How to Use the Browserbear MCP in Vercel AI SDK

Stream Browserbear automation results directly into your Vercel AI SDK frontends for live, real-time feedback.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Browserbear MCP to Vercel AI SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Live browser task execution in Vercel AI SDK

Trigger automated workflows directly from your React components using `run_task`. Your users watch the data arrive as the stream processes. This MCP Server handles the heavy lifting while your UI updates instantly. No more waiting for spinners to resolve before showing results.

Capture visual state with Browserbear

Use `take_screenshot` to grab current page views for your application dashboard. It saves time by pulling the image directly into your state management. Your frontends pull these snapshots to confirm task progress. It's a quick way to verify what the bot actually sees.

Manage Browserbear projects via code

Call `list_projects` to populate your application menus dynamically. You can build custom interfaces that map directly to your backend setup. This approach keeps your UI in sync with your automation environment. You'll never hardcode a project ID again.

Setup guide

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

You initialize the client via the HTTP transport in your edge functions. Use the provided endpoint token to handle authentication for your Vercel AI SDK routes.

Yes, the tool results stream back as the agent executes them. You get the output immediately within your AI SDK response stream.

Browserbear only handles the task run records and screenshots you explicitly trigger. Your Vercel AI SDK session keys remain on your server, not ours.

Absolutely. Just define the tool client in your server file and call the functions as part of your standard logic flow.

The server returns an error object that you can catch in your code. You decide how the UI handles that failure state for your end users.

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