<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>MCP on Mark Kikta</title><link>https://mkikta.com/tags/mcp/</link><description>Recent content in MCP on Mark Kikta</description><generator>Hugo</generator><language>en-us</language><lastBuildDate>Fri, 17 Jul 2026 00:00:00 -0400</lastBuildDate><atom:link href="https://mkikta.com/tags/mcp/index.xml" rel="self" type="application/rss+xml"/><item><title>Designing an MCP Server for Unstructured Data</title><link>https://mkikta.com/posts/ariadne/</link><pubDate>Wed, 01 Jul 2026 00:00:00 -0400</pubDate><guid>https://mkikta.com/posts/ariadne/</guid><description>&lt;h2 id="introduction"&gt;
 Introduction
&lt;/h2&gt;
&lt;p&gt;Agents are most valuable when connected to your data. However, most data is unstructured: PDFs, Word documents, emails, etc. Unlike structured databases, unstructured documents cannot be queried directly. Agents often have to reread entire documents to recover context, wasting both time and tokens. And once your agent has read a document, that context is often local to your machine or even to that agent.&lt;/p&gt;
&lt;p&gt;🧶 &lt;a href="https://github.com/mkikta/ariadne"&gt;Ariadne&lt;/a&gt; processes unstructured documents into a searchable vector index and exposes them through a &lt;a href="https://modelcontextprotocol.io/docs/getting-started/intro"&gt;Model Context Protocol (MCP)&lt;/a&gt; server. This allows you to save tokens and share context between agents and teammates.&lt;/p&gt;</description></item></channel></rss>