How to Use the CERN Open Data MCP in LangChain

Q: Can a LangChain agent explain physics terms from a CERN Open Data abstract?

Yes. After using getrecord to fetch an abstract, the agent can identify technical terms and call getglossary. It will return definitions for concepts like 'transverse momentum' or 'luminosity' directly in the chain's output.

Q: What's the best way for a LangChain agent to find analysis software in CERN Open Data?

The agent should use the searchsoftware tool. It can look for a specific name, like 'CMSSW', or search by a physics topic to find relevant analysis frameworks and validation tools associated with published results.

Q: How do I check if the connection is working before my agent starts a long chain?

Have your agent call checkcernopendatastatus at the beginning of its chain. This simple check confirms the API is responsive and prevents failed steps later on in a complex reasoning process.

Build LangChain agents that reason over petabytes of LHC data from the CERN Open Data portal.

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 LangChain

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Chain Together Data Discovery Steps

Give your LangChain agent a goal, not a script. It can start by calling `list_experiments` to get a feel for the landscape, then use `search_by_category` to zero in on 'Higgs Physics'. The agent builds a plan on the fly, using the output of one tool to decide what to do next. This is how you explore a massive data catalog. The agent might take the results from a category search and feed them into a `search_datasets` query for 'SM Higgs to two photons'. It's a sequence of logical steps, with each tool call informing the next, all without you hard-coding the workflow.

Deconstruct Physics Records in a Chain

Finding a dataset is just the start. Once your agent gets a record ID from `search_datasets`, its work begins. The next link in the chain is a call to `get_record` for the full abstract, author list, and DOI. From there, the agent can get even more specific. If it hits a term like 'pseudorapidity' in the abstract, it calls `get_glossary` to define it. To prep for a download, it uses `list_record_files` to check the exact ROOT file names and sizes. It's a full-stack investigation, all handled by the agent's reasoning process.

Build Dynamic Reports with This MCP Server

You can build an agent that generates a complete status report on the CERN portal. The chain starts with `get_portal_statistics` to get the big picture: total dataset counts, available years, and top keywords. Then, it drills down. The agent can loop through the results of `list_categories` and run `search_by_category` for each one, summarizing the top datasets in each field. This isn't a static dashboard; it's a live report generated by your agent's tool-using logic, powered by this MCP connection.

Setup guide

Set up CERN Open Data MCP in LangChain

Prerequisites

Python 3.10+ installed
langchain-mcp-adapters + langgraph packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install langchain-mcp-adapters langgraph langchain-openai. The MCP adapters package converts MCP tools into native LangChain BaseTool objects.
2

Connect via HTTP transport
Use MultiServerMCPClient with "transport": "http" pointing to your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Create a ReAct agent
Pass the discovered tools to create_react_agent() from LangGraph. The agent automatically routes CERN Open Data tool calls through the MCP protocol.
4

Run with any LLM
Swap ChatOpenAI for ChatAnthropic, ChatGoogleGenerativeAI, or any LangChain-compatible model. The MCP tools work identically across all providers.

agent.py

from langchain_mcp_adapters.client import MultiServerMCPClient
from langgraph.prebuilt import create_react_agent
from langchain_openai import ChatOpenAI

async with MultiServerMCPClient({
    "cern-open-data-mcp": {
        "transport": "http",
        "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp",
    }
}) as client:
    tools = client.get_tools()

    agent = create_react_agent(
        ChatOpenAI(model="gpt-4o"),
        tools,
    )
    result = await agent.ainvoke({
        "messages": "List recent CERN Open Data transactions"
    })
    print(result["messages"][-1].content)

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 LangChain

Your LangChain agent can chain two tool calls. First, it uses `search_by_collision_energy` for '13TeV', then feeds those results into `search_by_collision_type` for 'pp' to get the exact datasets you need.

Yes. After using `get_record` to fetch an abstract, the agent can identify technical terms and call `get_glossary`. It will return definitions for concepts like 'transverse momentum' or 'luminosity' directly in the chain's output.

The agent should use the `search_software` tool. It can look for a specific name, like 'CMSSW', or search by a physics topic to find relevant analysis frameworks and validation tools associated with published results.

Have your agent call `check_cern_opendata_status` at the beginning of its chain. This simple check confirms the API is responsive and prevents failed steps later on in a complex reasoning process.

Your queries, like dataset searches or record ID requests, are sent through an ephemeral, zero-trust sandbox. Vinkius processes the query and returns only the public CERN data, like titles and abstracts, without logging your specific inputs.

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