AI Agents & MCP Workshop | AI Builders Global Conference 2026 Archive

AI Builders Global Conference 2026. October 14-16, 2026. Online.

Building AI Agents with Tool Use, Function Calling & MCP

This description belongs to the 2026 topic catalog. The 2027 program is being prepared separately.

The Model Context Protocol (MCP) is becoming the USB-C of AI tool use: a standardized interface for agents to securely connect to enterprise data systems and applications. This workshop covers designing tool-using agents, MCP implementation from scratch, function calling patterns across different LLM providers, safety constraints and permissions, and building agents that interact with databases, APIs, file systems, and external services.

Questions explored in the 2026 topic catalog

What is MCP and how does it standardize agent-tool interaction?
How do you design effective function calling schemas?
What safety constraints prevent agents from taking destructive actions?
How do you handle authentication and authorization for tool-using agents?
What are the performance implications of complex tool chains?
How do you test and validate tool-using agent behavior?

Who this topic is for

Full-stack engineers, AI developers, and architects building agent systems that need to interact with external tools, APIs, and databases.

2026 attendee access and recordings

Your original pass and its entitlements remain associated with the 2026 edition. The recording page explains availability and access; a program listing is not a promise that a recording is ready.