How to Use the Cleveland Museum of Art MCP in Vercel AI SDK

Q: Can I stream exhibition data from the Cleveland Museum of Art directly into my Next.js app with the Vercel AI SDK?

Yes. The searchexhibitions tool is designed for this. Your agent can query for exhibitions by name or date, and the Vercel AI SDK will stream the results directly to your Next.js frontend, perfect for displaying in real-time.

Q: What's the best way to handle image similarity searches for the Cleveland Museum of Art using the Vercel AI SDK?

Use the searchsimilarartworks tool. Your agent provides an artwork ID, and the tool returns related works. The AI SDK's streaming response lets you build a dynamic UI where similar images appear as they're found, rather than all at once after a delay.

Q: Does this MCP server support finding artists from the 'May Shows'?

It does. The searchmayshowcreators tool is specifically for querying artists who participated in the Cleveland Museum of Art's historical May Shows. You can search by name or year.

Stream Cleveland Museum of Art data directly into your React and Next.js apps with the Vercel AI SDK.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Cleveland Museum of Art MCP to Vercel AI SDK

Create your Vinkius account to connect Cleveland Museum of Art 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 Cleveland Museum of Art with Vercel AI SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Build a Live Art Explorer

The `search_artworks` tool lets your users query the entire museum collection. With the Vercel AI SDK, results don't wait for a spinner. They stream directly into your UI components, creating a live, interactive search experience. Users see artworks appearing as the agent finds them. You can also find creators with `search_creators` or past events with `search_exhibitions`. It's all about building a front-end that feels fast and responsive because the data arrives in real-time, not in one big chunk. Your agent does the work, and the results render instantly.

Visual Search That Renders Instantly

This MCP Server's `search_similar_artworks` tool finds art based on visual similarity. Instead of just getting a list of IDs, you can use the AI SDK to build a component that shows similar images appearing one by one. It’s a great way to create a 'discover more like this' feature that feels dynamic. Your agent passes an artwork ID, the tool returns visually related pieces, and your React components update on the fly. This turns a simple API call into a compelling user experience, all handled by the AI SDK's streaming capabilities.

Get Artwork Details on Demand

Let users click on any piece of art to get its full story. The `get_artwork` tool fetches detailed metadata for a specific piece using its ID or accession number. Your agent can call this tool and stream the response right into a modal or detail view. Combine this with `get_creator` to also pull in the artist's biography. Because the Vercel AI SDK streams the data, your UI can show the title and image first, then populate the description and artist info as they arrive. No more blank loading states.

Setup guide

Set up Cleveland Museum of Art 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 Cleveland Museum of Art 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 Cleveland Museum of Art 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 Cleveland Museum of Art. 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 Cleveland Museum of Art 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 Cleveland Museum of Art MCP in Vercel AI SDK

Connect the Vercel AI SDK to this MCP server's endpoint. Then, in your UI code, pass the `search_artworks` tool to the `streamText` or `generateText` function. The results will stream in, ready for you to render into your React or Svelte components.

Yes. The `search_exhibitions` tool is designed for this. Your agent can query for exhibitions by name or date, and the Vercel AI SDK will stream the results directly to your Next.js frontend, perfect for displaying in real-time.

Use the `search_similar_artworks` tool. Your agent provides an artwork ID, and the tool returns related works. The AI SDK's streaming response lets you build a dynamic UI where similar images appear as they're found, rather than all at once after a delay.

It does. The `search_may_show_creators` tool is specifically for querying artists who participated in the Cleveland Museum of Art's historical May Shows. You can search by name or year.

Your search queries and artwork IDs are the only data sent. The connection is secured over HTTPS, and Vinkius runs each MCP Server in an isolated, ephemeral environment. Your app's requests are private and not logged.

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