<?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 NicoLabs</title>
		<link>http://blog.hellonico.info/tags/mcp/</link>
		<description>Recent content in Mcp on NicoLabs</description>
		<generator>Hugo</generator>
		<language>en</language>
		
		
		
		
			<lastBuildDate>Wed, 29 Jul 2026 10:00:00 +0900</lastBuildDate>
		
			<atom:link href="http://blog.hellonico.info/tags/mcp/index.xml" rel="self" type="application/rss+xml" />
			<item>
				<title>Introducing the Coni Introspection Agent &amp; MCP Server</title>
				<link>http://blog.hellonico.info/posts/coni/agent-introspection-mcp/</link>
				<pubDate>Wed, 29 Jul 2026 10:00:00 +0900</pubDate>
				<guid>http://blog.hellonico.info/posts/coni/agent-introspection-mcp/</guid>
				<description>&lt;p&gt;Imagine sitting in your REPL, writing code, and suddenly forgetting how a standard library function works. Or maybe you need a quick algorithmic implementation, but you don&amp;rsquo;t want to switch context to a browser or a separate AI chat window.&lt;/p&gt;&#xA;&lt;p&gt;What if your programming language &lt;em&gt;itself&lt;/em&gt; could introspect its own codebase, write code for you, and evaluate it live in your REPL memory?&lt;/p&gt;&#xA;&lt;p&gt;Today, we&amp;rsquo;re thrilled to introduce the &lt;strong&gt;Coni Introspection Agent&lt;/strong&gt;—a natively integrated, tool-calling LLM agent built directly into the Coni language ecosystem. And because we know developers love their modern IDEs, we&amp;rsquo;ve also packaged it with a native &lt;strong&gt;Model Context Protocol (MCP)&lt;/strong&gt; server.&lt;/p&gt;</description>
			</item>
			<item>
				<title>Building a Zero-Dependency MCP Client &amp; Server Natively in Coni</title>
				<link>http://blog.hellonico.info/posts/coni/native-mcp/</link>
				<pubDate>Mon, 27 Jul 2026 19:50:00 +0900</pubDate>
				<guid>http://blog.hellonico.info/posts/coni/native-mcp/</guid>
				<description>&lt;p&gt;The &lt;strong&gt;Model Context Protocol (MCP)&lt;/strong&gt; is rapidly becoming the gold standard for connecting Large Language Models to external tools and data sources. Historically, if you wanted to build an MCP client or server, you needed to reach for heavy, bloated SDKs in Node.js or Python, dealing with complex asynchronous state and dependency hell.&lt;/p&gt;&#xA;&lt;p&gt;We thought: &lt;em&gt;What if we could do it entirely natively in Coni?&lt;/em&gt;&lt;/p&gt;&#xA;&lt;p&gt;In this post, we’re going to walk through how we brought a complete, zero-dependency MCP Client and Server directly into the Coni standard library (&lt;code&gt;mcp.coni&lt;/code&gt;). It’s fast, highly concurrent, and ridiculously easy to use.&lt;/p&gt;</description>
			</item>
	</channel>
</rss>
