<?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 Sigasi</title><link>https://www.sigasi.com/tags/mcp/</link><description>Recent content in MCP on Sigasi</description><generator>Hugo</generator><language>en</language><lastBuildDate>Tue, 28 Jul 2026 00:00:00 +0000</lastBuildDate><atom:link href="https://www.sigasi.com/tags/mcp/index.xml" rel="self" type="application/rss+xml"/><item><title>Fixing Dependencies with Sigasi MCP</title><link>https://www.sigasi.com/screencasts/fixing_dependencies/</link><pubDate>Tue, 28 Jul 2026 00:00:00 +0000</pubDate><guid>https://www.sigasi.com/screencasts/fixing_dependencies/</guid><description>&lt;h2 
 class="uk-heading-large" 
 id="modular-project-setup"&gt;
 &lt;a
 href="https://www.sigasi.com/screencasts/fixing_dependencies/#modular-project-setup"
 class="uk-link-reset"
 aria-label="Link to this section: Modular Project Setup"&gt;
 Modular Project Setup
 &lt;/a&gt;
&lt;/h2&gt;
&lt;p&gt;Before talking about dependencies, we need to talk about project setup. Sigasi Visual HDL is not a single-file editor. It considers the project as a whole and performs real-time analysis using project context to provide accurate results. That&amp;rsquo;s why a project description is required.&lt;/p&gt;</description></item><item><title>Iterative HDL Generation with Sigasi MCP</title><link>https://www.sigasi.com/screencasts/iterative_hdl_generation/</link><pubDate>Tue, 28 Jul 2026 00:00:00 +0000</pubDate><guid>https://www.sigasi.com/screencasts/iterative_hdl_generation/</guid><description>&lt;h1 
 
 id="agents--mcp-in-sigasi-visual-hdl"&gt;
 &lt;a
 href="https://www.sigasi.com/screencasts/iterative_hdl_generation/#agents--mcp-in-sigasi-visual-hdl"
 class="uk-link-reset"
 aria-label="Link to this section: Agents &amp;amp; MCP in Sigasi Visual HDL"&gt;
 Agents &amp;amp; MCP in Sigasi Visual HDL
 &lt;/a&gt;
&lt;/h1&gt;
&lt;p&gt;AI tools started with chat assistants and code completion, but agents take things a step further. Instead of generating a single response, an agent can work towards a goal. It can plan tasks, execute actions, evaluate results, and decide what to do next. This is particularly interesting for HDL development because designs go through multiple cycles of analysis, validation, and refinement before they are ready. An AI agent can participate in that loop by reading files, invoking tools, analyzing outputs, and iterating until the objective is achieved. The key takeaway is that agents are not just generating code. They can support the entire RTL workflow, from implementation to verification and debugging.&lt;/p&gt;</description></item></channel></rss>