API token while letting your agent call testdiffbotauth to verify the active session.

Render structured web data in real time using the Vercel AI SDK and Diffbot.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Diffbot MCP to Vercel AI SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Stream product details live using Vercel AI SDK

Stop making users stare at loading spinners. This MCP Server lets your application grab raw e-commerce data on the fly. You run `extract_product_data` and watch the structured price, availability, and specs feed straight into your frontend components. The Vercel AI SDK handles the plumbing so you don't have to write custom API endpoints. You get clean JSON back immediately. It feels like magic because it bypasses the typical backend lag.

Live profile enrichment on the edge

Edge functions need to run fast and light with an MCP setup. When a new user signs up, pass their details to `enhance_person_profile` or `enhance_company_profile` to populate your UI instantly. Traditional databases make you wait for batch syncs. This setup fetches fresh, structured market intelligence the moment your client requests it. Your application stays snappy because the data streams in chunks.

Parse complex layouts without custom scrapers

Writing custom CSS selectors is a fool's errand. Instead, let your agent use `extract_article_data` and `extract_forum_thread` to pull clean text from messy sites. Web layouts change daily, but this tool handles the variance. Your Next.js app stays functional without constant maintenance commits when using this MCP integration.

Setup guide

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

You initialize the client using `createMCPClient` and pass the tools to `streamText`. This allows your UI to display live data from `extract_article_data` as it resolves. No more blockages or long loading screens.

Yes, the server is fully compatible with Edge environments. You just need to configure the HTTP transport with your endpoint token. It keeps your serverless execution times low.

You manage credentials using the `authProvider` configuration during client setup. This secures your API token while letting your agent call `test_diffbot_auth` to verify the active session.

The extraction doesn't break because the underlying AI model interprets the visual layout. It relies on cognitive understanding rather than brittle CSS paths. You won't need to redeploy your Next.js application.

Your raw HTML and target URLs are processed in a secure, ephemeral V8 sandbox. No data is stored or logged after the extraction completes. The transaction remains entirely zero-trust.

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