Dr. Luca Di Grazia
luca.digrazia@unisg.ch
0000-0002-5306-8645
luca-digrazia
https://www.lucadigrazia.com

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

I am a Great Minds Fellow at the University of St. Gallen in the Programming Group. My research focuses on AI for Programming to improve software quality. Previously, I was a postdoc at the Università della Svizzera Italiana (USI), advised by Prof. Mauro Pezzè. I earned my PhD (summa cum laude) at the University of Stuttgart, advised by Prof. Michael Pradel, with the thesis “Supporting Software Evolution via Search and Prediction”.

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.