How to Use the Browse AI MCP in Vercel AI SDK

Q: How do I trigger a Browse AI extraction using Vercel AI SDK?

You call triggerrobotrun inside your route handler through this MCP Server. The server handles the API handshake, letting your agent start the task and return the run ID instantly.

Q: Can Vercel AI SDK check my remaining Browse AI extraction credits?

Yes, your agent can call getusagequotas to verify your remaining Browse AI credits. This is useful for blocking expensive operations before they run on your edge functions.

Q: How do I list my active Browse AI scrapers in Vercel AI SDK?

You invoke listrobots through the MCP client to get a list of all your trained scraper robots. The agent can then parse this list to let the user select which site they want to extract.

Q: Do I need to manage long-polling for slow extractions?

No, you can have your agent periodically call getrunstatus to check the progress. This keeps your edge functions light and prevents them from timing out on long scraping jobs.

Feed live web scraping data directly into your frontend components in real-time 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

Live Scraping Streams in Vercel AI SDK

When your user requests a live web scrape, your frontend doesn't need to sit behind a loading spinner. Your Next.js app calls `trigger_robot_run` and streams the status updates straight to the UI as they happen. You can display the progress of the scraper by polling `get_run_status` inside your edge functions with this MCP Server. The end user watches the extraction progress live, making your application feel incredibly fast and responsive.

Dynamic Robot Selection on the Edge

Your edge routes can query your active scraper fleet instantly. By calling `list_robots`, your agent identifies which scraper fits the user's current request without hardcoding IDs. Once the right scraper is found, the agent uses `get_robot_details` to check its input parameters. This lets you build dynamic forms that adapt to whatever scraping robots you have trained in your account.

Real-time Quota and History Monitoring

Keep your users informed about their usage limits directly in your application's dashboard. Your agent fetches the current credit balance via `get_usage_quotas` to prevent unnecessary run failures. This MCP Server pulls the run logs using `list_robot_history` whenever a user wants to audit their past extractions. It displays the historical data on your screen without requiring a custom database setup.

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

You call `trigger_robot_run` inside your route handler through this MCP Server. The server handles the API handshake, letting your agent start the task and return the run ID instantly.

Yes, your agent can call `get_usage_quotas` to verify your remaining Browse AI credits. This is useful for blocking expensive operations before they run on your edge functions.

You invoke `list_robots` through the MCP client to get a list of all your trained scraper robots. The agent can then parse this list to let the user select which site they want to extract.

No, you can have your agent periodically call `get_run_status` to check the progress. This keeps your edge functions light and prevents them from timing out on long scraping jobs.

Completely. Vinkius runs the server in an isolated V8 sandbox, meaning your API tokens and scraped website data are never exposed to the public internet or stored on disk. All execution is ephemeral and secure.

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