How to Use the Megaphone MCP in Vercel AI SDK

Q: How do I stream Megaphone podcast data using the Vercel AI SDK?

You install the @ai-sdk/mcp package and connect it to the server endpoint using createMCPClient. Pass the tools directly to streamText so your agent can call listpodcasts and display the results live in your UI. Always remember to close the client connection when the execution finishes to prevent memory leaks.

Q: What is the easiest way to search episodes through this MCP setup?

Your agent will automatically choose the searchepisodes tool when a user asks to find a specific audio file. The Vercel AI SDK handles the tool call, fetches the matching episodes, and streams the titles directly to the user's screen.

Feed live Megaphone ad data and podcast feeds directly into your Vercel AI SDK interface without waiting for slow page reloads.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Megaphone MCP to Vercel AI SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Stream podcast structures straight to your Vercel AI SDK UI

Stop making your users stare at spinners while fetching heavy audio catalogs. This MCP Server lets your application pull network layouts and podcast inventories on the fly, feeding the raw data directly into your frontend stream. By combining `list_networks` with `list_podcasts`, your client populates your dashboard layout while the LLM is still generating the summary text. Your interface feels instantaneous because the data arrives in chunks rather than one massive payload. If a user asks for a specific show, the agent triggers `get_podcast` to grab the details and render the view immediately. It keeps your Next.js edge functions fast and your users engaged.

Live ad campaign tracking for ops dashboards

Pulling ad data usually means clicking through slow enterprise portals. Now, your Vercel AI SDK setup can pull active campaigns and orders directly into your custom workspace. The agent uses `list_campaigns` and `list_orders` to surface what is running and what is booked without requiring a manual database sync. This setup gives your ad ops team a conversational interface to audit live inventory. When they ask about a specific campaign's structure, the model calls `list_ad_locations` to show exactly where the mid-rolls are placed inside the episodes.

Instant episode search and metadata inspection

Finding a specific audio file across dozens of feeds is usually a headache. With this MCP Server integration, your agent uses `search_episodes` to scan your entire library in seconds. It bypasses the clunky web interface entirely and surfaces the exact files you need. Once the target is found, the system runs `get_episode` and `list_episodes` to inspect the publishing status. You get clean, structured data injected straight into your React components without writing custom API wrappers.

Setup guide

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

You install the `@ai-sdk/mcp` package and connect it to the server endpoint using `createMCPClient`. Pass the tools directly to `streamText` so your agent can call `list_podcasts` and display the results live in your UI. Always remember to close the client connection when the execution finishes to prevent memory leaks.

Yes, the server is built to run in lightweight environments. Because the Vercel AI SDK supports edge runtimes, you can fetch network details using `get_network_details` with minimal latency. It keeps your serverless execution times low and avoids cold-start delays.

You can inspect the tool calls before they execute by wrapping the tool execution block in your server-side code. This is useful when your agent wants to run `list_orders` to check financial data, allowing you to intercept and log the request first.

Your agent will automatically choose the `search_episodes` tool when a user asks to find a specific audio file. The Vercel AI SDK handles the tool call, fetches the matching episodes, and streams the titles directly to the user's screen.

Your Megaphone API tokens and podcast metadata never leave your secure Vercel environment. This MCP Server runs in an isolated sandbox, meaning sensitive ad order details retrieved via `list_orders` are processed locally and never stored on external third-party servers.

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