The Met Museum MCP Server for OpenAI Agents SDK 8 tools — connect in under 2 minutes
The OpenAI Agents SDK enables production-grade agent workflows in Python. Connect The Met Museum through Vinkius and your agents gain typed, auto-discovered tools with built-in guardrails. no manual schema definitions required.
ASK AI ABOUT THIS MCP SERVER
Vinkius supports streamable HTTP and SSE.
import asyncio
from agents import Agent, Runner
from agents.mcp import MCPServerStreamableHttp
async def main():
# Your Vinkius token. get it at cloud.vinkius.com
async with MCPServerStreamableHttp(
url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
) as mcp_server:
agent = Agent(
name="The Met Museum Assistant",
instructions=(
"You help users interact with The Met Museum. "
"You have access to 8 tools."
),
mcp_servers=[mcp_server],
)
result = await Runner.run(
agent, "List all available tools from The Met Museum"
)
print(result.final_output)
asyncio.run(main())
* Every MCP server runs on Vinkius-managed infrastructure inside AWS - a purpose-built runtime with per-request V8 isolates, Ed25519 signed audit chains, and sub-40ms cold starts optimized for native MCP execution. See our infrastructure
About The Met Museum MCP Server
Connect to The Met Museum and explore one of the world's largest art collections through natural conversation — no API key needed.
The OpenAI Agents SDK auto-discovers all 8 tools from The Met Museum through native MCP integration. Build agents with built-in guardrails, tracing, and handoff patterns. chain multiple agents where one queries The Met Museum, another analyzes results, and a third generates reports, all orchestrated through Vinkius.
What you can do
- Artwork Search — Search 470,000+ artworks by artist name, title, culture, medium or any term
- Artwork Details — Get full metadata including title, artist, date, medium, dimensions, credit line and images
- Department Browse — Explore artworks by department (European Paintings, Egyptian Art, Asian Art, etc.)
- Highlights — Discover curator-selected highlights from the collection
- On-View Objects — Find artworks currently displayed in the museum galleries
- Date Range Search — Filter artworks by century or specific date ranges
- Image Discovery — Find artworks with Open Access CC0 images
The The Met Museum MCP Server exposes 8 tools through the Vinkius. Connect it to OpenAI Agents SDK in under two minutes — no API keys to rotate, no infrastructure to provision, no vendor lock-in. Your configuration, your data, your control.
How to Connect The Met Museum to OpenAI Agents SDK via MCP
Follow these steps to integrate the The Met Museum MCP Server with OpenAI Agents SDK.
Install the SDK
Run pip install openai-agents in your Python environment
Replace the token
Replace [YOUR_TOKEN_HERE] with your Vinkius token from cloud.vinkius.com
Run the script
Save the code above and run it: python agent.py
Explore tools
The agent will automatically discover 8 tools from The Met Museum
Why Use OpenAI Agents SDK with the The Met Museum MCP Server
OpenAI Agents SDK provides unique advantages when paired with The Met Museum through the Model Context Protocol.
Native MCP integration via `MCPServerSse`, pass the URL and the SDK auto-discovers all tools with full type safety
Built-in guardrails, tracing, and handoff patterns let you build production-grade agents without reinventing safety infrastructure
Lightweight and composable: chain multiple agents and MCP servers in a single pipeline with minimal boilerplate
First-party OpenAI support ensures optimal compatibility with GPT models for tool calling and structured output
The Met Museum + OpenAI Agents SDK Use Cases
Practical scenarios where OpenAI Agents SDK combined with the The Met Museum MCP Server delivers measurable value.
Automated workflows: build agents that query The Met Museum, process the data, and trigger follow-up actions autonomously
Multi-agent orchestration: create specialist agents. one queries The Met Museum, another analyzes results, a third generates reports
Data enrichment pipelines: stream data through The Met Museum tools and transform it with OpenAI models in a single async loop
Customer support bots: agents query The Met Museum to resolve tickets, look up records, and update statuses without human intervention
The Met Museum MCP Tools for OpenAI Agents SDK (8)
These 8 tools become available when you connect The Met Museum to OpenAI Agents SDK via MCP:
get_departments
Useful for filtering searches by department (e.g. European Paintings, Egyptian Art, Asian Art, Arms and Armor). Get all museum departments
get_object
Returns title, artist, culture, date, medium, dimensions, credit line, repository URL, image URLs and more. All Open Access images are CC0 public domain. Get detailed info for a specific artwork by object ID
get_objects_by_department
Use get_departments first to find the department ID. Returns list of object IDs which can be used with get_object for full details. Get all object IDs for a specific department
search_by_century
Returns object IDs which can be used with get_object for full artwork details including images. Search for objects created in a specific century
search_highlights
These represent some of the most significant and popular works in the collection. Search for highlighted (curator-selected) objects
search_objects
Supports filtering by department, date range, medium, images, highlights and on-view status. Returns object IDs which can be used with get_object for full details. Search The Met collection for artworks
search_on_view
Useful for planning museum visits. Search for objects currently on view in the museum
search_with_images
Useful for finding visual artworks. Supports all standard search filters plus has_images=true. Search for objects that have images
Example Prompts for The Met Museum in OpenAI Agents SDK
Ready-to-use prompts you can give your OpenAI Agents SDK agent to start working with The Met Museum immediately.
"Search for paintings by Monet."
"Show me the highlights from Egyptian Art."
"Find sculptures from the 1800s."
Troubleshooting The Met Museum MCP Server with OpenAI Agents SDK
Common issues when connecting The Met Museum to OpenAI Agents SDK through the Vinkius, and how to resolve them.
MCPServerStreamableHttp not found
pip install --upgrade openai-agentsAgent not calling tools
The Met Museum + OpenAI Agents SDK FAQ
Common questions about integrating The Met Museum MCP Server with OpenAI Agents SDK.
How does the OpenAI Agents SDK connect to MCP?
MCPServerSse(url=...) to create a server connection. The SDK auto-discovers all tools and makes them available to your agent with full type information.Can I use multiple MCP servers in one agent?
MCPServerSse instances to the agent constructor. The agent can use tools from all connected servers within a single run.Does the SDK support streaming responses?
Connect The Met Museum with your favorite client
Step-by-step setup guides for every MCP-compatible client and framework:
Anthropic's native desktop app for Claude with built-in MCP support.
AI-first code editor with integrated LLM-powered coding assistance.
GitHub Copilot in VS Code with Agent mode and MCP support.
Purpose-built IDE for agentic AI coding workflows.
Autonomous AI coding agent that runs inside VS Code.
Anthropic's agentic CLI for terminal-first development.
Python SDK for building production-grade OpenAI agent workflows.
Google's framework for building production AI agents.
Type-safe agent development for Python with first-class MCP support.
TypeScript toolkit for building AI-powered web applications.
TypeScript-native agent framework for modern web stacks.
Python framework for orchestrating collaborative AI agent crews.
Leading Python framework for composable LLM applications.
Data-aware AI agent framework for structured and unstructured sources.
Microsoft's framework for multi-agent collaborative conversations.
Connect The Met Museum to OpenAI Agents SDK
Get your token, paste the configuration, and start using 8 tools in under 2 minutes. No API key management needed.