| ▲ | JambalayaJimbo 2 days ago | |
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? | ||
| ▲ | conception 2 days ago | parent | next [-] | |
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. | ||
| ▲ | simonw 2 days ago | parent | prev | next [-] | |
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. | ||
| ▲ | gavmor 2 days ago | parent | prev [-] | |
Typically, no; an MCP is a deterministic program with SSE protocols. | ||