How to Use the AssemblyAI MCP in Vercel AI SDK

Q: How do I run AssemblyAI transcription tasks inside Vercel AI SDK edge functions?

You initialize the client using createMCPClient with an HTTP transport pointing to your Vinkius endpoint. Pass the tools directly into streamText to trigger transcribeaudio without running into serverless execution timeouts.

Q: Can I stream live paragraph updates from AssemblyAI to my React frontend using Vercel AI SDK?

Yes, you use gettranscriptparagraphs inside your stream loop. The SDK pipes the structured text blocks directly to your UI components, updating the screen as the transcription completes.

Q: How do I clean up files after processing them with AssemblyAI and Vercel AI SDK?

Call deletetranscript inside your SDK's onFinish callback or a dedicated API route. This ensures the audio data is wiped from the servers immediately after your frontend receives the final payload.

Q: What's the best way to list past AssemblyAI audio jobs in a Vercel AI SDK UI?

Call listtranscripts via the MCP toolset to pull the history of your AssemblyAI runs. You can render this list in a Vercel AI SDK sidebar, allowing users to click any past job to fetch its details via gettranscript.

Pipe AssemblyAI transcription progress and text chunks directly to your Next.js frontend using 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 AssemblyAI MCP to Vercel AI SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Show live transcript chunks in your Vercel AI SDK UI

Your users hate waiting for long AssemblyAI transcription jobs to finish processing. By pairing this MCP Server with `streamText`, you feed raw audio URLs to `transcribe_audio` and pipe the resulting text segments straight to the browser as they resolve. Instead of showing a generic loading spinner, you use `get_transcript_sentences` to update the DOM sentence by sentence. This keeps your Vercel AI SDK interface snappy and gives users instant visual feedback while the AssemblyAI engine processes the rest of the audio.

Clean up processed audio files on the edge

When running Vercel AI SDK functions on the edge, you need to clean up AssemblyAI transcription records fast to protect user privacy. Your Vercel AI SDK code can trigger `delete_transcript` the moment your user confirms they have saved their text. Because the Vercel AI SDK MCP setup integrates directly with your edge routes, you trigger `delete_transcript` asynchronously without blocking the main UI thread. It keeps your AssemblyAI workspace clean and your compliance team happy.

Navigate long files with paragraph-level queries

Feeding a massive two-hour AssemblyAI transcription into a Vercel AI SDK model context window wastes tokens. Use `get_transcript_paragraphs` to let your Vercel AI SDK application pull structured blocks of text rather than the whole raw file. Your Vercel AI SDK frontend can then render a clean, jumpable table of contents where users click a block to read specific AssemblyAI paragraphs. It makes navigating dense AssemblyAI audio files feel like reading a well-formatted blog post.

Setup guide

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

You initialize the client using `createMCPClient` with an HTTP transport pointing to your Vinkius endpoint. Pass the tools directly into `streamText` to trigger `transcribe_audio` without running into serverless execution timeouts.

Yes, you use `get_transcript_paragraphs` inside your stream loop. The SDK pipes the structured text blocks directly to your UI components, updating the screen as the transcription completes.

Call `delete_transcript` inside your SDK's onFinish callback or a dedicated API route. This ensures the audio data is wiped from the servers immediately after your frontend receives the final payload.

Call `list_transcripts` via the MCP toolset to pull the history of your AssemblyAI runs. You can render this list in a Vercel AI SDK sidebar, allowing users to click any past job to fetch its details via `get_transcript`.

Your AssemblyAI audio payloads and generated transcriptions never touch persistent storage on Vinkius. The V8 sandbox processes Vercel AI SDK requests to AssemblyAI securely, and then immediately destroys the execution context once the HTTP request 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