How to Use the Harvard Art Museums Alternative MCP in Google ADK

Q: Can I limit which tools the Harvard Art Museums Alternative exposes to my Google ADK agent?

Yes, you can use the toolnames filter during initialization to expose only the tools you need. For example, you can limit the agent to listobjects and getiiifobjectmanifest to keep its focus tight.

Q: How does this MCP Server handle color-based searches?

Your agent can call listcolors and listspectrums to retrieve the exact CSS3 and extracted color terms used in the collection. This allows your agent to find works matching specific color profiles.

Q: Does the Harvard Art Museums Alternative MCP Server work with Google ADK's native BigQuery integrations?

Yes, the structured JSON returned by tools like listclassifications and listmediums fits clean schemas. Your agent can fetch this data and write it directly to BigQuery tables.

Feed 250,000+ museum records straight into your Google ADK pipelines for long-context research and BigQuery joins.

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 Alternative MCP to Google ADK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Long-Context Art History Research

`list_objects` lets your Google ADK agent pull massive batches of museum records into Gemini's million-token context window. The agent uses `get_object` to inspect specific pieces, extracting detailed histories and donor records. By using this MCP Server, your agent can cross-reference hundreds of objects at once. This lets you build deep historical maps without hitting context limits.

Enterprise Data Joins with Google ADK

`list_people` and `get_person` fetch clean JSON records of artists, donors, and curators. You can feed this data directly into BigQuery to join museum records with your own internal databases. Your agent calls `list_publications` and `get_publication` to pull bibliographic sources. This lets your pipeline verify historical references against external academic datasets.

Media and Gallery Analysis

`get_iiif_gallery_manifest` and `list_videos` expose rich media assets directly to your agent. Your agent uses these tools to inspect physical gallery layouts and associated video files. This MCP Server provides direct access to audio descriptions via `list_audios` and `get_audio`. Your agent can process these files to generate alt-text or accessibility reports for your web projects.

Setup guide

Set up Harvard Art Museums Alternative 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 Alternative 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 Alternative_agent",
    model="gemini-2.0-flash",
    instruction="You have access to Harvard Art Museums Alternative 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 Alternative 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 Alternative MCP in Google ADK

You initialize the McpToolset with the server's HTTP URL and pass it to your LlmAgent tools list. Your Gemini-backed agent will instantly discover all 35 tools, from list_objects to get_object.

Yes, you can use the tool_names filter during initialization to expose only the tools you need. For example, you can limit the agent to list_objects and get_iiif_object_manifest to keep its focus tight.

Your agent can call list_colors and list_spectrums to retrieve the exact CSS3 and extracted color terms used in the collection. This allows your agent to find works matching specific color profiles.

Yes, the structured JSON returned by tools like list_classifications and list_mediums fits clean schemas. Your agent can fetch this data and write it directly to BigQuery tables.

All requests for museum metadata, search terms, and gallery IDs are processed in an ephemeral, zero-trust sandbox. Your connection token is encrypted, and no query history is saved on our servers.

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