How to Use the Art Institute of Chicago MCP in OpenAI Agents SDK

Q: How do I connect the Art Institute of Chicago MCP Server to OpenAI Agents SDK?

Install openai-agents via pip. Create an MCPServerStreamableHttp instance pointing to your Vinkius endpoint. Pass that into your agent constructor to auto-discover the 31 available tools.

Q: Can OpenAI Agents SDK search the Art Institute of Chicago collection by artist?

Yes, the searchagents tool handles creator queries. Your agent can then pipe those artist IDs into searchartworks to find their specific pieces.

Q: Does the Art Institute of Chicago integration support image retrieval in OpenAI Agents SDK?

You pull the IIIF manifest using the getartworkmanifest tool. That returns the structured image metadata required to fetch high-resolution files.

Connect the Art Institute of Chicago MCP Server to OpenAI Agents SDK to build production applications with built-in guardrails.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Art Institute of Chicago MCP to OpenAI Agents SDK

Create your Vinkius account to connect Art Institute of Chicago to OpenAI Agents 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 Art Institute of Chicago with OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Fetch artwork details with OpenAI Agents SDK

The `get_artwork` tool grabs the exact dimensions, medium, and provenance for any piece in the collection. You pass an ID, and the agent pulls structured data directly from the museum database. Tracing matters when dealing with high-res assets. Your system can call `get_artwork_manifest` to pull the IIIF manifest, validating the response before passing it to a specialized image-processing agent. Handoffs happen automatically under your defined constraints.

Map artist histories and museum events

The `search_agents` tool scans the database for specific creators, while `list_exhibitions` pulls their show history. Building an accurate timeline requires exact dates and physical locations. You configure your OpenAI agent to cross-reference those results using `get_gallery` and `get_event`. Guardrails ensure the agent only returns verified museum data instead of hallucinating exhibition details.

Query shop items and scholarly articles

Running `search_publications` lets your agent find academic papers published by the institution. It pairs naturally with `search_products` to find related exhibition catalogs in the museum store. Connecting this MCP Server gives your deployment direct access to retail and research data. The SDK logs every API request in your OpenAI dashboard so you can audit exactly what the agent queried.

Setup guide

Set up Art Institute of Chicago MCP in OpenAI Agents SDK

Prerequisites

Python 3.10+ installed
openai-agents package (pip install openai-agents)
Active Vinkius subscription with a valid endpoint token

1

Install the SDK

Run pip install openai-agents to install the OpenAI Agents SDK. The MCP integration is built-in — no extra dependencies needed.
2

Connect via SSE transport

Use MCPServerSse with your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. The SDK auto-discovers all Art Institute of Chicago tools at runtime.
3

Create your Agent

Pass the MCP to Agent(mcp_servers=[server]). The agent receives Art Institute of Chicago tools as native definitions — JSON schemas resolve automatically.
4

Run the agent

Call Runner.run(agent, prompt) to execute. The agent invokes the appropriate Art Institute of Chicago tools and returns structured results. Copy the full example on the right to get started.

agent.py

import asyncio
from agents import Agent, Runner
from agents.mcp import MCPServerSse

async def main():
    async with MCPServerSse(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ) as server:
        agent = Agent(
            name="Art Institute of Chicago Agent",
            instructions="You have access to Art Institute of Chicago tools.",
            mcp_servers=[server],
        )
        result = await Runner.run(agent, "List recent transactions")
        print(result.final_output)

asyncio.run(main())

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 Art Institute of Chicago. 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 Art Institute of Chicago 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 Art Institute of Chicago MCP in OpenAI Agents SDK

Install `openai-agents` via pip. Create an `MCPServerStreamableHttp` instance pointing to your Vinkius endpoint. Pass that into your agent constructor to auto-discover the 31 available tools.

Yes, the `search_agents` tool handles creator queries. Your agent can then pipe those artist IDs into `search_artworks` to find their specific pieces.

You pull the IIIF manifest using the `get_artwork_manifest` tool. That returns the structured image metadata required to fetch high-resolution files.

Response times depend on the Vinkius endpoint and the museum API. Set `cacheToolsList=True` in your SDK configuration to skip tool discovery on subsequent runs and cut latency.

Vinkius runs the connection inside a V8 Isolate Sandbox that destroys itself after the request. The exact artwork IDs and search strings you pass to the museum API are never logged or stored by the infrastructure.

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