How to Use the Harvard Art Museums MCP in OpenAI Agents SDK

Build production-grade OpenAI Agents SDK systems that query, audit, and analyze the Harvard Art Museums database 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 Harvard Art Museums MCP to OpenAI Agents SDK

Create your Vinkius account to connect Harvard Art Museums 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 Harvard Art Museums with OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Run secure collection audits with OpenAI Agents SDK

The `search_museum_objects` tool exposes raw catalog records from the Harvard Art Museums directly to your agent. Let's look at the actual data. You get direct access to accession numbers, classification fields, and medium descriptions — and yes, metadata matters — without dealing with manual web scrapers. Your production agent uses these schemas to run automated provenance audits. OpenAI guardrails intercept the payload before execution, meaning your client won't query malformed IDs or trigger API rate limits during deep archival runs. This MCP Server integration keeps your pipelines running smoothly.

Track historical exhibitions across galleries

The `search_exhibitions` tool pulls past and present show data to map how physical space correlates with curation decisions. Look: it's not rocket science. You query the exhibition histories, then feed the physical layout from `list_museum_galleries` straight into your agent's context. This MCP Server integration lets your agent coordinate handoffs between a spatial analysis agent and a historical archiving agent. One agent maps the room coordinates while the other traces the artists, keeping your production pipeline clean and focused.

Map artist networks using structured agent tools

The `search_museum_people` tool lets your agent find biographical details, roles, and birth-death dates for every cataloged creator. Truth be told, museum records are messy, but this endpoint normalizes the JSON so your agent doesn't choke on inconsistent artist names. Once your agent identifies a creator, it automatically invokes `get_object_details` to pull their associated works. This direct MCP connection traces this entire multi-step tool chain, letting you debug exactly how your agent navigates the museum's digital archives.

Setup guide

Set up Harvard Art Museums 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 Harvard Art Museums tools at runtime.
3

Create your Agent

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

Run the agent

Call Runner.run(agent, prompt) to execute. The agent invokes the appropriate Harvard Art Museums 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="Harvard Art Museums Agent",
            instructions="You have access to Harvard Art Museums 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 Harvard Art Museums. 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 Harvard Art Museums 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 Harvard Art Museums MCP in OpenAI Agents SDK

Your agent auto-discovers the tools during initialization. You instantiate MCPServerStreamableHttp pointing to the Vinkius endpoint and pass it to the agent constructor. The SDK automatically inspects the schema and exposes the six museum tools to your model.

Yes, you set cacheToolsList=True in the server configuration parameter. This stops the SDK from fetching the tool schema from the MCP Server on every single run. It saves network roundtrips and keeps your production agent fast.

You write custom guardrails in your SDK code to throttle agent requests. Before the agent calls check_api_status or runs a heavy search, your middleware checks your rate budget. This prevents your agent from spamming the museum's public API.

Yes, your agent does this by chaining the tools sequentially. It lists the physical rooms via list_museum_galleries and then queries specific items using get_object_details. The agent handles the logical flow based on your system prompt.

Vinkius executes the server inside an ephemeral, zero-trust V8 isolate sandbox. Your museum API keys and search queries are stored as encrypted environment variables. They never leak to the client or touch persistent storage.

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