<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Integration on Le Site de François</title><link>https://lesitedefrancois.be/en/tags/integration/</link><description>Recent content in Integration on Le Site de François</description><generator>Hugo -- gohugo.io</generator><language>en</language><copyright>© 2026 François</copyright><atom:link href="https://lesitedefrancois.be/en/tags/integration/index.xml" rel="self" type="application/rss+xml"/><item><title>MCP (Model Context Protocol)</title><link>https://lesitedefrancois.be/en/ai/mcp/</link><pubDate>Mon, 01 Jan 0001 00:00:00 +0000</pubDate><guid>https://lesitedefrancois.be/en/ai/mcp/</guid><description>&lt;p&gt;&lt;strong&gt;MCP (Model Context Protocol)&lt;/strong&gt; is an open standard for how &lt;strong&gt;LLM applications&lt;/strong&gt; discover and invoke &lt;strong&gt;tools&lt;/strong&gt;, read structured &lt;strong&gt;resources&lt;/strong&gt;, and exchange &lt;strong&gt;prompts&lt;/strong&gt; with external systems through MCP &lt;strong&gt;servers&lt;/strong&gt; and &lt;strong&gt;clients&lt;/strong&gt;. The objective is interchangeable integrations: instead of every chat product implementing bespoke plugins for Git, databases, or ticketing, a tool provider ships an MCP server and any compatible client (IDE, assistant, agent runtime) can use it with consistent auth and capability negotiation. MCP complements HTTP &lt;strong&gt;inference&lt;/strong&gt; APIs—it sits at the orchestration layer where the model decides which tool to call, not inside &lt;strong&gt;vLLM&lt;/strong&gt;’s token loop. It is widely associated with &lt;strong&gt;agentic&lt;/strong&gt; workflows (multi-step plans, code execution, retrieval).&lt;/p&gt;</description></item></channel></rss>