Byte Size15min
MCP at the LHC: Coordinating the World’s Largest Machine
A prototype Model Context Protocol (MCP) server was developed to help CERN’s LHC coordinators plan and analyze maintenance schedules. By linking scheduling tools with a language model, it enables natural‑language interaction, automatic conflict detection, and validation—demonstrating how AI can streamline complex, high‑stakes coordination workflows.
Georg ŠumailovCERN
talkDetail.whenAndWhere
Tuesday, February 10, 12:55-13:10
Room C
talks.roomOccupancytalks.noOccupancyInfo
At CERN’s Large Hadron Collider (LHC), every minute of downtime is precious. During technical stops, hundreds of specialists perform maintenance and upgrades before physics runs resume. Coordinating these interventions requires precise, conflict-free scheduling - a complex and time-critical process.
During the AI for Scientific Writing and Coding Assistants Hackathon, we built a prototype Model Context Protocol (MCP) server to assist LHC coordinators in planning and analyzing linear schedules. The system bridges the LHC scheduling tools’ APIs with a CERN-hosted large language model, enabling coordinators to interact with complex planning data in plain English. Through this interface, the MCP can perform automatic analyses such as detecting potential conflicts, validating resource and timing constraints, and gathering contextual information about interventions.
By combining structured scheduling data with natural language understanding, the prototype demonstrates how AI-assisted tools can enhance situational awareness and streamline planning quality checks. This talk explores the motivation, design, and lessons learned from integrating MCP with existing LHC workflows - showcasing how lightweight AI infrastructure can empower experts to coordinate maintenance and upgrades in one of the world’s most complex scientific machines.
During the AI for Scientific Writing and Coding Assistants Hackathon, we built a prototype Model Context Protocol (MCP) server to assist LHC coordinators in planning and analyzing linear schedules. The system bridges the LHC scheduling tools’ APIs with a CERN-hosted large language model, enabling coordinators to interact with complex planning data in plain English. Through this interface, the MCP can perform automatic analyses such as detecting potential conflicts, validating resource and timing constraints, and gathering contextual information about interventions.
By combining structured scheduling data with natural language understanding, the prototype demonstrates how AI-assisted tools can enhance situational awareness and streamline planning quality checks. This talk explores the motivation, design, and lessons learned from integrating MCP with existing LHC workflows - showcasing how lightweight AI infrastructure can empower experts to coordinate maintenance and upgrades in one of the world’s most complex scientific machines.
Georg Šumailov
Georg is a Software Engineer at the European Organization for Nuclear Research (CERN), primarily focused on developing an in-house Google Street View analogue that allows virtual visits to the accelerator complex, even while it is operating. In addition, he works part-time on the Scheduling Tools application, which helps LHC coordinators plan interventions in the machine. Before joining CERN, Georg developed core digital healthcare information systems for the Government of Estonia.
talkDetail.shareFeedback
talkDetail.feedbackNotYetAvailable
talkDetail.feedbackAvailableAfterStart
talkDetail.signInRequired
talkDetail.signInToFeedbackDescription
occupancy.title
occupancy.votingNotYetAvailable
occupancy.votingAvailableBeforeStart
talkDetail.signInRequired
occupancy.signInToVoteDescription
comments.speakerNotEnabledComments