Thank you for the overwhelming response. This workshop is overbooked! Registrations are closed for in-person attendance.
The workshop will be live streamed. Stream links will be shared with 2025 edition ticket holders and annual members on the day before the workshop.
The rise of the Model-Context Protocol (MCP) has made it is possible to expose your backend services as tools which AI assistants such as Claude can directly invoke. MCP bridges the gap between natural language and your actual systems. For e.g., HubSpot’s MCP enables users to manage CRM contacts and deals directly through AI conversations; Atlassian’s MCP enables customers to view assigned tasks, create issues, and update project status right from their LLM interface.
In this hands-on workshop, participants will explore how to bring this capability to their own systems. Participants will learn how to build a lightweight MCP server in Python that wraps your existing REST APIs, turning them into tools that AI assistants can use. By the end of the workshop, participants will be equipped to empower users to interact with their systems through natural language query.
- This workshop is of 2.5 hours duration.
- This is a beginner-friendly workshop.
- This is an in-person and hands-on workshop.
- Only 40 seats are open for workshop participation.
- Live stream will be available for The Fifth Elephant members to participate remotely.
- Code & materials can be accessed on Github
- Introduction to what is MCP, why it matters and how MCPs came to be in the AI ecosystem
- Leveraging MCP in daily workflows; explore existing MCP integrations (Atlassian, HubSpot, etc.) and how they transform user experiences
- Hands-on: GitHub MCP demo on Claude desktop to showcase real-world MCP capabilities
- Building MCPs: architecture & design such as explanation of the MCP server architecture, client-server communication via different transports, components and design principles with diagrams
- What are we building? Introduction to demo REST APIs, demo project, and endpoints which will expose as MCP tools
- Break/Q&A - for questions, troubleshooting, and environment issues
- Build MCP servers - code MCP tools with public/private endpoints; use MCP debugger for testing; and integrate with Claude Desktop
- Live demonstration of the complete MCP server; discuss best practices, production considerations, and resources for further learning
- Python 3.8+ installed and verified (python --version)
- VS Code or Cursor IDE installed.
- Claude Desktop installed
- Docker Desktop installed
- Basic command line familiarity along with uv and venv for Python package management
- REST API and JSON knowledge helpful, but not required
- Engineers and builders working with internal backend services who want to plug LLMs into business actions.
- Product, ops, or AI platform teams exploring LLM integrations with enterprise systems such as CRM, support, billing, analytics.
- Anyone interested in making AI “actually useful” for real-world tasks - not just answering questions.
- Learn the key requirements to make your system compatible and ready for MCP integration.
- Get hands-on experience building a Python-based MCP server that wraps existing REST APIs.
- Understand best practices for tool schema design and choose the right architecture for scalable, effective MCP servers
Chaitanya Anand is a software development engineer at Atlan, working at the intersection of LLM integration, developer tooling, and business system orchestration. A seasoned hackathon veteran with 8 wins, he prototypes AI-assisted tools and experiments with early-stage protocols like MCP.
Shubhankar is a senior software engineer at Atlan, leading AI initiatives and experimenting with RAGs, AI agents, and MCP protocol to enhance data workflows. As a co-instructor, he brings hands-on experience in deploying AI solutions at scale and translating theory into practical applications.
This workshop is open for The Fifth Elephant members and for The Fifth Elephant 2025 annual conference ticket buyers
This workshop is open to 40 participants only. Seats will be available on first-come-first-serve basis. 🎟️
For inquiries about the workshop, contact +91-7676332020 or write to info@hasgeek.com