<rss xmlns:atom="http://www.w3.org/2005/Atom" version="2.0"><channel><title>Integrations - Category - EONYX Blog</title><link>https://eonyx.tech/blog/categories/integrations/</link><description>Integrations - Category - EONYX Blog</description><generator>Hugo -- gohugo.io</generator><language>en</language><managingEditor>eonyx.tech@proton.me (EONYX)</managingEditor><webMaster>eonyx.tech@proton.me (EONYX)</webMaster><copyright>This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.</copyright><lastBuildDate>Tue, 30 Jun 2026 00:00:00 +0300</lastBuildDate><atom:link href="https://eonyx.tech/blog/categories/integrations/" rel="self" type="application/rss+xml"/><item><title>EONYX and MCP: connecting external tools</title><link>https://eonyx.tech/blog/eonyx-mcp/</link><pubDate>Tue, 30 Jun 2026 00:00:00 +0300</pubDate><author><name>EONYX</name></author><guid>https://eonyx.tech/blog/eonyx-mcp/</guid><description><![CDATA[<div class="featured-image">
                <img src="/blog/eonyx-mcp/cover.svg" referrerpolicy="no-referrer">
            </div><p><strong>Model Context Protocol (MCP)</strong> is an open standard through which an agent gains access to external systems: databases, APIs, issue trackers and any other services. EONYX has a built-in MCP client based on the official Go SDK (<code>modelcontextprotocol/go-sdk</code>) — servers are described right in <code>eonyx.json</code> and their tools show up for the model alongside the built-in ones.</p>]]></description></item><item><title>EONYX Hooks: Automation Around Tool Calls</title><link>https://eonyx.tech/blog/eonyx-hooks/</link><pubDate>Wed, 03 Jun 2026 00:00:00 +0300</pubDate><author><name>EONYX</name></author><guid>https://eonyx.tech/blog/eonyx-hooks/</guid><description><![CDATA[<div class="featured-image">
                <img src="/blog/eonyx-hooks/cover.svg" referrerpolicy="no-referrer">
            </div><p><strong>Hooks</strong> are shell commands that EONYX runs <strong>around tool calls</strong>: before (<code>before</code>) and after (<code>after</code>). They are a convenient way to bolt on auto-formatting, auditing, checks and guardrails without touching the agent&rsquo;s code.</p>]]></description></item><item><title>EONYX Headless Mode: Running the Agent Without the TUI</title><link>https://eonyx.tech/blog/eonyx-headless/</link><pubDate>Tue, 19 May 2026 00:00:00 +0300</pubDate><author><name>EONYX</name></author><guid>https://eonyx.tech/blog/eonyx-headless/</guid><description><![CDATA[<div class="featured-image">
                <img src="/blog/eonyx-headless/cover.svg" referrerpolicy="no-referrer">
            </div><p>Besides the interactive TUI, EONYX can run <strong>headless</strong> — perform a task and exit. That is what you need for scripts, pipes and CI: predictable output, JSON events and meaningful exit codes.</p>]]></description></item><item><title>EONYX recipes: practical workflows</title><link>https://eonyx.tech/blog/eonyx-recipes/</link><pubDate>Mon, 18 May 2026 00:00:00 +0300</pubDate><author><name>EONYX</name></author><guid>https://eonyx.tech/blog/eonyx-recipes/</guid><description><![CDATA[<div class="featured-image">
                <img src="/blog/eonyx-recipes/cover.svg" referrerpolicy="no-referrer">
            </div><p>Features are nice, but it is more interesting to see them at work. A few practical scenarios: how to phrase the task and which EONYX techniques to turn on. The prompts are deliberately plain.</p>]]></description></item></channel></rss>