Local MCP Servers for Cursor (Step by step)

In this video, you'll learn how to create a custom MCP (Model Context Protocol) server in Python, mock-integrate it with Confluence, and expose custom tools to the Cursor code editor. The tutorial walks you through understanding MCP, setting up your environment, implementing and describing your tools, testing connectivity, and configuring the integration for live use. By following along, you'll be able to empower Cursor or your AI assistant with up-to-date project data pulled from Confluence (or your own backend), even if your workspace is empty. ## Links - 👉 Code from the video: https://github.com/alejandro-ao/mcp-for-vs-code - 🚀 Complete AI Engineer Bootcamp: https://aibootcamp.dev - ❤️ Buy me a coffee... or a beer (thanks): https://link.alejandro-ao.com/l83gNq - 💬 Join the Discord Help Server: https://link.alejandro-ao.com/HrFKZn - ✉️ Get the news from the channel and AI Engineering: https://link.alejandro-ao.com/AIIguB ## Timestamps 0:00:00 - Intro 0:00:59 - What is MCP? 0:02:45 - Connect to An Existing MCP Server 0:06:00 - Project Setup 0:07:31 - Create Functions 0:11:19 - From Functions to MCP Tools 0:14:21 - Debug Inspector 0:16:08 - Add to Cursor 0:18:42 - Testing out MCP