How to Use the Elai AI Video MCP in Vercel AI SDK

Q: Can I build a user-facing video editor with Elai AI Video and the Vercel AI SDK?

Yes, absolutely. You can use the tools to fetch listvideotemplates, listavailableavatars, and listavailablevoices to build the editor UI. Then, your app can call createnewaivideo and stream the status back to the user with getvideodetails.

Q: What's the best way to handle rendering status for Elai AI Video in a Vercel AI SDK app?

The most direct way is to periodically call getvideodetails with the video ID. You can wrap this in a React hook that uses useSWR or react-query to poll the API route that calls the MCP tool, and then stream the updated status to your UI components.

Stream Elai-generated videos directly into your React UI with the Vercel AI SDK. No more loading spinners.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Elai AI Video MCP to Vercel AI SDK

Create your Vinkius account to connect Elai AI Video 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 Elai AI Video with Vercel AI SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Generate Video Content in Real-Time

Kick off video creation right from your frontend. When a user submits a script, your app calls `create_new_ai_video`. The Vercel AI SDK streams the initial response, like the new video ID, directly into your UI so the user gets immediate feedback. Then, you can build a component that polls for render status using `get_video_details`. As the status changes from 'pending' to 'rendering' to 'done', the UI updates live. Once it's finished, you can use `list_successfully_rendered_videos` to find the final asset and show a download link. The user sees the whole process happen without a page refresh.

Build Interactive Video Creation UIs

Give your users the tools to build their own videos. Use the Vercel AI SDK to call `list_available_avatars` and `list_available_voices` on page load. The results stream in, populating your dropdowns and selection grids almost instantly. When the user makes their choices and types a script, you bundle it all up and pass it to `create_new_ai_video`. The whole experience feels fast and interactive because it is. This isn't some backend job anymore; it's a creative tool running in the browser, powered by your frontend and this MCP server.

Manage Video Assets from Your Vercel AI SDK App

Build a dashboard where users can see all their projects. A simple call to `list_ai_videos` fetches the list, and with the AI SDK, that list can populate your UI as the data arrives. It feels much faster than waiting for the entire request to finish. From that dashboard, you can add buttons that let users trigger a re-render using `trigger_video_rendering` or get their current account balance with `get_elai_account_metadata`. It puts real video production control right in their hands, all through a simple web interface.

Setup guide

Set up Elai AI Video 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 Elai AI Video 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 Elai AI Video 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 Elai AI Video. 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 Elai AI Video 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 Elai AI Video MCP in Vercel AI SDK

The Vercel AI SDK streams data directly from the MCP server's tools as it becomes available. This means for a tool like `list_available_avatars`, your UI can start rendering the first few avatars while the rest are still being fetched, which makes the application feel much more responsive.

Yes, absolutely. You can use the tools to fetch `list_video_templates`, `list_available_avatars`, and `list_available_voices` to build the editor UI. Then, your app can call `create_new_ai_video` and stream the status back to the user with `get_video_details`.

The most direct way is to periodically call `get_video_details` with the video ID. You can wrap this in a React hook that uses `useSWR` or `react-query` to poll the API route that calls the MCP tool, and then stream the updated status to your UI components.

This server lets you choose from existing assets. You can get a full list of what's available for your account by calling `list_available_avatars` and `list_available_voices`. The tools don't support creating new ones from scratch.

The MCP server processes only the data needed for a tool to run, like video scripts, template IDs, and avatar selections. Vinkius runs each server in an ephemeral, zero-trust sandbox, so your data is only used for the transaction and not stored long-term.

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