How to Use the Castmagic MCP in Vercel AI SDK

Q: How do I connect the Castmagic MCP Server to the Vercel AI SDK?

Install @ai-sdk/mcp and use createMCPClient. Point the HTTP transport URL to your Vinkius endpoint, then pass the resulting tools into streamText to start generating UI components.

Q: Can the Vercel AI SDK stream Castmagic social posts directly to my Next.js app?

Yes, the SDK pipes the output of getmagiccontent straight to the browser. Your users see the LinkedIn posts and Twitter threads rendering live instead of waiting for a completed response.

Q: Do I need to keep the connection open in Vercel Edge Functions?

No, you should always call mcpClient.close() when the tool execution finishes. Edge functions run ephemerally, so closing the connection prevents memory leaks and hanging requests.

Q: How does the Vercel AI SDK handle Castmagic audio uploads?

You pass an audio or video URL to createnewtranscript through your agent. The MCP Server pulls the media from that URL, processes it, and the SDK streams the status back to your frontend.

Build React apps that stream Castmagic transcripts and show notes straight to the browser 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 Castmagic MCP to Vercel AI SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Stream Transcripts via MCP Server

Converting audio to text usually forces users to stare at a blank screen. By connecting this MCP Server, your frontend components can trigger `create_new_transcript` and immediately pipe the resulting text back to the client. The Vercel AI SDK handles the HTTP transport layer while the user watches the text appear word by word. You never have to poll an API to see if the file finished processing. Calling `get_transcript_details` through `streamText` pushes the raw text directly into your React state. It feels instant because the data flows as a continuous stream rather than a delayed bulk payload.

Render Show Notes Live

Nobody wants to wait for a massive JSON object to resolve before reading their podcast summary. Your agent grabs the generated social posts and bullet points using `get_magic_content` and renders them into your UI components instantly. You build the frontend, and the model handles formatting the output for Twitter or LinkedIn. Getting the right data requires knowing who said what. Firing `list_transcript_speakers` lets your Svelte or Vue interface populate speaker tags dynamically while the rest of the content is still generating. The user gets a responsive dashboard that reacts to the audio file in real time.

Manage Audio Quotas on the Edge

Running out of minutes mid-generation breaks the user experience. You can check remaining transcription time by executing `get_castmagic_account` right from your Edge Functions. This lets your application catch quota limits before the user tries to upload a two-hour video. Cleaning up old files happens just as fast. When a user removes a project from your app, calling `delete_transcript` wipes the source file and generated text from the backend. You close the `mcpClient` connection, and the storage stays clean without writing custom cleanup routines.

Setup guide

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

Install `@ai-sdk/mcp` and use `createMCPClient`. Point the HTTP transport URL to your Vinkius endpoint, then pass the resulting tools into `streamText` to start generating UI components.

Yes, the SDK pipes the output of `get_magic_content` straight to the browser. Your users see the LinkedIn posts and Twitter threads rendering live instead of waiting for a completed response.

No, you should always call `mcpClient.close()` when the tool execution finishes. Edge functions run ephemerally, so closing the connection prevents memory leaks and hanging requests.

You pass an audio or video URL to `create_new_transcript` through your agent. The MCP Server pulls the media from that URL, processes it, and the SDK streams the status back to your frontend.

The Vinkius zero-trust sandbox only handles the transit of your media URLs and raw transcript text. It never stores your audio files, generated show notes, or speaker data on disk. Everything runs ephemerally and disappears the moment the connection drops.

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