MSc Christoph Bühler
christoph.buehler@unisg.ch
christoph-bühler-a3a262270
0000-0002-2224-1687
buehler

School of Computer Science
Torstrasse 25
9000 St. Gallen, Switzerland

I joined the Programming Group as a Research Assistant in July 2024. My Master Thesis of the university of applied science OST (former HSR) resolved around identity security and authentication in heterogenuous systems. I finished the MCS program in spring 2026 and enrolled as a PhD student in April 2026. My research interest center around the security of AI and AI agentic systems.

Publications

1. FSE
   

   AgentBound: Securing Execution Boundaries of AI Agents

   Christoph Bühler, Matteo Biagiola, Luca Di Grazia, Guido Salvaneschi

   In Proceedings of the 34th ACM Joint European Software Engineering Conference and Symposium on the Foundations of Software Engineering (FSE), 2026

   Abstract PDF Supp

   Large Language Models (LLMs) have evolved into AI agents that interact with external tools and environments to perform complex tasks. The Model Context Protocol (MCP) has become the de facto standard for connecting agents with such resources, but security has lagged behind: thousands of MCP servers execute with unrestricted access to host systems, creating a broad attack surface. In this paper, we introduce AgentBound, the first access control framework for MCP servers. AgentBound combines a declarative policy mechanism, inspired by the Android permission model, with a policy enforcement engine that contains malicious behavior without requiring MCP server modifications. We build a dataset containing the 296 most popular MCP servers, and show that access control policies can be generated automatically from source code with 80.9% accuracy. We also show that AgentBound blocks the majority of security threats in several malicious MCP servers, and that policy enforcement engine introduces negligible overhead. Our contributions provide developers and project managers with a practical foundation for securing MCP servers while maintaining productivity, enabling researchers and tool builders to explore new directions for declarative access control and MCP security.

2. CAPE - European Open Compute Architecture for Powerful Edge

   Martin Kaiser, Lennart Tigges, Jens Hagemeyer, Christian Klarhorst, Björn Voß, Fred Buining, Bola Fakhoury, János Lazányi, René Griessl, Muhammad Shahzad, Yiannis Georgiou, Salim Mimouni, Pedro Velho, Michael Mercier, Eva Trungel, Julian Gajewski, Stefan Krupop, Michavor Dem Berge, Deepak M. Mathew, Skipis Dimitrios, Arnidis Iordanis, Orestis Vantzos, David Georgantas, Gautier Rouaze, Christoph Bühler, Guido Salvaneschi, Brandon Lewis, Angela Hauber

   In 2025 28th Euromicro Conference on Digital System Design (DSD), 2025

   Abstract PDF

   CAPE is a European-funded project targeting to reshape edge-cloud computing by defining edge micro data centers as a new unit of computing. Fully committing to open source, CAPE develops a fully Composable Infrastructure (CI) for high-performance edge server hardware platforms grounded in open, forward-looking standards. Together with an open-source software stack covering the Edge-Cloud Continuum, this holistic approach boosts power and energy efficiency while reducing resource overprovisioning. Completely based on open standards, CAPE strengthens the digital sovereignty Europe needs in a challenging future. This work gives an overview of the current architectural blueprint of the project, focusing on integrating game-changing technologies like Compute Express Link (CXL) for compute and memory disaggregation, pushing open source cluster management, and AI-assisted deployment software stacks using Infrastructure from Code (IfC). The proposed approaches and benefits for future Edge-Cloud data centers are demonstrated within three use cases, ranging from Smart Grid and Edge-AI to Satellite Data Processing.

3. MSR
   

   TerraDS: A Dataset for Terraform HCL Programs

   Christoph Bühler, David Spielmann, Roland Meier, Guido Salvaneschi

   In Proceedings of the IEEE/ACM 22nd International Conference on Mining Software Repositories, MSR, 2025

   Abstract PDF

   Infrastructure as Code (IaC) aims to automate infrastructure management by enabling the definition of infrastructure configurations in programs, rather than manually configuring hardware or cloud resources. Terraform is one of the most widely used IaC tools, gaining significant traction in recent years, as highlighted by its large and active user community and widespread adoption in both open-source and enterprise environments. Terraform’s code is written in the HashiCorp Configuration Language (HCL), which defines the infrastructure in a declarative manner. Despite the widespread adoption of Terraform, there is no large-scale dataset available for researchers to study IaC Terraform programs systematically. To address this gap, we present TerraDS, the first dataset of publicly available Terraform programs written in HCL. TerraDS contains the HCL code and the metadata of 67,360 open source repositories with permissive open-source licenses. The dataset includes 279,344 Terraform modules with 1,773,991 registered resources, all compiled into a reusable archive ( 335 MB).