<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Search &amp; Web on Vibe Coding</title><link>https://vibecoding.rest/category/search--web/</link><description>Recent content in Search &amp; Web on Vibe Coding</description><generator>Hugo</generator><language>en</language><atom:link href="https://vibecoding.rest/category/search--web/index.xml" rel="self" type="application/rss+xml"/><item><title>Brave Search</title><link>https://vibecoding.rest/mcp-servers/brave-search/</link><pubDate>Mon, 01 Jan 0001 00:00:00 +0000</pubDate><guid>https://vibecoding.rest/mcp-servers/brave-search/</guid><description>&lt;p&gt;The Brave Search server gives an agent access to web and local search results through Brave&amp;rsquo;s Search API, without routing through another AI vendor&amp;rsquo;s index.&lt;/p&gt;&#10;&lt;h2 id="why-it-matters"&gt;Why it matters&lt;/h2&gt;&#10;&lt;p&gt;Models have a training cutoff and no innate awareness of anything after it. A search connector lets an agent verify current information — a library&amp;rsquo;s latest version, a recent API change, a live status — instead of confidently guessing from stale training data.&lt;/p&gt;</description></item><item><title>Fetch</title><link>https://vibecoding.rest/mcp-servers/fetch/</link><pubDate>Mon, 01 Jan 0001 00:00:00 +0000</pubDate><guid>https://vibecoding.rest/mcp-servers/fetch/</guid><description>&lt;p&gt;The Fetch server retrieves a given URL and converts its HTML into clean markdown sized for an LLM context window, with a start-index parameter so an agent can page through long documents in chunks. It&amp;rsquo;s one of the official reference servers in the modelcontextprotocol/servers repo.&lt;/p&gt;</description></item></channel></rss>