How to Use the CERN Open Data MCP in OpenAI Agents SDK

Q: How do I find CMS datasets using CERN Open Data in my OpenAI Agents SDK?

You use the searchbyexperiment tool to filter for CMS entries. Your agent then iterates through the results to select the specific datasets relevant to your query.

Q: Can my OpenAI Agents SDK pipeline verify CERN Open Data status before querying?

Yes. Call checkcernopendatastatus before any data-intensive operations to confirm the endpoint is responding correctly.

Q: Does the CERN Open Data MCP Server provide raw file links for my OpenAI Agents SDK agent?

It does. Once you resolve a record, use listrecordfiles to retrieve the ROOT or EOS URIs for the data files.

Q: Is it possible to filter by collision energy in OpenAI Agents SDK?

Absolutely. You pass the energy parameter to searchbycollisionenergy to limit your search to specific LHC or LEP run conditions.

Query particle physics records directly from your OpenAI Agents SDK production pipeline using the CERN Open Data MCP Server.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect CERN Open Data MCP to OpenAI Agents SDK

Create your Vinkius account to connect CERN Open Data 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 CERN Open Data with OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Search and inspect physics records

Your agent can ping the portal to find specific datasets via `search_datasets` or resolve known references using `get_record_by_doi`. Once you have a record ID, use `get_record` to pull metadata like author ORCID identifiers and collision parameters. This workflow allows your agent to handle complex data discovery without manual intervention. It feeds the raw metadata directly into your downstream logic for further processing.

Analyze experimental data facets

Use `get_portal_statistics` to understand the scope of available data across different years and record types. This helps your agent decide which experiments to query first, such as those listed by `list_experiments`. Filtering by technical parameters is straightforward with `search_by_collision_energy` or `search_by_collision_type`. Your agent can quickly narrow down the millions of events to the specific subsets required for your current analysis.

Access technical documentation and software

Connect your agent to `search_documentation` or `search_software` to pull the exact analysis frameworks needed for reproduction. If you hit a wall with physics terminology, `get_glossary` provides clear definitions for terms like pseudorapidity or b-tagging. By incorporating `search_supplementaries`, your agent gathers the necessary configurations for published results. This ensures your production code remains grounded in the correct technical context.

Setup guide

Set up CERN Open Data 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 CERN Open Data tools at runtime.
3

Create your Agent

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

Run the agent

Call Runner.run(agent, prompt) to execute. The agent invokes the appropriate CERN Open Data 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="CERN Open Data Agent",
            instructions="You have access to CERN Open Data 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 CERN Open Data. 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 CERN Open Data 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 CERN Open Data MCP in OpenAI Agents SDK

You use the `search_by_experiment` tool to filter for CMS entries. Your agent then iterates through the results to select the specific datasets relevant to your query.

Yes. Call `check_cern_opendata_status` before any data-intensive operations to confirm the endpoint is responding correctly.

It does. Once you resolve a record, use `list_record_files` to retrieve the ROOT or EOS URIs for the data files.

Absolutely. You pass the energy parameter to `search_by_collision_energy` to limit your search to specific LHC or LEP run conditions.

The server only exposes public research data. It does not touch private user information or sensitive credentials, keeping your agent's execution scope strictly limited to open-access physics records.

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