How to Use the Met Museum MCP in OpenAI Agents SDK

Q: How do I register the Met Museum MCP Server with the OpenAI Agents SDK?

You install the SDK with pip install openai-agents and instantiate MCPServerStreamableHttp using the Vinkius endpoint. Pass this server instance inside the mcpservers list when you build your Agent constructor. The SDK automatically discovers all four museum tools at runtime.

Q: Does this integration support image downloads?

The getobject tool returns the public URL of the primary image along with metadata. Your agent receives this URL and can pass it to other tools in your pipeline to download, analyze, or display the image.

Feed 470,000+ works of art from the Met Museum MCP Server directly to your OpenAI Agents SDK production deployment with zero manual cataloging.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Met Museum MCP to OpenAI Agents SDK

Create your Vinkius account to connect Met Museum 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 Met Museum with OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Connect OpenAI Agents SDK to 5,000 years of art

This MCP Server exposes four distinct tools including `list_departments` to let your agent map out the entire physical layout of the museum's collection. You get immediate access to curated departments like Arms and Armor or Egyptian Art without hardcoding any directory paths. The SDK automatically registers these tools when you initialize the server connection. Your agents can query the department list, decide which areas are relevant to a user's prompt, and route the conversation to a specialized sub-agent trained on that specific historical era.

Guardrails and tracing for artwork queries

The `search_objects` tool lets your agent find specific pieces of art using text queries. Because the OpenAI Agents SDK forces runtime validation, you can trace exactly how your agent translates a user's messy search query into a structured API call. You can inspect every step of the search execution in your OpenAI dashboard. If the agent tries to run a search that violates your custom safety protocols, the SDK blocks the call before it hits the museum's endpoint, keeping your production environment secure.

Safe metadata retrieval with automated handoffs

The `get_object` tool pulls deep metadata, historical context, and image links for any specific artifact. When a user asks for detailed provenance, your general-purpose agent hands the task to a dedicated researcher agent that calls this tool. To avoid hammering the API and wasting your rate limits, you set `cacheToolsList=True` during setup. This caches the tool schemas locally, ensuring your agents resolve routing decisions instantly without fetching the tool definitions on every single turn.

Setup guide

Set up Met Museum 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 Met Museum tools at runtime.
3

Create your Agent

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

Run the agent

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

You install the SDK with `pip install openai-agents` and instantiate `MCPServerStreamableHttp` using the Vinkius endpoint. Pass this server instance inside the `mcp_servers` list when you build your Agent constructor. The SDK automatically discovers all four museum tools at runtime.

Yes, you control tool access by defining specific agent roles and restricting their tool lists. For example, you can assign `list_objects` solely to a background indexing agent while giving your customer-facing agent access only to `get_object`.

The SDK relies on your python application's rate-limiting logic to manage execution speed. Since `list_objects` can return large arrays of IDs, you should implement a token bucket or queue in your agent's execution loop to stay within the Met's public API limits.

The `get_object` tool returns the public URL of the primary image along with metadata. Your agent receives this URL and can pass it to other tools in your pipeline to download, analyze, or display the image.

This server only handles public domain museum catalog metadata and open-access image links, meaning no user-identifying data is ever sent to the museum's endpoints. Vinkius runs the server in an isolated, ephemeral sandbox that destroys the execution context as soon as your query completes.

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