How to Use the Cradl AI MCP in Vercel AI SDK

Q: How do I stream Cradl AI tool outputs using Vercel AI SDK?

You use the createMCPClient helper to connect to this MCP Server and pass the tools directly to streamText. When the agent triggers extractdatafromurl, the raw key-value pairs stream straight into your React or Next.js frontend.

Stop making users wait for OCR spinners; stream Cradl AI document extractions directly to your Vercel AI SDK frontend using this MCP Server.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Cradl AI MCP to Vercel AI SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Stream live Cradl AI extractions to Vercel AI SDK

Your users hate staring at loading spinners while documents process. When you pass `extract_data_from_url` to your Vercel AI SDK setup, you can pipe raw document data straight into your UI as the AI processes the file. The edge-compatible client lets you trigger `get_task_status` in your API routes without hitting cold starts. Your frontend displays extracted key-value pairs the millisecond Cradl AI finishes normalizing them.

Dynamic model selection during chat

Don't hardcode your document parsers. Let your Vercel AI SDK agent call `list_extraction_models` to inspect what parsers you have available on the fly based on what the user uploads. Once the agent finds the right parser via `search_models_by_name`, it pulls the exact schema details with `get_model_details`. Your UI then renders a form matching the model schema before the extraction even finishes.

Real-time batch tracking in Next.js

When users upload dozens of invoices at once, you need a way to show progress. Use `list_batches` to pull the active document queues and show a live progress bar in your React components. The agent can loop through `get_batch_details` to update individual file statuses on the fly. Because this MCP Server runs inside a zero-trust sandbox, your user's raw files stay safe while your UI updates.

Setup guide

Set up Cradl 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 Cradl 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 Cradl 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 Cradl 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 Cradl 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 Cradl AI MCP in Vercel AI SDK

You use the `createMCPClient` helper to connect to this MCP Server and pass the tools directly to `streamText`. When the agent triggers `extract_data_from_url`, the raw key-value pairs stream straight into your React or Next.js frontend.

Yes, the Vinkius client is lightweight and fully compatible with the Vercel Edge runtime. You can query `get_task_status` or list models without worrying about node-specific dependencies slowing down your edge middleware.

Instead of keeping an HTTP connection open forever, your agent can kick off a task and then use `list_processing_tasks` to poll the status asynchronously. This keeps your edge functions from timing out while large PDFs are analyzed.

Vinkius handles the Cradl AI credentials for your Vercel AI SDK app behind the scenes. You only need one endpoint token in your environment variables, and the SDK client handles the rest when calling `get_flow_details`.

Absolutely. All document processing runs in an isolated V8 sandbox on Vinkius, meaning your raw PDFs and image files are processed ephemerally and never stored on the MCP host.

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