How to Use the Mabl (AI-Powered Test Automation) MCP in Vercel AI SDK

Q: How do I connect the Mabl (AI-Powered Test Automation) MCP Server to the Vercel AI SDK?

Install @ai-sdk/mcp and use createMCPClient. Pass your HTTP transport URL, then call mcpClient.tools() to inject the Mabl tools into generateText or streamText.

Q: Can the Vercel AI SDK stream Mabl (AI-Powered Test Automation) failure analysis to my Next.js app?

Yes. When you invoke mb.getexecution, the AI client streams the failure reasons and test outcomes directly to your frontend components. You skip the intermediate API layer completely.

Q: What is the best way to handle Mabl (AI-Powered Test Automation) triggers with the Vercel AI SDK?

Map a user prompt to mb.triggerplan. The SDK will execute the tool call on the edge, fire the deployment event in Mabl, and stream the confirmation text back to the user.

Stream Mabl test execution data and AI failure analysis directly into your React frontends using 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 Mabl (AI-Powered Test Automation) MCP to Vercel AI SDK

Create your Vinkius account to connect Mabl (AI-Powered Test Automation) 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 Mabl (AI-Powered Test Automation) with Vercel AI SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Stream Test Results via Vercel AI SDK

This MCP server exposes Mabl's core testing infrastructure to your Vercel AI SDK applications. When your Next.js dashboard needs to show real-time deployment health, you call `mb.list_executions` and stream the test statuses straight to the client. The user watches the results populate without waiting for a loading spinner. You don't have to build a custom polling backend. The SDK handles the streaming transport while `mb.get_execution` pulls the exact failure analysis and screenshots. Your users see exactly why a build broke before the CI pipeline even finishes timing out.

Trigger Plans from the UI

Using this MCP Server, developers can launch targeted test suites directly from your web application using `mb.trigger_plan`. Instead of jumping into the Mabl console, your AI agent reads the current environment state via `mb.list_envs` and automatically fires off the correct deployment event. The feedback loop stays entirely inside your custom frontend. Once triggered, the agent uses `mb.list_plans` to confirm the run policy and updates the UI state. You ship a self-serve QA dashboard that actually responds to user commands.

Map Application Environments Live

Building a deployment portal means you need accurate targets. The `mb.get_app` tool pulls the exact web URLs and API endpoints configured in Mabl, streaming that metadata straight into your React components. If a user asks the AI client to test the staging environment, it checks `mb.list_apps` to verify the application exists. It then grabs the active tags through `mb.list_labels` and sets up the test run. The entire context flows into your UI instantly.

Setup guide

Set up Mabl (AI-Powered Test Automation) 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 Mabl (AI-Powered Test Automation) 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 Mabl (AI-Powered Test Automation) 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 Mabl. 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 Mabl (AI-Powered Test Automation) 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 Mabl (AI-Powered Test Automation) MCP in Vercel AI SDK

Install `@ai-sdk/mcp` and use `createMCPClient`. Pass your HTTP transport URL, then call `mcpClient.tools()` to inject the Mabl tools into `generateText` or `streamText`.

Yes. When you invoke `mb.get_execution`, the AI client streams the failure reasons and test outcomes directly to your frontend components. You skip the intermediate API layer completely.

Map a user prompt to `mb.trigger_plan`. The SDK will execute the tool call on the edge, fire the deployment event in Mabl, and stream the confirmation text back to the user.

Not if you structure your AI response correctly. You can have the agent query `mb.list_executions` once, return the current state, and prompt the user if they want to check again.

The server reads your test outcomes, failure logs, and application URLs. We isolate this execution in a V8 sandbox that destroys itself after the Vercel AI SDK closes the connection. Nothing persists in memory or on disk.

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