How to Use the Met Museum MCP in Google ADK

Q: How do I add the Met Museum MCP Server toolset to my Google ADK agent?

You install the package using pip install google-adk and configure McpToolset with your Vinkius HTTP URL. Pass that toolset object into the tools list of your LlmAgent to let Gemini call the museum endpoints.

Q: Can I filter which Met Museum tools the Google ADK exposes to Gemini?

Yes, you can use the optional toolnames filter when initializing your McpToolset to restrict exposure. For instance, you can expose only getobject and block the broader listing tools to keep your agent focused on specific lookups.

Q: How does Google ADK leverage Gemini's long context with the Met Museum data?

The ADK allows Gemini to process large payloads from listobjects without truncation. Your agent can hold thousands of retrieved object IDs in its active memory, cross-referencing them against historical databases you have stored in Google Cloud.

Feed the Met Museum MCP Server collection directly into your Google ADK pipelines to ground Gemini models with real art history.

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 Google ADK

Create your Vinkius account to connect Met Museum 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 Met Museum with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Ground Gemini models with this MCP Server

This MCP Server provides direct access to the Metropolitan Museum of Art's archives, starting with the `list_departments` tool. It lets your Gemini models map out the museum's structured categories before initiating deep historical searches. Because Google ADK integrates natively with Vertex AI, you can feed these department listings straight into your enterprise data pipelines. The agent uses this structural data to categorize incoming user queries before pulling specific records.

Long-context search across thousands of artifacts

The `search_objects` tool returns arrays of matching object IDs based on raw search queries. Gemini's massive one-million-token context window allows your agent to ingest hundreds of these search results simultaneously. Your agent can analyze patterns across vast collections of search results in a single turn. This lets you build comparative analysis tools that spot trends in artistic mediums or historical eras without running out of memory.

Deep metadata analysis with BigQuery integration

The `get_object` tool fetches the complete database record for any individual artwork, including its creator, medium, and creation year. Your agent can retrieve these records on the fly to answer complex, multi-step research questions. You can write the output of these tool calls directly into BigQuery tables using the ADK's native cloud connections. This makes it easy to archive historical metadata alongside your internal enterprise datasets for scheduled analytical runs.

Setup guide

Set up Met Museum 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 Met Museum 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="Met Museum_agent",
    model="gemini-2.0-flash",
    instruction="You have access to Met Museum 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 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 Google ADK

You install the package using `pip install google-adk` and configure `McpToolset` with your Vinkius HTTP URL. Pass that toolset object into the `tools` list of your `LlmAgent` to let Gemini call the museum endpoints.

Yes, you can use the optional `tool_names` filter when initializing your `McpToolset` to restrict exposure. For instance, you can expose only `get_object` and block the broader listing tools to keep your agent focused on specific lookups.

The ADK allows Gemini to process large payloads from `list_objects` without truncation. Your agent can hold thousands of retrieved object IDs in its active memory, cross-referencing them against historical databases you have stored in Google Cloud.

No, the Met Museum API is public and does not require credentials. Vinkius manages the connection details securely, so your ADK agent only needs your single Vinkius endpoint token to authorize the tool calls.

The server only processes public museum metadata and search queries, never touching your private enterprise data. Vinkius executes each tool call inside a zero-trust, ephemeral V8 isolate that leaves zero trace of your queries once the response is sent back to your Google Cloud environment.

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