How to Use the Browse AI MCP in Vercel AI SDK

Q: How do I configure the Browse AI MCP Server with Vercel AI SDK?

Install the MCP client package and initialize it using createMCPClient with your HTTP endpoint. Pass the tools directly to streamText or generateText to let your agent start scraping.

Q: Can Vercel AI SDK handle bulk Browse AI scraping runs?

Yes, your agent can trigger parallel scrapes using runbulktask and monitor them. It polls the status with getbulktask and streams the results back as soon as they are ready.

Q: How does the Browse AI integration with Vercel AI SDK manage API credits?

Your agent calls listcredits to check your current usage before starting any heavy scraping tasks. This helps you prevent out-of-credit errors during live streaming sessions.

Q: Where does the extracted web data go when using this MCP Server?

All scraped JSON data from gettaskdata passes directly through Vinkius's secure sandbox to your Vercel AI SDK application. No scraped content is stored on our servers, keeping your data confidential.

Get live-extracted web data directly on your user's screen using Browse AI 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 Browse AI MCP to Vercel AI SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Stream Bulk Scrapes in Vercel AI SDK

Your Next.js app doesn't have to freeze while waiting for web scraping jobs. This MCP Server lets your frontend trigger massive concurrent scrapes across multiple URLs using `run_bulk_task` and stream the status updates directly to your users. Once the scraping jobs finish, the agent uses `download_bulk_data` to pull down the structured JSON arrays. Your UI updates in real-time as the data flows in, keeping your Edge Functions fast and your users engaged.

Inspect Scraper Configurations on the Fly

Let your agent inspect exactly how your web scrapers are built before running them. By calling `get_robot`, your Vercel AI SDK setup reads the exact selectors and schema your scraper expects. This prevents runtime errors when your UI triggers a scraping run. The agent matches user inputs directly to the robot's expected fields, then kicks off the extraction with `run_robot` to get clean data.

Monitor Scraping Budgets in Your UI

Keep an eye on your scraping costs directly inside your client dashboard using this MCP Server. The agent uses `list_credits` to fetch your remaining Browse AI balance and displays it live to your users. It also tracks active schedulers using `list_monitors` to show which pages are currently being watched for changes. Your Vercel AI SDK frontend stays updated without manual polling.

Setup guide

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

Install the MCP client package and initialize it using `createMCPClient` with your HTTP endpoint. Pass the tools directly to `streamText` or `generateText` to let your agent start scraping.

Yes, your agent can trigger parallel scrapes using `run_bulk_task` and monitor them. It polls the status with `get_bulk_task` and streams the results back as soon as they are ready.

Your agent calls `list_credits` to check your current usage before starting any heavy scraping tasks. This helps you prevent out-of-credit errors during live streaming sessions.

No, your agent cannot modify the scrapers directly, but it can read their configuration using `get_robot`. This lets the agent understand what parameters are needed before running a job.

All scraped JSON data from `get_task_data` passes directly through Vinkius's secure sandbox to your Vercel AI SDK application. No scraped content is stored on our servers, keeping your data confidential.

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