The linked article there makes a salient argument against it, but the discussion cuts the other way. Basically, having an MCP between the agent/AI and Gmail could have been structured in a manner to prevent these kinds of hijinks. Nevermind that it keeps credentials out of the hands of the agent, making it harder to go rogue.
There is a thread right now on Hacker News about the use of MCPs with a robust discussion on the matter.
https://news.ycombinator.com/item?id=49779329
The linked article there makes a salient argument against it, but the discussion cuts the other way. Basically, having an MCP between the agent/AI and Gmail could have been structured in a manner to prevent these kinds of hijinks. Nevermind that it keeps credentials out of the hands of the agent, making it harder to go rogue.