How to Use the HeyGen MCP in Vercel AI SDK

Q: Can I track HeyGen video generation progress in my UI?

Yes. Your AI agent calls getvideostatus repeatedly. The Vercel AI SDK streams these tool execution updates to your frontend, letting you build a live progress bar.

Q: What happens if a template generation fails?

The generatefromtemplate tool returns an error object. Your Next.js error boundary catches this, allowing you to display a fallback message instead of breaking the page.

Q: How do I list HeyGen templates using the Vercel AI SDK?

Trigger the listtemplates tool through your agent. The SDK streams the JSON array of available templates back to your React components, ready for rendering in a dropdown menu.

Q: Does this MCP Server expose my user's video scripts?

The bodyjson payloads containing your raw video scripts flow through the V8 Isolate Sandbox. Vinkius drops the ephemeral container the moment the Vercel AI SDK closes the connection. No data persists.

Build real-time video generation interfaces into your Next.js apps using the HeyGen MCP Server and 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 HeyGen MCP to Vercel AI SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Stream HeyGen MCP Server template renders to React

Use `generate_from_template` to render personalized videos directly from your Vercel AI SDK frontend. You pass the `variables_json` payload through your edge function, mapping user input straight to the video template. The client streams the generation state back to the UI instantly. Your users never stare at a blank screen. While `get_video_status` polls the API in the background, your React components show live progress. Once the status hits completed, the `video_url` drops right into your video player without a page reload.

Build dynamic avatar selectors

The `list_avatars` tool feeds your frontend with every available digital actor. You pull the `avatar_id` data and render a grid of options for your users. Group them visually by calling `list_avatar_groups` to keep the interface organized. Hook this up to `generate_video` to let users build custom scenes from scratch. They pick the avatar, type the script, and your application sends the `body_json` configuration back through the MCP connection.

Localize content with live feedback

Execute `translate_video` to convert existing media into new languages while maintaining perfect lip-sync. Your Next.js app handles the file selection, passing the `body_json` config to the AI agent. The agent then coordinates the translation job. Check your credit balance before running heavy translation jobs using `get_api_profile`. This prevents failed generations from breaking your user experience. If credits drop too low, your UI prompts the user to upgrade their plan immediately.

Setup guide

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

Install @ai-sdk/mcp and initialize your connection using createMCPClient. Point the transport URL to your Vinkius endpoint. Then call mcpClient.tools() and pass the result to streamText.

Yes. Your AI agent calls get_video_status repeatedly. The Vercel AI SDK streams these tool execution updates to your frontend, letting you build a live progress bar.

The generate_from_template tool returns an error object. Your Next.js error boundary catches this, allowing you to display a fallback message instead of breaking the page.

Trigger the list_templates tool through your agent. The SDK streams the JSON array of available templates back to your React components, ready for rendering in a dropdown menu.

The body_json payloads containing your raw video scripts flow through the V8 Isolate Sandbox. Vinkius drops the ephemeral container the moment the Vercel AI SDK closes the connection. No data persists.

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