How to Use the Harvard Art Museums MCP in Google ADK

Q: Can I restrict which Harvard Art Museums tools are exposed to Google ADK?

Yes, you use the optional toolnames filter when instantiating your McpToolset. If you only want your agent to search exhibitions, you expose searchexhibitions and block administrative tools like checkapistatus.

Connect Gemini models to the Harvard Art Museums using Google ADK to analyze massive cultural datasets.

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 Google ADK

Create your Vinkius account to connect Harvard Art Museums to Google ADK 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 Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Analyze massive museum datasets using Google ADK

The `search_museum_objects` tool feeds raw collection data directly into Gemini's million-token context window. Let's look at the actual data. You can dump hundreds of object payloads into a single run to spot curation patterns across centuries — and yes, metadata matters — without hitting context walls. Your Google ADK agent processes these bulk inputs alongside your existing data warehouses. Running this as an MCP Server lets you feed these museum records straight into your analytics pipelines for deep academic research.

Sync physical gallery layouts with cloud databases

The `list_museum_galleries` tool extracts the actual floor plans and room configurations of the physical museum. Look: it's not rocket science. Your agent pulls the active gallery list, maps it against your BigQuery tables, and identifies which physical spaces house specific historical collections. This MCP Server toolset lets enterprise developers build spatial-cultural maps. By combining real-time gallery statuses with cloud storage, your agent maintains an accurate digital twin of the physical museum layout.

Trace artist provenance with Gemini agents

The `search_museum_people` tool queries the biographical records of artists, donors, and curators associated with each piece. Here's the deal: tracing provenance is tedious, but this endpoint lets your agent build structured lineage graphs. Your agent calls `get_object_details` to verify the ownership history of specific items. The Google ADK manages the tool execution state, passing clean JSON directly to Gemini for reasoning, extraction, and cloud-archiving.

Setup guide

Set up Harvard Art Museums MCP in Google ADK

Prerequisites

Python 3.10+ installed
google-adk package (pip install google-adk)
Active Vinkius subscription with a valid endpoint token

1

Install Google ADK

Run pip install google-adk to install the Agent Development Kit. MCP support is included via the McpToolset class.
2

Connect via SSE transport

Use McpToolset.from_server() with SseServerParams pointing to your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Create an LlmAgent

Pass the returned mcp_tools list directly to LlmAgent(tools=mcp_tools). The ADK maps each MCP tool to a native Gemini function call — no manual schema definitions required.
4

Run with any Gemini model

The agent works with any Gemini model (gemini-2.0-flash, gemini-2.5-pro, etc.). Copy the full example on the right to get started with Harvard Art Museums tools in your ADK agent.

agent.py

from google.adk.agents import LlmAgent
from google.adk.tools.mcp_tool.mcp_toolset import McpToolset
from google.adk.tools.mcp_tool.mcp_session_manager import SseServerParams

# Connect to the MCP via SSE
mcp_tools, exit_stack = await McpToolset.from_server(
    connection_params=SseServerParams(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    )
)

# Create your agent with auto-discovered tools
agent = LlmAgent(
    name="Harvard Art Museums_agent",
    model="gemini-2.0-flash",
    instruction="You have access to Harvard Art Museums tools via MCP.",
    tools=mcp_tools,
)

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 Google ADK

You use the McpToolset class with StreamableHttpServerParameters pointing to your Vinkius endpoint URL. Pass this toolset into your LlmAgent tools list. The Gemini model immediately gains the ability to query the museum's database.

Yes, you use the optional tool_names filter when instantiating your McpToolset. If you only want your agent to search exhibitions, you expose search_exhibitions and block administrative tools like check_api_status.

The framework passes the structured JSON payloads directly into Gemini's native context. Since the model handles massive token counts, you can run extensive searches using search_museum_objects without worrying about truncating the results.

Yes, the Google ADK toolset accommodates both transport layers. For hosted Vinkius servers, you will configure the HTTP streamable transport to communicate with the remote museum database.

All search parameters and API keys are processed within secure, ephemeral V8 isolates on Vinkius. This MCP architecture ensures your museum query payloads and API credentials are never exposed to external networks.

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