How to Use the Met Museum MCP in AutoGen

Connect your AutoGen agents to the Met Museum collection. Let your agents debate art history and fetch records in real-time.

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 AutoGen

Create your Vinkius account to connect Met Museum to AutoGen 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 AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Search and retrieve with AutoGen

Your agents can now query the museum database using `search_objects` to find specific pieces for their research. This allows your multi-agent team to identify relevant artworks before narrowing down their selection. Once the agents agree on a target, they trigger `get_object` to pull the full metadata. Your system gets the title, artist, and primary image link directly from the source.

Map out the Met Museum departments

Agents often need context before diving into a deep search. Use `list_departments` to get a structured view of the museum's organization. This helps your agents refine their queries by targeting specific collections. It prevents them from hunting through unrelated data when they know exactly where an object belongs.

Catalog access for your MCP Server

The `list_objects` tool provides a broad index of IDs for the entire collection. It gives your agents a starting point to iterate through the vast inventory. Your agents can use these IDs to systematically audit or categorize records. It acts as the backbone for any agentic workflow that requires a full scan of the museum's holdings.

Setup guide

Set up Met Museum MCP in AutoGen

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] package
Active Vinkius subscription with a valid endpoint token

1

Install AutoGen with MCP
Run pip install "autogen-ext[mcp]" autogen-agentchat. The MCP extension includes mcp_server_tools for stateless tool access.
2

Fetch tools from the MCP
Call mcp_server_tools(SseServerParams(url=...)) with your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Run your agent
Pass the tools to AssistantAgent and call agent.run(). The agent invokes Met Museum tools and returns structured results.

agent.py

from autogen_ext.tools.mcp import SseServerParams, mcp_server_tools
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

server_params = SseServerParams(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

tools = await mcp_server_tools(server_params)

agent = AssistantAgent(
    name="Met Museum_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

result = await agent.run("List recent Met Museum data")
print(result.messages[-1].content)

Get your connection token →

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] + autogen-agentchat
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Same packages as above. McpWorkbench is ideal when your agent needs stateful sessions across multiple tool calls.
2

Use McpWorkbench as context manager
Wrap your agent in async with McpWorkbench(...) to maintain shared state and resources. The workbench manages the full MCP session lifecycle.
3

Run with workbench
Pass workbench=workbench to your agent. State is preserved across multiple tool calls within the same session.

agent.py

from autogen_ext.tools.mcp import McpWorkbench, SseServerParams
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

server_params = SseServerParams(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

async with McpWorkbench(server_params) as workbench:
    agent = AssistantAgent(
        name="Met Museum_assistant",
        model_client=OpenAIChatCompletionClient(model="gpt-4o"),
        workbench=workbench,
    )

    result = await agent.run("List recent Met Museum data")
    print(result.messages[-1].content)

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 AutoGen

You initialize the tool via the McpToolAdapter and pass it to your AssistantAgent. Once connected, your agent calls `search_objects` with your query string. The agent then processes the resulting IDs to decide the next step in its debate.

Yes, absolutely. Since the server exposes these tools to the agent's environment, different agents can pull conflicting or supporting data from the Met Museum to verify their claims. They negotiate based on the actual metadata returned.

Your agents can be configured to challenge each other's findings. If one agent retrieves a record and makes a bad inference, a second agent can use `get_object` again to cross-check the metadata and correct the record.

The server manages the connection logic so your agent doesn't have to deal with complex auth headers. You just provide the endpoint token and the server handles the handshake with the museum's public API.

The server only touches public artwork metadata like titles, artist names, and image URLs. No personal user data is ever sent to the museum's servers during your agent's session.

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