How to Use the Crawlbase MCP in Vercel AI SDK

Q: How do I connect Crawlbase to my Vercel AI SDK setup?

Install @ai-sdk/mcp and initialize the client using the Vinkius HTTP transport URL. Pass the tools directly into streamText to let your agent call the MCP endpoint.

Q: Can the Vercel AI SDK handle JavaScript-heavy sites with Crawlbase?

Yes. The scrapejsrendered tool executes the target page's scripts before returning the DOM. Your agent receives the fully evaluated HTML to parse.

Q: How does Crawlbase prevent IP blocks during Vercel AI SDK runs?

The customscrape tool routes your requests through high-availability proxies. This shifts the scraping load away from your Vercel deployment IPs.

Feed raw HTML and social data straight from Crawlbase into your Vercel AI SDK frontend without loading spinners.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Crawlbase MCP to Vercel AI SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Render JS Pages Live in Vercel AI SDK

`scrape_js_rendered` executes JavaScript on target pages to trace payload IDs through cloud logs. Your frontend gets the fully rendered DOM immediately, skipping the usual blank screens caused by client-side hydration. The Vercel AI SDK pipes this raw markup to your LLM. It extracts the structured data and streams it to the user's viewport in real-time.

Parse Amazon Arrays on the Edge

This MCP server tool inspects deep internal arrays on product listings while avoiding common e-commerce rate limits. You bypass the blocks that usually stop standard cloud functions from reading inventory. Edge-compatible execution means your serverless functions don't timeout waiting for the page to load. The agent extracts pricing and reviews, then formats them for your UI.

Extract Social Profiles Directly to Your UI

`scrape_facebook` exports active social pages by applying structured rules to target profiles. Your AI agent reads the raw profile elements without manual browser automation. The server handles the underlying proxy rotation automatically. This keeps your React UI responsive while your agent grabs social data.

Setup guide

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

Install `@ai-sdk/mcp` and initialize the client using the Vinkius HTTP transport URL. Pass the tools directly into `streamText` to let your agent call the MCP endpoint.

Yes. The `scrape_js_rendered` tool executes the target page's scripts before returning the DOM. Your agent receives the fully evaluated HTML to parse.

It does. The MCP client uses standard HTTP fetch transports, which run perfectly inside the Vercel Edge runtime without Node.js dependencies.

The `custom_scrape` tool routes your requests through high-availability proxies. This shifts the scraping load away from your Vercel deployment IPs.

Target URLs and retrieved HTML payloads pass through an ephemeral, zero-trust V8 sandbox. Vinkius does not store the raw content of your scrape requests.

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