How to Use the HeyGen MCP in Vercel AI SDK

Q: How do I stream HeyGen video generation progress in Vercel AI SDK?

Call getvideoprogress inside your streamText tool call. The Vercel AI SDK streams the status updates directly to your React components, letting you build real-time progress bars.

Q: Can I let users select HeyGen avatars directly from a Vercel AI SDK dropdown?

Yes. Use listavailableavatars to fetch the active list of digital actors. The SDK feeds this array directly into your UI state so users can click and choose their preferred speaker.

Q: Can my edge functions generate videos using templates?

Yes, you run createfromtemplate within your edge-runtime route. It bypasses cold starts, matches your template ID with the user inputs, and triggers the render instantly.

Build live web interfaces where users watch Vercel AI SDK stream HeyGen video creation steps directly to their screen.

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

Live Avatar Discovery in Next.js Frontends

The `list_available_avatars` tool lets your Vercel AI SDK client query HeyGen's actor library and render choices in your UI immediately. Users see real-time avatar previews populate their screen as the agent fetches the raw metadata. You don't have to write custom API wrappers to parse the payload. The Vercel AI SDK hooks this MCP Server directly into your UI components, feeding voice options through `list_available_voices` to let users customize their digital spokesperson on the fly.

Stream Progress Bars with Vercel AI SDK

The `get_video_progress` tool feeds current rendering states straight to your Vercel AI SDK streaming text or UI components. Instead of a generic loading spinner, your users watch the actual percentage tick up as HeyGen cooks the final MP4. This MCP Server integration handles the polling lifecycle behind the scenes. Your frontend gets clean updates from `generate_ai_video` and displays the status instantly, keeping users glued to the page while the video builds.

Direct Prompt-to-Video Generation on the Edge

The `generate_from_prompt` tool lets edge-rendered Vercel AI SDK applications trigger complete video generation from a single user input. You bypass heavy backend servers entirely by letting the client negotiate directly with the MCP Server. Feeding user assets into the mix with `upload_media_asset` lets you personalize the output instantly. The SDK manages the connection, handles the payload, and outputs a ready-to-play video link without blocking the main browser thread.

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

Call `get_video_progress` inside your streamText tool call. The Vercel AI SDK streams the status updates directly to your React components, letting you build real-time progress bars.

Yes. Use `list_available_avatars` to fetch the active list of digital actors. The SDK feeds this array directly into your UI state so users can click and choose their preferred speaker.

Vinkius manages the API key securely inside its sandbox. Your Vercel AI SDK client only needs to call `test_heygen_auth` to confirm the secure MCP connection is live before running video jobs.

Yes, you run `create_from_template` within your edge-runtime route. It bypasses cold starts, matches your template ID with the user inputs, and triggers the render instantly.

Your uploaded media files, voice scripts, and final MP4 videos remain inside HeyGen's secure processing pipeline. The Vinkius MCP Server operates an ephemeral sandbox that never caches or stores your voice assets or video records after transmission.

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