How to Use the Met Museum MCP in Pydantic AI

Q: How do I configure the Met Museum MCP Server toolset in Pydantic AI?

Install the framework using pip install "pydantic-ai-slimmcp" and initialize MCPToolset with the Vinkius HTTP endpoint. Pass this toolset into the toolsets argument of your Agent to expose all four museum tools.

Q: Does Pydantic AI support both HTTP and SSE transports for the Met Museum MCP Server?

Yes, the MCPToolset supports both streamable HTTP and SSE transports. You simply pass the appropriate Vinkius connection string to the constructor, and the framework handles the underlying network protocols.

Query the Met Museum MCP Server with Pydantic AI to enforce strict type safety and validation on every artwork record.

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 Pydantic AI

Create your Vinkius account to connect Met Museum to Pydantic AI 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 Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Type-safe art history via Pydantic AI

This MCP Server exposes the `get_object` tool to retrieve structured metadata for any artwork in the Metropolitan Museum of Art. Every piece of returned data—from the artist's name to the creation date—is validated against your Pydantic schemas before your agent even sees it. If the museum's API returns a null value where your application expects a string, the runtime fails loudly with a validation error. This prevents corrupted metadata or missing fields from silently breaking your production pipeline.

Structured department filtering with zero schema drift

The `list_departments` tool provides a clean list of all valid museum departments. Pydantic AI validates this list against your defined models, ensuring that your agent only routes queries to departments that actually exist. By using the unified `MCPToolset` class, you connect to the external Vinkius server over HTTP. The toolset dynamically generates the required validation schemas, keeping your local codebase in sync with any changes to the museum's department structure.

Guaranteed search results validation

The `search_objects` tool returns an array of object IDs matching your search criteria. Your agent can then use `list_objects` to verify these IDs against active museum records, with Pydantic AI enforcing integer constraints on every single identifier. This strict validation prevents your agent from hallucinating fake object IDs or trying to fetch records that do not exist. You get clean, type-safe arrays that you can immediately pass to downstream database operations or UI rendering components.

Setup guide

Set up Met Museum MCP in Pydantic AI

Prerequisites

Python 3.10+ installed
pydantic-ai-slim[fastmcp] package
Active Vinkius subscription with a valid endpoint token

1

Install Pydantic AI with FastMCP
Run pip install "pydantic-ai-slim[fastmcp]". The FastMCP toolset replaces the deprecated MCPServerHTTP class with full protocol support.
2

Configure the FastMCPToolset
Pass a JSON-style config dict to FastMCPToolset with your Vinkius URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. Supports Streamable HTTP, SSE, and Stdio transports.
3

Create and run your agent
Pass the toolset to Agent(toolsets=[toolset]) and call agent.run(). Swap openai:gpt-4o for any supported model — Anthropic, Google, Mistral, or Groq.

agent.py

from pydantic_ai import Agent
from pydantic_ai.toolsets.fastmcp import FastMCPToolset

toolset = FastMCPToolset({
    "mcpServers": {
        "met-museum-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

agent = Agent(
    "openai:gpt-4o",
    toolsets=[toolset],
    system_prompt="You have access to Met Museum tools.",
)

result = await agent.run("List recent Met Museum transactions")
print(result.output)

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 Pydantic AI

Install the framework using `pip install "pydantic-ai-slim[mcp]"` and initialize `MCPToolset` with the Vinkius HTTP endpoint. Pass this toolset into the `toolsets` argument of your `Agent` to expose all four museum tools.

The framework will immediately raise a validation error, halting execution before the invalid data can corrupt your application state. This guarantees that your agent only operates on clean, verified museum metadata.

Yes, the `MCPToolset` supports both streamable HTTP and SSE transports. You simply pass the appropriate Vinkius connection string to the constructor, and the framework handles the underlying network protocols.

Yes, Pydantic AI is model-agnostic. You can connect this server to local models running via Ollama or commercial APIs from OpenAI and Anthropic, and the system will still enforce strict type validation on all museum data.

The server only transmits public museum search terms and object IDs, keeping your application logic completely private. Vinkius hosts the server in a secure V8 isolate sandbox, ensuring your queries are processed in isolation and never logged or stored.

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