I made a small MCP server for OpenAI’s Ads API

<!-- SC_OFF --><div class="md"><p>Built a Rust CLI that auto-discovers subcommands and flags from any command-line tool's <code>--help</code> and exposes them as MCP tools. Your

<!-- SC_OFF --><div class="md"><p>Been heads down building graphify since April 5th. The idea: instead of stuffing your entire codebase into context every session, build a

<!-- SC_OFF --><div class="md"><p>The basic idea is simple: if you have an OpenAPI REST API, it makes it useable by AI agents with a single command without writing a MCP server

<!-- SC_OFF --><div class="md"><p><a href="https://github.com/SomeoneAlt-86/open-mythos">https://github.com/SomeoneAlt-86/open-mythos</a><br /> Claude just previewed their Mythos

<!-- SC_OFF --><div class="md"><p>Just putting together a quick list of the new <strong>open-source physical AI / robotics models</strong> from <strong>NVIDIA GTC

<!-- SC_OFF --><div class="md"><p>Anthropic just pushed out <strong>Claude Opus 4.7</strong> and it’s live right now on <a href="http://claude.ai">claude.ai</a>, the Platform, and

<!-- SC_OFF --><div class="md"><p>Most of my LLM cost was on the wrong tier of work.</p> <p>Classification, extraction, JSON formatting, summarization I'm going to review anyway.

<p>REST APIs gave humans (and the code they wrote) a standardized way to access software over the network.</p> <p>MCP is trying to do the same thing for agents.</p> <p>That simple