How to Use the Artsy MCP in Vercel AI SDK

Q: How do I handle authentication for Artsy inside a Vercel AI SDK project?

You pass your Vinkius endpoint token to the createMCPClient transport configuration. The platform manages the underlying API keys, so your Next.js application only needs to handle one secure token.

Q: What happens if an art show query returns no results?

Your agent receives an empty list from the listshows tool. The model can then automatically fallback to calling searchartsy to find related galleries or historical exhibitions instead.

Stream real-time art database queries directly into your React components with the Vercel AI SDK and the Artsy 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 Artsy MCP to Vercel AI SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Stream Artsy Data Live to Vercel AI SDK Frontends

The `search_artsy` tool lets your agent query the global art database and stream the results instantly to your user interface. You bypass loading spinners by feeding raw data chunks directly into your Next.js or React components. This setup uses `streamText` to keep the UI responsive. When the agent pulls artist bios or show dates, the client renders them on the fly, keeping users engaged while the model processes the rest of the payload.

Build Interactive Art Galleries

The `list_artworks` tool fetches high-resolution art metadata, which your agent can format into interactive UI cards. By combining this with `get_artwork_details`, your application lets users click an image and immediately stream deep historical context right next to the visual. You initialize this with the MCP client in an Edge Function. The edge environment keeps latency low, ensuring that when a user asks about a specific painting, the metadata loads in milliseconds.

Live Art Fair and Show Trackers

The `list_shows` tool retrieves active gallery exhibitions, while `list_fairs` pulls global art fair schedules. Your AI client parses these endpoints to generate real-time local art guides for your users. To prevent memory leaks, you call `mcpClient.close()` after the stream finishes. This keeps your serverless execution clean and prevents API usage from spiking during high-traffic events.

Setup guide

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

You pass your Vinkius endpoint token to the `createMCPClient` transport configuration. The platform manages the underlying API keys, so your Next.js application only needs to handle one secure token.

Yes. Because the Artsy MCP server runs in a V8 isolate, it is fully compatible with Edge runtimes. You just import `@ai-sdk/mcp`, initialize the client, and call your tools within your edge route.

The SDK handles concurrent execution out of the box. If your agent decides to call `get_artist_details` and `get_artwork_details` at the same time, the MCP client executes them in parallel and streams both payloads back to your frontend.

Your agent receives an empty list from the `list_shows` tool. The model can then automatically fallback to calling `search_artsy` to find related galleries or historical exhibitions instead.

Vinkius processes all your requests in ephemeral V8 sandboxes. Your search queries and artist metadata requests are never written to persistent disks or stored after the execution window closes.

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