Not sure I understand what you mean. MCP servers and methods available do have to be visible to the model in some way so that it can spit out tool calls instructions to be executed by the orchestration layer around it. But you probably meant something else?
MCP is the protocol by which the harness can connect with additional tools. The harness does the work of discovering the tools, the model is then fed a description of what tools it has available, with zero awareness of whether those tools are MCP or built into the harness itself (except for by the mcp__ prefix in the tool’s name, which a harness could choose to strip off)