How to Use the Harvard Art Museums MCP in AutoGen

Q: How do I add the Harvard Art Museums MCP to AutoGen?

Run pip install -U "autogen-extmcp". Use mcpservertools with a StreamableHttpServerParams pointing to your Vinkius URL. Pass the resulting tool list directly to your AssistantAgent.

Q: Does the framework convert the tool schemas automatically?

McpToolAdapter handles the translation. It reads the JSON schema from the server and formats it so your agents understand exactly what parameters to send.

Build debating agent teams to analyze the Harvard Art Museums collection using AutoGen.

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 AutoGen

Create your Vinkius account to connect Harvard Art Museums 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 Harvard Art Museums with AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Debate acquisition records in real time

The `search_museum_objects` tool hands your AutoGen agents raw data on the museum's holdings. You do not just get a simple answer. A data-crunching agent pulls the object records, while a critical-analysis agent reviews that same data for historical acquisition biases. They debate the findings in real time. If the agents disagree on a piece's origin, one of them will call `get_object_details` to pull the exact provenance. The framework forces them to negotiate based on the actual JSON payload. You watch a multi-agent system reach a consensus grounded in hard institutional facts.

Investigate creator representation

The `search_museum_people` tool lets your agents investigate the creators behind the collection. One agent might argue that a specific demographic is underrepresented. It queries the artist database to prove its point, feeding the raw counts back into the chat. To add context, another agent can trigger `search_exhibitions`. It cross-references the artist data with actual show histories. The AutoGen system manages this back-and-forth automatically, invoking the MCP server only when an agent needs evidence to win an argument.

Audit physical curation with this MCP Server

The `list_museum_galleries` tool gives your agent team the physical layout of the Harvard Art Museums. An architectural agent can map where specific art movements are placed, while a curation agent debates the logic of those placements. They use the API data as the foundation for their discussion. Before they start arguing, the system runs `check_api_status`. This keeps the agents from getting stuck in a loop if the museum database is offline. The framework ensures the underlying connection works before kicking off a massive multi-agent deliberation.

Setup guide

Set up Harvard Art Museums 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 Harvard Art Museums 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="Harvard Art Museums_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

result = await agent.run("List recent Harvard Art Museums 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="Harvard Art Museums_assistant",
        model_client=OpenAIChatCompletionClient(model="gpt-4o"),
        workbench=workbench,
    )

    result = await agent.run("List recent Harvard Art Museums 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 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 AutoGen

Run `pip install -U "autogen-ext[mcp]"`. Use `mcp_server_tools` with a `StreamableHttpServerParams` pointing to your Vinkius URL. Pass the resulting tool list directly to your `AssistantAgent`.

Yes. You can equip different agents with the same tools. A research agent might pull gallery data while a fact-checker agent pulls artist records to verify claims.

If a query returns empty, the agents adapt. They might negotiate a different search term or try a broader query using a different endpoint.

`McpToolAdapter` handles the translation. It reads the JSON schema from the server and formats it so your agents understand exactly what parameters to send.

No. The server only sees the specific search parameters sent to query art objects, exhibitions, and artists. Vinkius routes these requests through isolated, ephemeral containers that retain absolutely zero memory of your agents' conversations.

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