<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Hcp-Terraform on Danilo Falcão da Silva</title><link>https://falcao.org/tags/hcp-terraform/</link><description>Recent content in Hcp-Terraform on Danilo Falcão da Silva</description><generator>Hugo</generator><language>en-us</language><lastBuildDate>Sun, 19 Jul 2026 17:15:00 -0300</lastBuildDate><atom:link href="https://falcao.org/tags/hcp-terraform/index.xml" rel="self" type="application/rss+xml"/><item><title>Terraform MCP Is Useful. Apply Access Is a Different Decision.</title><link>https://falcao.org/posts/terraform-mcp-apply-access-different-decision/</link><pubDate>Sun, 19 Jul 2026 17:15:00 -0300</pubDate><guid>https://falcao.org/posts/terraform-mcp-apply-access-different-decision/</guid><description>&lt;p>Infrastructure agents rarely fail because the model cannot write HCL.
They fail because they write HCL against a provider schema they
half-remember from training data, invent a module that does not exist,
or reason confidently about a workspace they have never seen. That is a
context problem, and the Terraform MCP server is a real fix for it.&lt;/p>
&lt;p>My concern is the packaging. &amp;ldquo;The agent can read current provider
documentation&amp;rdquo; and &amp;ldquo;the agent can act on Terraform runs&amp;rdquo; ship in the
same server, behind the same install step, and a lot of teams are going
to turn both on with one checkbox because the README made it easy.&lt;/p></description></item></channel></rss>