How to Use the BannerBite MCP in Vercel AI SDK

Q: How do I install BannerBite with the Vercel AI SDK?

Run npm install @ai-sdk/mcp to get started with the MCP client. Then, instantiate the client with the Vinkius HTTP endpoint and pass mcpClient.tools() directly into your streamText function.

Q: Does BannerBite support user authentication inside Vercel AI SDK?

Configure your authentication using the SDK's authProvider during client initialization. This keeps your API keys secure while letting users trigger image generation from their own accounts.

Q: What happens if a media render fails?

Your agent catches the error returned by getrender and can automatically retry with adjusted parameters. The SDK handles the error state gracefully without crashing the user's chat session.

Get raw marketing videos and social images rendered right inside your Vercel AI SDK stream, zero loading spinners required.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect BannerBite MCP to Vercel AI SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Render Videos Live with Vercel AI SDK

This BannerBite MCP Server integration lets your app trigger `generate_video` and watch the rendering status update in real-time. Don't make your users stare at a blank loading screen while the backend chugs along. You pull project details using `get_project` and list available scenes with `list_bites` to populate your frontend options. The Vercel AI SDK handles the data stream, meaning users see their custom media compile frame-by-frame on their screens.

Instant Image Generation in Chat

Your user requests a banner, and `generate_image` fires off behind the scenes to build it from your active templates. The resulting URL streams straight into the chat window, skipping the usual API polling delay. By calling `list_projects` first, your client knows exactly which design templates are ready to use. Users modify text fields in real-time, and the SDK reflects those changes in the generated image immediately.

Monitor Render Queues on the Edge

Running on Vercel Edge Functions requires fast, lightweight calls, which is why `get_render` tracks compilation progress with minimal overhead. Your UI stays responsive because the server handles the heavy lifting of media processing elsewhere. You query `list_renders` to show users their history of generated assets directly in their dashboard. Because the MCP connection is handled cleanly, edge execution limits won't cut off your image generation mid-process.

Setup guide

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

Run `npm install @ai-sdk/mcp` to get started with the MCP client. Then, instantiate the client with the Vinkius HTTP endpoint and pass `mcpClient.tools()` directly into your `streamText` function.

Yes, the BannerBite MCP Server exposes tools to stream rendering progress. You combine `generate_video` with `get_render` in a streaming loop to display live status updates as Vinkius processes the media.

Configure your authentication using the SDK's `authProvider` during client initialization. This keeps your API keys secure while letting users trigger image generation from their own accounts.

Your agent catches the error returned by `get_render` and can automatically retry with adjusted parameters. The SDK handles the error state gracefully without crashing the user's chat session.

Vinkius runs the server in an isolated sandbox, keeping your API keys and project templates hidden from the frontend. Your video templates and generated image assets are processed through secure, ephemeral sessions that discard sensitive data immediately after the render completes.

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