2025-09-14 –, Ballroom 1
Providing the right context to large language models is challenging. Every integration—whether accessing local files, connecting to Google Calendar, or querying internal databases—requires custom work. Each tool connection becomes a separate, manual effort. This is where MCP comes in. Model Context Protocol (MCP), in simple terms, is a universal adapter for AI models that need external context. It standardizes how context is passed to models, making it easier to build and manage these connections.
My talk will not only focus on how to get started with MCP, but I will also outline how to build MCP Agents using your own MCP Server tools and the MCP Client UI with Streamlit. At the end of my talk, we will also discuss the security issues associated with MCP and how one can mitigrate those.
Outline of my talk- breakdown of the 30 minutes:
- Issues with Large language models and discuss the pain points for the need of MCP (3 min)
- What is MCP in basic words (2 min)
- How does MCP work?- Architecture breakdown? (5 min)
- Need of MCP - Is it overhyped? Share the experience of working with MCP (5 min)
- Use MCP as a tool in the Agentic Workflow (4-5 minutes)
- Security concerns and Migration (5-6 minutes)
- Show a simple code snippet in the end on how to use MCP and Agno Agent (5 min)
- QA (2 min)
Tarun Jain is a Super Agent at AI Planet and is recognized as a Google Developer Expert in AI. He enjoys contributing to open-source projects and maintains two repositories: OpenAGI, for building AI Agents, and BeyondLLM, for quick experimenting, evaluating, and observing RAG pipelines. Tarun also contributed to Google Summer of Code 2024 at Red Hen Lab and Google Summer of Code 2023 at caMicroscope. He is a content creator with over 3500+ subscribers for his channel AI with Tarun.
Previous Experience:
- Speaker at PyCon Hong Kong 2024
- Speaker at PyCon Malaysia 2024
- Speaker at PyCon APAC - Indonesia 2024
- Speaker at PyCon Singapore - 2025