How to Use the Akeneo PIM MCP in Vercel AI SDK

Q: How do I fetch Akeneo PIM attributes in Vercel AI SDK?

You invoke the listattributes tool within your tool call configuration. The server returns the full metadata set, which you can then pass to your frontend components for rendering.

Q: Can I update Akeneo PIM records via Vercel AI SDK?

Yes, use the updateproduct tool to push attribute changes. Ensure your API credentials provide write permissions before calling this function in your agent.

Q: Does this MCP server support custom channels?

It lists all configured channels using listchannels. You can filter these results inside your agent code to target specific outputs.

Stream Akeneo PIM product data directly into your Vercel AI SDK interface without waiting for slow loading spinners.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Akeneo PIM MCP to Vercel AI SDK

Create your Vinkius account to connect Akeneo PIM 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 Akeneo PIM with Vercel AI SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Live product data in Vercel AI SDK

Feed your UI real-time inventory details by calling `get_product_details` through your existing Vercel AI SDK stack. You get the raw JSON back instantly, so your React components render product specs the moment the agent finishes its logic. Stop forcing users to stare at blank screens while your backend fetches catalog info. This MCP server pushes the data straight into your streamText calls, ensuring the end user sees content appear as the AI generates the response.

Manage catalog hierarchies in the browser

Use `list_categories` and `list_families` to map out your site structure dynamically. Your agent can traverse the PIM tree, giving your frontend the context needed to build navigation menus on the fly. If you need to check which `list_channels` are active, your agent pulls that config directly into the SDK's tool execution flow. It keeps your interface synced with your PIM settings without manual updates.

Push product updates from the edge

Trigger `update_product` from your edge functions to sync changes back to your PIM immediately. Your agent handles the payload, keeping your database accurate based on user input or automated events. This workflow bypasses the need for complex middleware or custom API wrappers. You interact with the PIM through the same toolset you already use for your agent logic, saving you from writing extra boilerplate.

Setup guide

Set up Akeneo PIM 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 Akeneo PIM 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 Akeneo PIM 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 Akeneo PIM. 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 Akeneo PIM 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 Akeneo PIM MCP in Vercel AI SDK

You invoke the `list_attributes` tool within your tool call configuration. The server returns the full metadata set, which you can then pass to your frontend components for rendering.

Yes, use the `update_product` tool to push attribute changes. Ensure your API credentials provide write permissions before calling this function in your agent.

Not if you use the streaming capabilities correctly. The server responds as soon as the PIM data is ready, letting your SDK render results incrementally.

It lists all configured channels using `list_channels`. You can filter these results inside your agent code to target specific outputs.

Your product data stays within your transport layer and is never logged by the Vinkius infrastructure. We use ephemeral, single-token authentication to ensure your catalog remains private.

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