How to Use the CERN Open Data MCP in Cursor

Inject live CERN Open Data directly into your analysis code with the Cursor agent.

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 Cursor

Create your Vinkius account to connect CERN Open Data to Cursor 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 Cursor

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Write Python scripts with actual API responses

Stop writing code against mock data. Tell the Cursor agent, "Write a function to get record details for DOI 10.7483/OPENDATA.CMS.XXX." It will call `get_record_by_doi`, see the real JSON response, and generate a Python function that correctly parses it. This works for any tool. You can have it build a script that searches for datasets using `search_datasets` and then loops through the results. The code it writes just works, because it's based on live data from the MCP server, not a guess.

Explore data without leaving your editor

You're in the middle of writing a data filter and can't remember the exact collision energy values. Just ask the agent in the chat panel, "What collision energies are available?" It runs `search_by_collision_energy` and gives you the list: 13TeV, 8TeV, 7TeV, etc. You can do the same to see which experiments are available with `list_experiments` or what physics categories exist with `list_categories`. It's about getting quick answers to guide your coding, all without switching windows.

Set Up Your Analysis Environment with the Cursor MCP Server

Finding the data is just the first step. You also need the right software. Use the agent to run `search_software` to find the specific CMSSW version or analysis framework associated with a dataset. From there, you can ask it to find supplementary materials using `search_supplementaries`. The agent can then help you script the setup for a fully reproducible analysis environment, right from your editor. This is what an MCP integration is for.

Setup guide

Set up CERN Open Data MCP in Cursor

Prerequisites

Cursor installed (macOS, Windows, or Linux)
Active Vinkius subscription with a valid endpoint token

1

Open MCP Settings

Go to Cursor Settings → MCP or open the Command Palette (Cmd+Shift+P / Ctrl+Shift+P) and search for "MCP: Add Server".
2

Add the CERN Open Data MCP

Cursor will create or open .cursor/mcp.json in your project root. Paste the JSON snippet on the right. Replace [YOUR_TOKEN_HERE] with your endpoint token from cloud.vinkius.com.
3

Enable Agent mode

Open Composer (Cmd+I / Ctrl+I) and switch to Agent mode using the dropdown at the top. MCP tools are only available in Agent mode.
4

Verify the connection

Ask Cursor something like "List my recent CERN Open Data transactions." If the MCP tools are loaded correctly, Cursor will call the CERN Open Data tools automatically. You can also check Settings → MCP for a green status indicator.

.cursor/mcp.json

{
  "mcpServers": {
    "cern-open-data-mcp": {
      "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    }
  }
}

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 Cursor

In the Cursor chat, tell the agent what you're looking for, like "Find datasets in CERN Open Data related to 'top quark pair production' from the CMS experiment." It will use `search_datasets` and show you the results.

Absolutely. Give it a prompt like "Write a python function that takes a DOI and uses the `get_record_by_doi` tool to find a CERN Open Data record." The agent will generate working code based on the tool's actual output.

First, find a record ID. Then, ask the agent: "List all files for record ID 1 from CERN Open Data." It will use the `list_record_files` tool and provide the filenames, sizes, and checksums.

The tools in this MCP server provide metadata and direct access URIs for the data files. You'd then use those URIs in your own code or download scripts to fetch the raw data.

No. Your code stays on your machine. When you ask the agent to use a tool, only the tool call and its parameters are sent to the Vinkius-managed MCP server. Your source code is not part of that request.

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