How to Use the Cloud BOT MCP in Vercel AI SDK

Q: Can Vercel AI SDK cancel a running Cloud BOT job mid-execution?

Yes, your agent calls canceljob if a user aborts the request or if a timeout occurs. This stops the remote browser instance immediately to prevent wasted runtime.

Q: How does Cloud BOT stream execution statuses back to Vercel AI SDK?

The agent uses getjobstatus inside a streaming loop to feed progress updates to the UI. The user sees the exact step the browser bot is executing in real time.

Q: How do I get a list of all available RPA tasks?

You call listbots to retrieve every configured browser flow. Your agent reads this list to determine which automation fits the user's natural language request.

Run Cloud BOT browser automations directly from your Next.js frontend and stream real-time job updates to users via 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 Cloud BOT MCP to Vercel AI SDK

Create your Vinkius account to connect Cloud BOT 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 Cloud BOT with Vercel AI SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Execute Cloud BOT tasks live in Vercel AI SDK

This MCP Server connects your web app directly to cloud-based browser automation. Your Vercel AI SDK client triggers browser scripts instantly using `execute_bot` while your frontend streams the execution state as it happens. Users watch data extraction occur in real time instead of staring at a static loading spinner. You pass parameters directly from your React components to the runtime. If a run hangs or hits an error, your UI can trigger `cancel_job` immediately to save API credits and keep the user in control.

Track browser job pipelines dynamically

This MCP Server gives your edge functions direct visibility into active browser tasks. Your Vercel AI SDK agent checks on running tasks using `get_job_status` and updates the UI state without polling overhead. You list all available RPA tasks using `list_bots` to build dynamic configuration forms for your users. The agent reads the available inputs, renders the form fields, and starts the automation with a single streaming text call.

Stream scraped files directly to your frontend

This MCP Server exposes remote storage access directly to your Next.js edge route. Your Vercel AI SDK UI displays downloaded PDFs or CSVs by invoking `list_cloudbot_files` as soon as the automation finishes. The agent verifies the output files match user expectations before rendering download links. This keeps your serverless functions light because the files stay in cloud storage until the user requests them.

Setup guide

Set up Cloud BOT 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 Cloud BOT 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 Cloud BOT 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 Cloud BOT. 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 Cloud BOT 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 Cloud BOT MCP in Vercel AI SDK

Provide the Vinkius token in the setup of your MCP client. The SDK manages the connection headers, so your edge functions authenticate automatically without storing third-party secrets in client-side code.

Yes, your agent calls `cancel_job` if a user aborts the request or if a timeout occurs. This stops the remote browser instance immediately to prevent wasted runtime.

The agent uses `get_job_status` inside a streaming loop to feed progress updates to the UI. The user sees the exact step the browser bot is executing in real time.

You call `list_bots` to retrieve every configured browser flow. Your agent reads this list to determine which automation fits the user's natural language request.

Your scraped CSV files, browser automation logs, and target URLs never touch intermediate servers. Vinkius runs the connection in an isolated V8 sandbox, routing execution payloads directly between your edge deployment and the browser runner.

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