So basically rewrite MCP tools with your own scripts.
MCP is just an API with docs.
The problem isn’t MCP itself. It’s that each MCP “server” has to expose every tool and docs which consumes context.
I think the tools should use progressive reveal and only give a short summary like the skill does. Then agent can get full API of the tool on request.
Right now loading GitHub MCP takes something like 50k tokens.