i built maybe don't ai's mcp gateway——but to me the interesting technology isn't about the registry or flattening of downstream MCP servers (honestly that was a reasonably easy problem to solve) it's about the behavior of the AI agents that are connecting to these servers and making very bad decisions.
And yes to teh comments about people making a million of these... so very very many of them.
just want to add that this line from the article "Before passing data to the assistant, scan them for suspicious patterns like imperative verbs, SQL-like fragments, or common injection triggers. This can be implemented as a lightweight wrapper around MCP that intercepts data and flags or strips risky input." is exactly what we're building at maybedont.ai .... it's free and downloadable today. if you're running in to these things, give it a try and get in touch with us (founder here), we'd lvoe all the input.