<rss xmlns:atom="http://www.w3.org/2005/Atom" version="2.0"><channel><title>MCP - 标签 - HAKULA†CHANNEL</title><link>https://hakula.xyz/tags/mcp/</link><description>MCP - 标签 - HAKULA†CHANNEL</description><generator>Hugo -- gohugo.io</generator><language>zh-CN</language><managingEditor>i@hakula.xyz (Hakula)</managingEditor><webMaster>i@hakula.xyz (Hakula)</webMaster><lastBuildDate>Fri, 13 Mar 2026 17:36:00 +0800</lastBuildDate><atom:link href="https://hakula.xyz/tags/mcp/" rel="self" type="application/rss+xml"/><item><title>MCP Server Guide: Building a Documentation Server for LLM Agents</title><link>https://hakula.xyz/posts/tutorial/llm-intro/mcp-server-guide/</link><pubDate>Fri, 13 Mar 2026 17:36:00 +0800</pubDate><author>Hakula</author><guid>https://hakula.xyz/posts/tutorial/llm-intro/mcp-server-guide/</guid><description><![CDATA[<div class="featured-image">
                <img src="https://hakula-1257872502.file.myqcloud.com/images/3/article-covers/21256a36-9d48-4447-862f-2ea8c59b8e39_129339284.webp" referrerpolicy="no-referrer">
            </div><p>A practical, end-to-end guide to building a custom MCP server that turns your documentation site into structured tools for LLM agents. Covers the llms.txt standard, FastMCP, caching, search, packaging, and LLM agents integration. Written for teams that have internal docs (Confluence pages, Markdown files) and want their agents to read them instead of hallucinating.</p>]]></description></item><item><title>LLM Intro: From the Basics to Context Engineering (Part 1)</title><link>https://hakula.xyz/posts/tutorial/llm-intro/part-1/</link><pubDate>Fri, 13 Mar 2026 15:25:00 +0800</pubDate><author>Hakula</author><guid>https://hakula.xyz/posts/tutorial/llm-intro/part-1/</guid><description><![CDATA[<div class="featured-image">
                <img src="https://hakula-1257872502.file.myqcloud.com/images/3/article-covers/7a0fae46-7783-4156-b223-ebf72d081e80_136849830.webp" referrerpolicy="no-referrer">
            </div><p>A practical guide to LLM agents, from foundational concepts to building a production-ready agent configuration. Part 1 of a two-part series: what an LLM actually is, how it becomes an agent, and the layered system (CLAUDE.md, hooks, MCP, skills, plugins) that makes it useful in practice. Part 2 covers subagents, agent teams, and more advanced topics. Written for everyone, regardless of technical background.</p>]]></description></item></channel></rss>