How to Use the Amplience MCP in Vercel AI SDK

Q: Can the Vercel AI SDK agent list all my Amplience folders?

Yes. The client can call listfolders to map out how content is organized in any given repository.

Q: Does the Vercel AI SDK support publishing Amplience content?

Your agent can publish content by executing the publishcontentitem tool, pushing drafts directly to the delivery CDN.

Build dynamic ecommerce frontends by connecting the Amplience MCP Server directly to your Vercel AI SDK streaming agents.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Amplience MCP to Vercel AI SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Fetch data through the MCP Server

Building a React application requires live product descriptions, preferably without loading spinners. Hooking this integration into your generative UI setup means users watch text populate in real time. The agent grabs the active workspace using `list_hubs` and finds the correct storage bucket via `list_repositories`. Instead of writing custom fetch logic, your Vercel AI SDK client pulls exactly what it needs. It calls `get_content_item` to grab the specific configuration and schema revision lock, streaming that raw data straight into your Next.js frontend components.

Edit CMS records from chat UI

Giving marketers a chat window to update site copy changes how teams work. When a user asks to rewrite a landing page, the agent drafts the text and immediately pushes it. It executes `update_content_item` to modify the existing data structure while strictly matching the current schema. New campaigns require fresh entries. If the folder structure is already set up, the AI client fires `create_content_item` to drop a brand new structured record right where it belongs. You get a conversational interface for a complex headless CMS.

Push approved changes to the edge

Drafts sitting in a database do not drive revenue. Once your end user approves the AI-generated copy in the UI, the agent can push it live immediately. It triggers `publish_content_item` to send that specific version straight to the live delivery CDN. Knowing what is actually live right now matters just as much. By running `get_delivery_content`, the agent retrieves the exact structural match from the delivery CDN blocks. This ensures the frontend always reflects the published state, avoiding cache mismatches.

Setup guide

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

Install both the core AI package and the MCP package. Then use createMCPClient with your Vinkius endpoint URL and pass the resulting tools into generateText or streamText.

Yes. The client can call `list_folders` to map out how content is organized in any given repository.

The server supports standard HTTP transport. You configure this directly in your transport settings when initializing the client.

Your agent can publish content by executing the `publish_content_item` tool, pushing drafts directly to the delivery CDN.

Your ecommerce product descriptions and schema revision locks never train external models. Vinkius runs the server in an ephemeral V8 Isolate Sandbox. The connection drops immediately after the CDN blocks are retrieved, leaving zero persistent footprint.

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