How to Use the BugBug MCP in Vercel AI SDK

Q: How do I stream BugBug test results using the Vercel AI SDK?

You connect the MCP Server using createMCPClient and pass the tools to streamText. When the agent calls runtest, the SDK streams the execution status ticks directly to your frontend UI.

Q: Can I trigger a BugBug suite run inside a Next.js Edge Function?

Yes. Because this MCP client is lightweight, you can call runsuite from any Edge Function. It avoids heavy dependencies, keeping your cold starts under 50ms.

Q: How does Vercel AI SDK handle BugBug IP whitelisting?

Your agent calls getips to grab the current BugBug runner IP addresses. You can then dynamically feed these IPs into your Vercel firewall rules to let the browser tests bypass security.

Q: What is the fastest way to list all active BugBug projects in my app?

Use the listprojects tool within your MCP tool call block. The SDK fetches the project list from the server and instantly renders it in your React layout.

Run BugBug browser tests and stream real-time execution states directly into your Next.js UI 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 BugBug MCP to Vercel AI SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Stream BugBug live test runs directly to your Vercel AI SDK UI

Stop making your users stare at static loading spinners while waiting for browser tests to finish. When you trigger `run_test` through this MCP Server, your Vercel AI SDK frontend streams the raw execution status updates in real-time. You can display the exact test steps as they execute without polling your backend. The agent uses `get_test_run` to fetch live execution ticks, instantly piping the JSON payload straight to your React or Next.js components. Because this client supports direct UI streaming, your developers can build custom QA dashboards where testing progress bars update frame-by-frame.

Read BugBug suites and project lists over edge runtimes

Pulling test configurations shouldn't slow down your edge functions. This MCP Server exposes `list_projects` and `list_suites` so your Vercel AI SDK application can query your entire QA setup in milliseconds. It runs on a lightweight V8 sandbox that fits perfectly within Vercel's tight edge execution limits. Your AI client parses these structures instantly to help developers debug broken paths. If a deploy fails, the agent calls `get_suite` to inspect the exact assertions, letting you display the failing selectors directly inside your deployment logs.

Trigger `run_suite` dynamically during Vercel AI SDK builds

Let your deployment pipeline trigger end-to-end tests the moment a preview branch goes live. By exposing `run_suite` to your AI agent, you can verify critical checkout flows before routing real traffic. The agent watches the run using `list_suite_runs` to make sure everything passes. If a test fails, the SDK handles the error stream gracefully, outputting the exact step failure. This lets you build smart Slack bots or internal tools that don't just say "build failed," but actually point out which browser assertion tripped.

Setup guide

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

You connect the MCP Server using `createMCPClient` and pass the tools to `streamText`. When the agent calls `run_test`, the SDK streams the execution status ticks directly to your frontend UI.

Yes. Because this MCP client is lightweight, you can call `run_suite` from any Edge Function. It avoids heavy dependencies, keeping your cold starts under 50ms.

Your agent calls `get_ips` to grab the current BugBug runner IP addresses. You can then dynamically feed these IPs into your Vercel firewall rules to let the browser tests bypass security.

Use the `list_projects` tool within your MCP tool call block. The SDK fetches the project list from the server and instantly renders it in your React layout.

Yes, your API keys never expose themselves to the browser. The Vinkius sandbox handles the credentials securely on the server side, so your client only receives the raw JSON output from `get_test_run` or `list_test_runs`.

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