How to Use the Descript MCP in Vercel AI SDK

Q: How do I stream Descript transcription text using Vercel AI SDK?

You call createtranscription through the SDK's tool calling mechanism. Once the job starts, your agent uses gettranscription to fetch the text, which Vercel AI SDK streams directly to your frontend components.

Q: Can Vercel AI SDK trigger Descript video exports?

Yes. The agent uses the createexport tool to kick off the export process. You can then use listexports to monitor the rendering progress and display it to the user.

Pipe live Descript transcriptions and export statuses straight into your Next.js UI using 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 Descript MCP to Vercel AI SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Live transcription rendering in your Vercel AI SDK UI

The `create_transcription` tool lets your agent kick off video transcription jobs directly from your Next.js app. Vercel AI SDK lets you render text word-by-word as the backend finishes processing. This MCP Server handles the Descript API connection, so your frontend code only worries about displaying the incoming stream.

Browse Descript drives and projects on the fly

The `list_projects` tool lets your agent pull your entire Descript workspace library into your frontend. If users need details on a specific video, the agent pulls them instantly using `get_project`. Because this MCP Server integrates directly with the SDK's tool calling, your UI updates dynamically as the agent traverses the workspace.

Trigger and monitor exports in real-time

The `create_export` tool lets your AI client trigger video renders directly from your web interface. By feeding these tool outputs into your streaming UI, users see the progress bar update in real-time. It turns a clunky video editing task into a responsive web experience powered by your custom MCP connection.

Setup guide

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

You call `create_transcription` through the SDK's tool calling mechanism. Once the job starts, your agent uses `get_transcription` to fetch the text, which Vercel AI SDK streams directly to your frontend components.

Yes. The agent uses the `create_export` tool to kick off the export process. You can then use `list_exports` to monitor the rendering progress and display it to the user.

The server manages your API credentials securely behind the scenes. When using Vercel AI SDK, you configure the server endpoint once, and your agent gains secure access to tools like `list_projects` without exposing keys to the client side.

No. The SDK's client handles the MCP transport layer automatically. Your agent calls tools like `list_templates` or `get_project` directly, and the results are injected right into your chat stream.

Absolutely. Your audio files, video files, and transcriptions are processed securely. The server operates in an ephemeral sandbox, meaning your Descript project data and media files are never stored or logged after the tool execution 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