February 24-26, 2027
Montreal, Canada
Code Execution with MCP: Production Architecture Case Study
Building AI agents on top of REST APIs sounds straightforward: turn each endpoint into an MCP tool. But as APIs grow, tool definitions and responses crowd the model's context. MCP as Code offers another way: let agents discover APIs, write code to call them, and filter results before they reach the model. This case study explores how semantic search and sandboxed execution make that work, and where the approach helps or adds complexity.
Pavel Makhov
Lightspeed Commerce
Pavel is a Staff Software Developer and open-source enthusiast with over a decade of experience, primarily in Java. Beginning his career at the birthplace of the World Wide Web, CERN in Switzerland, Pavel has since worked in various companies, gaining expertise across a wide range of technologies. His interests span Linux, macOS/iOS development, and open source, reflecting his passion for exploring and mastering diverse technological landscapes.
