How to Use the 3Scribe MCP in Vercel AI SDK

Q: How do I initialize 3Scribe with the Vercel AI SDK?

Install the @ai-sdk/mcp package first. Then, instantiate the client with createMCPClient using your Vinkius HTTP URL and feed the tools into streamText.

Q: Does 3Scribe support token-based authentication in Vercel AI SDK?

Yes. You can pass your credentials through the authProvider configuration when creating the connection. This keeps your transcription API keys safe on Vercel's edge network.

Q: Can I poll getjob status using Vercel AI SDK and 3Scribe?

Yes, you can run a loop inside streamText that calls getjob until the status returns completed. The client then streams the final transcript text directly into your React component.

Q: How do I clean up connections after running a 3Scribe job?

Always call mcpClient.close() when your edge function finishes processing. This prevents dangling SSE connections and keeps your Vercel execution times low.

Feed live 3Scribe transcription states directly into your Next.js frontend with 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 3Scribe MCP to Vercel AI SDK

Create your Vinkius account to connect 3Scribe 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 3Scribe with Vercel AI SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Stream 3Scribe jobs in Vercel AI SDK

Your users hate loading spinners. With this MCP Server, your React or Next.js app initiates transcription via `create_job` and streams status updates directly to the browser. By calling `get_job` inside `streamText`, the interface updates the moment the transcript is ready. You don't have to write polling logic or manage complex WebSockets manually.

Real-time UI updates for transcription lists

Populating a dashboard with active tasks usually requires custom API endpoints. Pass `list_jobs` directly to your Vercel AI SDK client to render the entire run history in a single render cycle. The UI displays the status of each audio file as the LLM processes the array. This keeps your edge functions fast and your frontend responsive.

Securely delete media data from the edge

Privacy matters when handling raw audio. Trigger `delete_job` directly from user-facing buttons in your Svelte or Vue application without spinning up a dedicated backend. The Vercel AI SDK securely passes the request through the Vinkius MCP gateway, ensuring the media and its text are wiped from the server instantly.

Setup guide

Set up 3Scribe 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 3Scribe 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 3Scribe 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 3Scribe. 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 3Scribe 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 3Scribe MCP in Vercel AI SDK

Install the `@ai-sdk/mcp` package first. Then, instantiate the client with `createMCPClient` using your Vinkius HTTP URL and feed the tools into `streamText`.

Yes. You can pass your credentials through the `authProvider` configuration when creating the connection. This keeps your transcription API keys safe on Vercel's edge network.

Yes, you can run a loop inside `streamText` that calls `get_job` until the status returns completed. The client then streams the final transcript text directly into your React component.

Always call `mcpClient.close()` when your edge function finishes processing. This prevents dangling SSE connections and keeps your Vercel execution times low.

Vinkius runs the server in an ephemeral sandbox. Your media URLs and raw text transcripts are processed securely, and you can trigger `delete_job` to wipe them permanently from the storage layer.

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