How to Use the Met Museum MCP in CrewAI

Run specialized CrewAI agent teams that collaborate to search, filter, and extract historical data from the Met Museum collection.

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 CrewAI

Create your Vinkius account to connect Met Museum to CrewAI 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 CrewAI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Coordinated Met Museum Search with CrewAI Agents

`search_objects` serves as the entry point for your research crew via this MCP Server. You assign one agent to run queries across the Met Museum's collection while a second agent monitors the incoming IDs to filter out irrelevant records. This setup eliminates manual searching by letting specialized agents divide the labor. The search agent passes its raw results to a curator agent, which uses `get_object` to pull deep metadata for only the most relevant pieces.

Targeted Department Sorting

`list_departments` lets your moderator agent map out the museum's layout before launching deep searches. Look, here's the thing: establishing valid department IDs first prevents your agents from making invalid queries to the external API. Once your lead agent gets this department list, it assigns specific sub-agents to target individual areas like Arms and Armor or Greek and Roman Art. Your CrewAI team operates within clean boundaries, preventing wasted API calls and keeping token usage low.

Automated Object Processing

`list_objects` feeds a continuous stream of raw object IDs directly to your processing agents using this MCP server. One agent pulls the IDs in bulk, while an analysis agent runs `get_object` on each ID to extract artist names, mediums, and creation dates. This division of labor prevents your main agent from getting bogged down in raw data extraction. Your crew processes hundreds of historical artifacts sequentially, compiling clean dossiers on specific art movements without human intervention.

Setup guide

Set up Met Museum MCP in CrewAI

Prerequisites

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

1

Install CrewAI
Run pip install crewai to install the framework. MCP support is built-in via the mcps parameter.
2

Add the MCP URL to your agent
Pass your Vinkius endpoint directly to the mcps list. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. CrewAI handles tool discovery and caching automatically.
3

Kick off your crew
Create a Crew with your agent and tasks. Call crew.kickoff() — the agent will automatically invoke Met Museum tools as needed.

crew.py

from crewai import Agent, Task, Crew

agent = Agent(
    role="Met Museum Analyst",
    goal="Access and analyze Met Museum data via MCP.",
    backstory="Expert analyst with direct Met Museum access.",
    mcps=[
        "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ],
)

task = Task(
    description="List recent Met Museum transactions",
    agent=agent,
    expected_output="A summary of recent activity",
)

crew = Crew(agents=[agent], tasks=[task])
result = crew.kickoff()
print(result)

Get your connection token →

Prerequisites

Python 3.10+ installed
crewai + crewai-tools packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install crewai crewai-tools. The MCPServerAdapter handles lifecycle management and tool conversion.
2

Connect with MCPServerAdapter
Use MCPServerAdapter as a context manager with SseServerParameters pointing to your Vinkius endpoint. The adapter automatically manages connection lifecycle.
3

Assign tools and run
Pass the returned mcp_tools to your agent's tools parameter. The adapter converts MCP tools to native BaseTool objects compatible with all CrewAI agents.

crew.py

from crewai import Agent, Task, Crew
from crewai_tools import MCPServerAdapter
from mcp import SseServerParameters

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

with MCPServerAdapter(server_params) as mcp_tools:
    agent = Agent(
        role="Met Museum Analyst",
        goal="Access and analyze Met Museum data via MCP.",
        backstory="Expert analyst with direct Met Museum access.",
        tools=mcp_tools,
    )

    task = Task(
        description="List recent Met Museum transactions",
        agent=agent,
        expected_output="A summary of recent activity",
    )

    crew = Crew(agents=[agent], tasks=[task])
    result = crew.kickoff()
    print(result)

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 CrewAI

You install the crewai packages and pass the server's URL directly in your Agent definition using the mcps parameter. This instantly exposes the museum's search and retrieval tools to that specific agent.

Yes, CrewAI agents use shared memory to pass artifact metadata retrieved via `get_object` to other agents in the crew. For example, a researcher agent finds the object ID, and a writer agent uses that ID to pull the full details.

The Met Museum public API limits traffic to 80 requests per second. You should configure your CrewAI manager agent to execute tasks sequentially rather than in parallel to avoid hitting these rate limits during bulk object lookups.

Yes, you can use the advanced setup with MCPServerHTTP and a tool_filter to restrict access. This lets you expose only `search_objects` to your research agents while keeping other tools hidden.

This server only handles public museum metadata, department listings, and object IDs. Vinkius runs the server in an isolated sandbox, meaning your CrewAI execution logs, agent prompts, and API keys never touch external servers or public 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