How to Use the CERN Open Data MCP in Claude Code

Q: How do I configure the CERN Open Data MCP Server in Claude Code?

Run claude mcp add --transport http cern-open-data-mcp -- . The configuration is automatically saved to your /.claude.json file for headless execution.

Pipe CERN Open Data directly into your terminal. Claude Code queries physics datasets and generates analysis pipelines from the command line.

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 Claude Code

Create your Vinkius account to connect CERN Open Data to Claude Code 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 Claude Code

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Monitor the CERN Open Data MCP Server

The `check_cern_opendata_status` tool verifies connectivity to the InvenioRDM REST framework before your CI/CD pipeline attempts to pull massive datasets. Claude Code runs this health check via the terminal, ensuring the portal is online before executing downstream analysis jobs. If the API is up, it can immediately trigger `get_portal_statistics` to log current record counts and data-taking years. You control the entire discovery phase without leaving your shell. Run a quick command, and the agent executes `list_experiments` to dump dataset distributions for ATLAS, ALICE, or LHCb straight to stdout. It parses this data and can pipe it into jq or write it to a local manifest file for your automated workflows.

Resolve DOIs and query metadata

The `get_record_by_doi` tool translates publication references into actionable dataset IDs right in your terminal. When your automated script encounters a paper's DOI, Claude Code resolves it, fetches the underlying record, and stages the data for download. It bypasses the web interface entirely, turning academic citations into raw data pipelines. Finding specific collision events requires aggressive filtering. Your CLI agent uses `search_datasets` combined with `search_by_collision_energy` to isolate 13.6 TeV LHC Run 3 data. It grabs the paginated JSON results and generates the exact curl commands needed to fetch the payloads.

Extract URIs and physics terms

The `list_record_files` tool returns the checksums, sizes, and ROOT URIs for every file in a specified dataset. Claude Code hits this endpoint to generate massive batch download scripts for your computing cluster. It uses `get_record` to pull the collision parameters and author metadata, writing everything into a structured YAML file for your records. Terminal workflows often need quick context on domain-specific terminology. The agent calls `get_glossary` to pull definitions for b-tagging or muon spectrometers without forcing you to open a browser. It injects these definitions directly into the comments of the analysis scripts it generates.

Setup guide

Set up CERN Open Data MCP in Claude Code

Prerequisites

Claude Code CLI installed (npm install -g @anthropic-ai/claude-code)
Active Vinkius subscription with a valid endpoint token

1

Run the add command

Open your terminal and run the command shown on the right. Replace [YOUR_TOKEN_HERE] with your endpoint token from cloud.vinkius.com. Use --scope user to make it available across all projects.
2

Verify the connection

Start a Claude Code session and type /mcp to list connected servers. You should see cern-open-data-mcp with a green status indicator.
3

Start using tools

Ask Claude Code something like "Check my latest CERN Open Data transactions." It will automatically discover and invoke the available CERN Open Data tools.

Terminal

claude mcp add --transport http cern-open-data-mcp https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp

Get your connection token →

Prerequisites

Claude Code CLI installed
Active Vinkius subscription with a valid endpoint token

1

Open the config file

Create or edit .mcp.json in your project root for project-level scope, or ~/.claude.json for user-level scope.
2

Add the CERN Open Data MCP

Paste the JSON snippet shown on the right into the mcpServers object. Replace [YOUR_TOKEN_HERE] with your endpoint token from cloud.vinkius.com.
3

Restart Claude Code

Start a new Claude Code session. Type /mcp to confirm the server is connected. The tools will be automatically available in your conversation.

.mcp.json

{
  "mcpServers": {
    "cern-open-data-mcp": {
      "type": "url",
      "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 Claude Code

Run `claude mcp add --transport http cern-open-data-mcp -- `. The configuration is automatically saved to your ~/.claude.json file for headless execution.

It filters directly by proton-proton, electron-positron, or heavy-ion collisions. You just specify the topology in your terminal prompt.

The agent pulls the paginated file arrays and extracts the direct EOS URIs. It then generates bash scripts using wget or xrootd to handle the actual bulk downloads.

Yes. The agent queries the supplementary endpoints to find configuration files and technical context needed to reproduce published physics analyses.

The server strictly reads public physics records, checksums, and metadata. Claude Code executes these read-only API calls without exposing your local machine state, environment variables, or private shell history to the remote endpoints.

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