How to Use the Gumroad MCP in Vercel AI SDK

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

Install @ai-sdk/mcp and set up createMCPClient with your HTTP endpoint. Pass the tools directly to generateText or streamText to let your agent call them. Remember to call close() on the client when your Edge Function finishes executing.

Q: Can I stream active Gumroad customer lists in Vercel AI SDK?

Yes. When your agent calls listsubscribers, the SDK streams the subscription states straight to your React UI. The customer details render component-by-component as the data arrives from the API.

Q: How do Gumroad refunds work inside Vercel AI SDK?

Your support agent can invoke refundsale directly from the chat UI. The SDK streams the refund confirmation status live, updating your database and the customer's view simultaneously.

Stream Gumroad sales data and license checks directly into your Next.js UI using Vercel AI SDK and this MCP Server.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Gumroad MCP to Vercel AI SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Stream license checks live with Vercel AI SDK

Your frontend calls `verify_license` to inspect a customer's purchase key while streaming the validation state directly to the user interface. This eliminates the awkward loading spinners that kill your conversion rates. By passing the MCP Server tools array directly into `streamText`, your React or Next.js application renders the active license metadata the millisecond the API responds. You keep your Edge Functions fast and your user experience clean.

Direct customer lookup in your chat interface

Your support dashboard calls `list_payers` and `get_sale` to pull up transaction histories inside a conversational UI. Users don't have to wait for a full page reload or click through multiple tabs to see who bought what. The SDK handles the real-time data binding so your agent can fetch customer profiles on the fly. It renders the customer's purchase history right inside the chat window while the conversation is still happening.

Real-time product inventory displays

The application executes `list_products` to fetch your current digital catalog and display it inside the streaming text window. This lets your backend fetch actual prices and availability without stale cache issues. Using this MCP Server, your LLM UI builds custom checkout links dynamically based on real-time inventory. Your customers see the correct product info instantly because the data streams straight from the source.

Setup guide

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

Install `@ai-sdk/mcp` and set up `createMCPClient` with your HTTP endpoint. Pass the tools directly to `generateText` or `streamText` to let your agent call them. Remember to call `close()` on the client when your Edge Function finishes executing.

Yes. When your agent calls `list_subscribers`, the SDK streams the subscription states straight to your React UI. The customer details render component-by-component as the data arrives from the API.

Your support agent can invoke `refund_sale` directly from the chat UI. The SDK streams the refund confirmation status live, updating your database and the customer's view simultaneously.

Yes, the server connection runs over lightweight transport layers compatible with Vercel's Edge runtime. You can run license verifications globally with minimal latency.

The MCP endpoint handles your API tokens in an isolated V8 sandbox, meaning Vercel AI SDK never exposes your secret keys to the browser. Your sales history, payouts, and customer email logs stay completely private and encrypted during transit.

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