rcarmo 7 days ago

There is one thing I pointed out in https://taoofmac.com/space/notes/2025/03/22/1900 and seems to be missing from the article:

"... MCP tends to crowd the model context with too many options. There doesn’t seem to be a clear way to set priorities or a set of good examples to expose MCP server metadata–so your model API calls will just pack all the stuff an MCP server can do and shove it into the context, which is both wasteful of tokens and leads to erratic behavior from models."

1
sshh12 7 days ago

It's in there briefly in the llm limitations section.