Get exclusive access to AI resources and project ideas: https://the-data-entrepreneurs.kit.com/shaw
This is the 5th video in a series on AI agents. Here, I discuss the model context protocol (MCP), then show how to build a custom MCP server with Python and connect it to Claude Desktop.
📰 Blog: https://medium.com/data-science-collective/model-context-protocol-mcp-explained-ef5c33c5fe05?sk=58f5c33b68915a28fd2aaf7575564926
💻 Code: https://github.com/ShawhinT/YouTube-Blog/tree/main/agents
References
[1] https://modelcontextprotocol.io/introduction
[2] https://github.com/cyanheads/model-context-protocol-resources/blob/main/guides/mcp-client-development-guide.md#1-introduction-to-mcp-clients
[3] https://github.com/modelcontextprotocol/python-sdk
[4] https://docs.astral.sh/uv/
Intro - 0:00
What is MCP? - 0:19
How MCP works - 2:35
MCP Client - 3:54
MCP Server - 5:43
Example: MCP Server with Python - 8:00
Connecting to Claude Desktop - 15:40
Homepage: https://www.shawhintalebi.com