<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Model Context Protocol (MCP) on DATATWEETS</title><link>https://datatweets.com/courses/generative-ai/model-context-protocol/</link><description>Recent content in Model Context Protocol (MCP) on DATATWEETS</description><generator>Hugo</generator><language>en</language><copyright>Copyright (c) 2025 Datatweets</copyright><lastBuildDate>Sat, 27 Jun 2026 09:00:00 +0200</lastBuildDate><atom:link href="https://datatweets.com/courses/generative-ai/model-context-protocol/index.xml" rel="self" type="application/rss+xml"/><item><title>Lesson 1 - What MCP Is and Why It Matters</title><link>https://datatweets.com/courses/generative-ai/model-context-protocol/lesson-1-what-mcp-is/</link><pubDate>Fri, 14 Nov 2025 09:00:00 +0200</pubDate><guid>https://datatweets.com/courses/generative-ai/model-context-protocol/lesson-1-what-mcp-is/</guid><description>MCP is &amp;lsquo;USB-C for AI tools&amp;rsquo;: one protocol so a tool you build once works in any AI app. Learn the architecture — hosts, clients, and servers exposing tools, resources, and prompts.</description></item><item><title>Lesson 2 - Connecting to MCP Servers</title><link>https://datatweets.com/courses/generative-ai/model-context-protocol/lesson-2-connecting-to-mcp-servers/</link><pubDate>Fri, 14 Nov 2025 09:00:00 +0200</pubDate><guid>https://datatweets.com/courses/generative-ai/model-context-protocol/lesson-2-connecting-to-mcp-servers/</guid><description>Build a real MCP client step by step with the Python SDK — StdioServerParameters, the session handshake, list_tools discovery, and call_tool. Then see the Anthropic MCP connector for remote servers.</description></item><item><title>Lesson 3 - Building Tools Over MCP</title><link>https://datatweets.com/courses/generative-ai/model-context-protocol/lesson-3-building-tools-over-mcp/</link><pubDate>Fri, 14 Nov 2025 09:00:00 +0200</pubDate><guid>https://datatweets.com/courses/generative-ai/model-context-protocol/lesson-3-building-tools-over-mcp/</guid><description>Turn plain Python functions into MCP tools with the @mcp.tool() decorator, serve them over stdio, then convert the discovered tools into Anthropic tool definitions so Claude can call them — one server for every host.</description></item><item><title>Lesson 4 - Guided Project: Connect Claude to an MCP Service</title><link>https://datatweets.com/courses/generative-ai/model-context-protocol/lesson-4-guided-project-mcp-integration/</link><pubDate>Fri, 14 Nov 2025 09:00:00 +0200</pubDate><guid>https://datatweets.com/courses/generative-ai/model-context-protocol/lesson-4-guided-project-mcp-integration/</guid><description>The module capstone: write a FastMCP task-tracker server with an in-memory store and tools, connect a client, build the Claude bridge that converts MCP tools to Anthropic tool defs, and watch Claude add a task then list tasks by chaining MCP tool calls — exactly how production AI apps plug into real systems.</description></item></channel></rss>