How to Use the Europeana MCP in OpenAI Agents SDK

Q: How do I connect Europeana to the OpenAI Agents SDK?

Install the openai-agents package via pip. Create an MCPServerStreamableHttp instance with your endpoint URL and pass it to your agent's constructor. Tools auto-discover immediately.

Q: Can the OpenAI Agents SDK search Europeana by specific creators?

Yes. The agent uses the searchrecords tool to filter by creator, date, or medium. It formats the query parameters automatically based on user prompts.

Q: How does Europeana and the OpenAI Agents SDK handle entity lookups?

When a search returns a linked ID, the agent triggers getentity. This fetches the exact historical context for that specific creator or location.

Q: Does caching work with this MCP Server?

You can set cacheToolsList=True in your setup. This prevents the agent from re-fetching the tool schema on every run, dropping latency for rapid queries.

Build safe, production-ready cultural heritage agents using the Europeana MCP Server and OpenAI Agents SDK.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Europeana MCP to OpenAI Agents SDK

Create your Vinkius account to connect Europeana to OpenAI Agents SDK 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 Europeana with OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Search records with OpenAI Agents SDK

Your agent calls `search_records` to query millions of European cultural artifacts. It passes search parameters directly to the API, returning exact matches for artworks, books, and museum items. You don't write custom integration code; the SDK auto-discovers the endpoint. Once the agent finds a relevant item, it triggers `get_record` to pull the detailed JSON metadata. Built-in guardrails validate these actions before execution, ensuring your agent only pulls the specific historical data you requested.

Resolve linked entities instantly

The `get_entity` tool retrieves precise information about linked cultural entities. When your system encounters an unknown creator or location in a record, it resolves the entity ID into structured context. This prevents hallucinations in production. Instead of guessing historical facts, your agent fetches verified entity data while the OpenAI dashboard traces every single API roundtrip.

Harvest XML metadata via MCP Server

Use `oaipmh_request` to pull raw XML data directly from Europeana via OAI-PMH. This enables bulk metadata synchronization for large-scale archival applications. Handoffs between specialized agents shine here. You can assign one agent to handle the heavy XML harvesting while another processes the outputs, keeping your production system stable and responsive.

Setup guide

Set up Europeana MCP in OpenAI Agents SDK

Prerequisites

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

1

Install the SDK

Run pip install openai-agents to install the OpenAI Agents SDK. The MCP integration is built-in — no extra dependencies needed.
2

Connect via SSE transport

Use MCPServerSse with your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. The SDK auto-discovers all Europeana tools at runtime.
3

Create your Agent

Pass the MCP to Agent(mcp_servers=[server]). The agent receives Europeana tools as native definitions — JSON schemas resolve automatically.
4

Run the agent

Call Runner.run(agent, prompt) to execute. The agent invokes the appropriate Europeana tools and returns structured results. Copy the full example on the right to get started.

agent.py

import asyncio
from agents import Agent, Runner
from agents.mcp import MCPServerSse

async def main():
    async with MCPServerSse(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ) as server:
        agent = Agent(
            name="Europeana Agent",
            instructions="You have access to Europeana tools.",
            mcp_servers=[server],
        )
        result = await Runner.run(agent, "List recent transactions")
        print(result.final_output)

asyncio.run(main())

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 Europeana. 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 Europeana 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 Europeana MCP in OpenAI Agents SDK

Install the `openai-agents` package via pip. Create an `MCPServerStreamableHttp` instance with your endpoint URL and pass it to your agent's constructor. Tools auto-discover immediately.

Yes. The agent uses the `search_records` tool to filter by creator, date, or medium. It formats the query parameters automatically based on user prompts.

When a search returns a linked ID, the agent triggers `get_entity`. This fetches the exact historical context for that specific creator or location.

You can set `cacheToolsList=True` in your setup. This prevents the agent from re-fetching the tool schema on every run, dropping latency for rapid queries.

This MCP Server only touches public cultural heritage metadata and XML records. The V8 Isolate Sandbox ensures that active memory wipes after the session closes, leaving zero persistent traces of your queries.

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