Jan 16
Loading video player...
I'm delighted to introduce build AI apps
with MCP service working with Box Files
both in partnership with Box and taught
by Van Kus who is a CTO chief technology
officer at Box. In this course you
create an AI application that extracts
information from PDF invoices stored in
a Box folder using an MCP server.
Without MCP, building this type of
application would require that you write
custom code to connect your data to
external data sources and search the
files and download them and extract the
text before finally passing it to your
LM. With MCP, you can offload all these
tasks to an MCP server which can
automatically provide the LM tools such
as file search and text extraction. This
enables your application to seamlessly
interact with your external data sources
[music] and you can reuse the same
server across multiple AI applications.
Ben will show you how this works.
Thanks, Andrew. Every enterprise that I
talk to is interested in using MCP as a
way to build custom applications. Many
of these types of applications [music]
involve extracting structured data from
unstructured data. In this course,
you'll first go through your
do-it-yourself approach where you'll
have your AI application work with the
local files. Then you'll connect your
application to the Box MCP [music]
server instead, which will illustrate
the benefits of MCP approach,
dramatically simplifying future
complexity and scaling challenges.
Finally, you'll explore how you can
evolve your application into a multi-
aent system to support more complex
application logic. [music] When agents
are implemented independently, you'll
learn how to make them communicate
through ADA or agentto agent protocol
while still using the boxes or any other
MCP [music] server. The application you
work on in this course will be a good
example how to use MCB service in
multiple AI applications. I hope you
enjoy the course.
Learn more: https://bit.ly/47IEVUk Join Build AI Apps with MCP servers: Working with Box files, built in partnership with Box, and taught by Ben Kus, its Chief Technology Officer. You’ll begin with an AI application that processes files manually downloaded from a Box folder and locally stored. You’ll then refactor the application to make it MCP-compliant and connect it to the Box MCP server. The server will provide the application with the required tools to process the files directly in Box. You’ll finally evolve your solution into a multi-agent system that coordinates via the A2A protocol. MCP or Model Context Protocol standardizes how context, in terms of tools and resources, is provided to LLMs. Instead of writing custom code inside your application for file search, file downloads, and text extraction, you can offload these tasks to an MCP server. An MCP client within your application can communicate with the MCP server to discover the tools and send requests to execute a certain tool. In this course, you’ll use the Box MCP server and learn how to connect it to your application to process files from a Box folder. You’ll also build a multi-agent system using Google’s Agent Development Kit. The agents will use A2A to communicate with each other, and the Box MCP server to access file and text extraction tools. In detail, you’ll: - Build an LLM-powered invoice app that processes local PDF invoices to extract fields such as client name, total amount, and purchased product, and generates per-client reports. - Transform your application into an MCP-compliant app and use the tools of the Box MCP server to list the invoices within a Box folder and extract texts from each invoice, without manually downloading the files. - Move from a single agent to a multi-agent design: use an orchestrator to coordinate the tasks among sub-agents that use the Box MCP server and are specialized in files listing, text extraction, and reporting. - Design the orchestrator and subagents as A2A servers, and use an A2A client to send the user's request to the orchestrator. By the end, you’ll know how to build an AI application and AI agents that use the MCP server to process Box content securely, without manual downloads, and that support several file types and scale better with the number of files. Enroll for free: https://bit.ly/47IEVUk