Your agent got slower the more MCP servers you added, and it's not the model. Every server dumps its whole tool list into context on every request: 3 servers cost ~24k tokens before you even say hi. Conduit puts them behind one local gateway that exposes 3 meta-tools the agent searches on demand. Measured: 97% less tool overhead per request, ~90% fewer tokens, same task success. Cloud or local, one tool or five. Keys in your OS keychain. Free and open source.