The MCP implementation is itself an agent right? Is that not just pushing the problem somewhere else?
Also, I run programs on my machine with a different privilege level than myself all the time. Why can’t an agent do that?
I define the agent as the harness that runs the LLM in a loop calling tools. The MCI implementation is one of those tools. I wouldn't call an MCP implementation an agent.
No, mcp just is a server that returns prompts to the llm. The server can be/do whatever. You can have an echo mcp that list echoes back whatever you send it.