How to Use the CERN Open Data MCP in CrewAI

Q: How do I limit which CERN Open Data tools a specific CrewAI agent can use?

Use the MCPServerHTTP class from crewai.mcp and apply a toolfilter. You can restrict your glossary agent to only use getglossary while giving your data agent access to searchdatasets.

Q: What happens when a CrewAI agent requests a massive list of files from a record?

The agent uses listrecordfiles to fetch the file details. Since the MCP Server runs on Vinkius, the response is handled efficiently, allowing the agent to parse the ROOT file URIs without crashing your local Python environment.

Deploy a team of specialized CrewAI agents using this MCP Server to autonomously search, validate, and catalog LHC collision data.

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 CrewAI

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Multi-agent particle physics research teams

Stop running single-agent prompts that lose context. With CrewAI, you can deploy a specialized team where one agent searches for Higgs boson data using `search_by_category` while a second agent analyzes the results. They collaborate using shared memory, passing record IDs to verify collision parameters. This team setup prevents mistakes. The research agent finds the datasets, and the validation agent uses `get_record` to confirm event counts and file sizes before compiling a final report, making the entire MCP search process autonomous.

Autonomous software and configuration matching

Set up a crew to find the exact software stack needed to reproduce published physics results. A software researcher agent can search for reconstruction frameworks using `search_software`. Meanwhile, a configuration specialist agent queries `search_supplementaries` to find the corresponding validation scripts. The agents cross-reference their findings, ensuring the software version matches the data-taking year. By using this MCP Server, your crew autonomously resolves complex dependencies that usually take human researchers hours to trace.

Automatic data cataloging with this MCP Server

Keep your internal documentation updated without manual work. A documentation agent can query `search_documentation` to extract the latest guides on detector configurations, while a glossary agent uses `get_glossary` to define technical terms used in the notes. They combine these inputs to generate clean markdown summaries. By pointing your CrewAI agents at these tools, you can automate the creation of training materials for new physics students.

Setup guide

Set up CERN Open Data MCP in CrewAI

Prerequisites

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

1

Install CrewAI
Run pip install crewai to install the framework. MCP support is built-in via the mcps parameter.
2

Add the MCP URL to your agent
Pass your Vinkius endpoint directly to the mcps list. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. CrewAI handles tool discovery and caching automatically.
3

Kick off your crew
Create a Crew with your agent and tasks. Call crew.kickoff() — the agent will automatically invoke CERN Open Data tools as needed.

crew.py

from crewai import Agent, Task, Crew

agent = Agent(
    role="CERN Open Data Analyst",
    goal="Access and analyze CERN Open Data data via MCP.",
    backstory="Expert analyst with direct CERN Open Data access.",
    mcps=[
        "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ],
)

task = Task(
    description="List recent CERN Open Data transactions",
    agent=agent,
    expected_output="A summary of recent activity",
)

crew = Crew(agents=[agent], tasks=[task])
result = crew.kickoff()
print(result)

Get your connection token →

Prerequisites

Python 3.10+ installed
crewai + crewai-tools packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install crewai crewai-tools. The MCPServerAdapter handles lifecycle management and tool conversion.
2

Connect with MCPServerAdapter
Use MCPServerAdapter as a context manager with SseServerParameters pointing to your Vinkius endpoint. The adapter automatically manages connection lifecycle.
3

Assign tools and run
Pass the returned mcp_tools to your agent's tools parameter. The adapter converts MCP tools to native BaseTool objects compatible with all CrewAI agents.

crew.py

from crewai import Agent, Task, Crew
from crewai_tools import MCPServerAdapter
from mcp import SseServerParameters

server_params = SseServerParameters(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

with MCPServerAdapter(server_params) as mcp_tools:
    agent = Agent(
        role="CERN Open Data Analyst",
        goal="Access and analyze CERN Open Data data via MCP.",
        backstory="Expert analyst with direct CERN Open Data access.",
        tools=mcp_tools,
    )

    task = Task(
        description="List recent CERN Open Data transactions",
        agent=agent,
        expected_output="A summary of recent activity",
    )

    crew = Crew(agents=[agent], tasks=[task])
    result = crew.kickoff()
    print(result)

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 CrewAI

You can pass the Vinkius endpoint URL directly in the agent's `mcps` array. This gives agents like your data analyst instant access to tools like `search_by_experiment` without manual Python coding.

Yes, your research crew can use sequential execution. One agent extracts DOIs from a paper, and a second agent uses `get_record_by_doi` to fetch the corresponding dataset metadata from the open data portal.

Use the `MCPServerHTTP` class from `crewai.mcp` and apply a `tool_filter`. You can restrict your glossary agent to only use `get_glossary` while giving your data agent access to `search_datasets`.

The agent uses `list_record_files` to fetch the file details. Since the MCP Server runs on Vinkius, the response is handled efficiently, allowing the agent to parse the ROOT file URIs without crashing your local Python environment.

Every connection to the MCP Server goes through an isolated Vinkius V8 sandbox. This zero-trust setup ensures that your agent's search parameters, file lists, and analytical queries remain private and protected from external access.

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