How to Use the Browserhub MCP in Vercel AI SDK

Q: Can I stream live scraped text into a Next.js UI using Browserhub and Vercel AI SDK?

Yes, by passing the directscrape tool to streamText in your route handler. The scraped text feeds directly into the AI client's generation context, allowing your UI to render the parsed markdown in real-time.

Q: How does Vercel AI SDK poll for long-running Browserhub scraping jobs?

Your agent uses the MCP tool interface to call runscraper to start the job, then uses getscrapingjob to check the status. You can stream these status updates directly to your frontend to keep the user informed.

Q: What happens when my Browserhub proxy locations change?

Your app calls listproxylocations to get the latest list of exit nodes. This allows your SDK client to dynamically choose the best geography for your scrape attempt on the fly.

Feed live scraped web data straight into your Next.js frontend with Vercel AI SDK and Browserhub.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Browserhub MCP to Vercel AI SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Live URL Scraping in Vercel AI SDK

The `direct_scrape` tool pulls raw data from any URL directly into your active Vercel AI SDK stream. Instead of making your users stare at a blank loading spinner while a background job runs, this tool feeds the raw scraped markdown straight into your frontend UI as it arrives. You configure the client to call this endpoint on the edge, grabbing clean text from target sites instantly. Your React components render the incoming scraped content chunk by chunk, giving your users immediate feedback.

Run Scraper Blueprints from the Edge

The `run_scraper` tool fires off pre-configured scraping blueprints to extract structured data without blocking your Vercel AI SDK edge runtime. You trigger the job, and the SDK monitors the progress by calling `get_scraping_job` in a clean, non-blocking polling loop. This setup keeps your Next.js API routes fast and within execution limits. Your users see the extraction status update live on their screen, moving from queued to completed as Browserhub handles the heavy lifting in the background.

Manage Browserhub MCP Server Blueprints in React

The `list_blueprints` and `get_blueprint` tools let your frontend dynamically fetch your stored scraping configurations. Your Vercel AI SDK client reads these blueprints through the MCP Server to understand what data structures are available before it even initiates a scrape. This means you can build a dynamic UI where users select a target site, and your React app automatically configures the LLM to expect the exact schema defined in that blueprint. You don't have to hardcode scraping schemas on your client side anymore.

Setup guide

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

You pass your single Vinkius endpoint token into the MCP client transport configuration. Vinkius handles the underlying API keys securely, so your Next.js edge functions never expose raw Browserhub credentials to the browser.

Yes, by passing the `direct_scrape` tool to `streamText` in your route handler. The scraped text feeds directly into the AI client's generation context, allowing your UI to render the parsed markdown in real-time.

Your agent uses the MCP tool interface to call `run_scraper` to start the job, then uses `get_scraping_job` to check the status. You can stream these status updates directly to your frontend to keep the user informed.

Your app calls `list_proxy_locations` to get the latest list of exit nodes. This allows your SDK client to dynamically choose the best geography for your scrape attempt on the fly.

Yes, all scraped URLs and raw text processed by Browserhub run inside ephemeral V8 isolates on Vinkius. Your scraped payloads are never stored on persistent disks, keeping your data collection completely private.

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