Overview
This tutorial demonstrates how to implement the Model Context Protocol (MCP) to connect local AI models to external tools. Learn to build a complete AI-powered todo list manager by creating an MCP server, client, and Streamlit UI. Discover what MCP is and how it enables LLMs like Ollama to interact with external systems. Follow along with step-by-step instructions for configuring your application, implementing task management functionality, setting up the MCP server, connecting MCP tools to Langchain tools, creating an AI agent, and developing a user interface. The 38-minute video includes access to a full-text tutorial with source code (requires MLExpert Pro) and covers everything from basic MCP concepts to running the completed application. Perfect for developers looking to enhance their AI agents with tool-using capabilities.
Syllabus
00:00 - Welcome
00:41 - Full-text tutorial and source code on MLExpert.io
01:14 - What is MCP?
13:22 - Learning MCP
13:53 - Build a simple MCP server and client
22:23 - App configuration Ollama, LLMs
23:08 - Task management
24:11 - MCP server
25:24 - Connect MCP tools to Langchain tools
29:55 - AI agent
33:24 - Streamlit UI
36:01 - Run the app
37:40 - Conclusion
Taught by
Venelin Valkov