This bootcamp introduces developers to the foundations of building AI agents that can interact with external tools, data sources, and services. Participants will learn how to leverage NVIDIA® NIM™ microservices for accelerated inference, implement the Model Context Protocol (MCP) for standardized AI-to-tool communication, and orchestrate agentic workflows using LangGraph followed by a Challenge.
This content contains 4 Labs, plus a challenge:
- Lab 1: Using NVIDIA NIM via Cloud and Local Endpoints
- Lab 2: Introduction to Model Context Protocol (MCP)
- Lab 3: Low-Level MCP Server Implementation
- Lab 4: Building Agentic Workflows with LangGraph
- Lab 5: Challenge
The tools and frameworks used in this bootcamp are as follows
The duration of the tutorial is 2 hours.
The duration of the challenge is 4 hours.
Basic experience with Python programming is required for this bootcamp. Familiarity with fundamental concepts of Large Language Models (LLMs) and generative AI is recommended but not mandatory. Experience working with APIs (such as REST APIs) will be helpful. No prior experience with agentic AI frameworks is required.
This material originates from the OpenHackathons Github repository. Check out additional materials here.
Don't forget to check out additional Open Hackathons Resources and join our OpenACC and Hackathons Slack Channel to share your experience and get more help from the community.
Copyright © 2026 OpenACC-Standard.org. This material is released by OpenACC-Standard.org, in collaboration with NVIDIA Corporation, under the Creative Commons Attribution 4.0 International (CC BY 4.0). These materials may include references to hardware and software developed by other entities; all applicable licensing and copyrights apply.