How to Use the Applitools MCP in Vercel AI SDK

Q: Can Vercel AI SDK stream Applitools batch stats to a Next.js app?

Yes. Call getbatchstats through your agent and use streamText to push the counts straight to your React components.

Q: What happens if an Applitools test fails in my Vercel AI SDK app?

Your agent spots the failure via listbatches and can immediately trigger getsession. The user sees the exact unresolved visual diffs appear live on their screen.

Q: How do I validate my API key before querying visual tests?

Run the validatekey tool on startup. This catches bad credentials before your users try to load their test dashboards.

Pipe live Applitools visual testing data directly into your React or Next.js frontends with the 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 Applitools MCP to Vercel AI SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Stream Applitools batches with Vercel AI SDK

You want your users to see visual test results without staring at a loading spinner. Hooking up this MCP Server lets you fetch that data live. Call `list_batches` to grab the latest test runs from Eyes. Pass those IDs right into `get_batch_stats`. Your agent streams the passed, failed, and unresolved counts straight into your Svelte or Vue UI components as they arrive.

Inspect test sessions live

High-level stats rarely cut it when a build turns red. Your custom dashboard needs the exact failure points. You can pull the full breakdown by passing the batch and session IDs to `get_session`. Combine that with `list_results` to show the exact visual diffs. The agent fetches the raw test data in the background and pipes it to the client side without blocking the main thread.

Manage baselines directly from the UI

Sometimes a button moves on purpose. You need a way to approve those new visual states without forcing users to log into another dashboard. Fetch the current environments using `list_baselines`. If a design changed intentionally, your agent can fire off `delete_baseline` to clear the old reference. It happens right from your custom frontend.

Setup guide

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

Pass your endpoint token to the HTTP transport config inside createMCPClient. The connection handles the rest automatically.

Yes. Call get_batch_stats through your agent and use streamText to push the counts straight to your React components.

Your agent spots the failure via list_batches and can immediately trigger get_session. The user sees the exact unresolved visual diffs appear live on their screen.

Run the validate_key tool on startup. This catches bad credentials before your users try to load their test dashboards.

Applitools test baselines and batch IDs remain entirely within your isolated V8 sandbox. The MCP Server guarantees ephemeral execution, so your visual state data disappears the moment the session closes.

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