How to Use the Olostep MCP in Vercel AI SDK

Q: Can Vercel AI SDK handle Olostep batch results asynchronously?

Yes. You trigger the batch, store the ID, and then poll getbatch until the status indicates completion. Your frontend can then render the final dataset once the promise resolves.

Q: Does Olostep support JavaScript rendering for Vercel AI SDK?

Every scrapeurl call defaults to a headless browser environment. It executes JS before returning the DOM, so your AI client gets the fully rendered page content.

Stream structured web data directly into your Vercel AI SDK frontends using the Olostep MCP server.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers — Included with Plan

Connect Olostep MCP to Vercel AI SDK

Create your Vinkius account to connect Olostep to Vercel AI SDK — we handle the hosting, security, and runtime updates so you don't have to. No server setup required.

GDPR Included with Plan

Setup Olostep with Vercel AI SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity Vinkius runs on Gemini

Gemini

Grok

Real-time web data for Vercel AI SDK

Feed live web content into your React or Next.js components by piping results from `scrape_url` through your AI client. Your users see data populate in real-time as the stream processes, removing the need for clunky loading states. This is ideal for building dynamic dashboards that require fresh data. You simply trigger the tool, and the raw markdown flows into your UI state.

Manage scraping volume with Olostep

Keep your project within budget by checking your credit balance via `get_usage` before spinning up new tasks. You can programmatically gate your features based on the remaining API credits returned by the server. It’s a straightforward way to prevent overages while maintaining a high-performance scraping pipeline. You'll always know exactly how many requests you have left to burn.

Batch processing for large data sets

Handle thousands of URLs without overloading your main thread by using `create_batch` to offload work to the Olostep infrastructure. Once the job is submitted, use `get_batch_results` to retrieve the processed content once it's ready. This asynchronous pattern keeps your edge functions responsive and prevents timeouts. It's the standard approach for indexers or data aggregators that don't need immediate, single-page results.

Setup guide

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

Install the MCP packages and instantiate the client using the HTTP transport. Point your configuration to the Vinkius endpoint, and you can immediately call tools like `list_agents` within your generateText functions.

Yes. You trigger the batch, store the ID, and then poll `get_batch` until the status indicates completion. Your frontend can then render the final dataset once the promise resolves.

Olostep keeps your scraped content isolated in ephemeral sessions. We don't store your target URLs or the resulting text on our servers beyond the duration of your immediate task.

The tool will return an error object that your agent can catch. You should implement basic retries or notify the user that the specific URL was unreachable.

Every `scrape_url` call defaults to a headless browser environment. It executes JS before returning the DOM, so your AI client gets the fully rendered page content.

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