Conduit
Fix the tool-list bloat slowing your AI agent
What is Conduit?
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.
From the website
Toolport: all your MCP servers, one gateway, every AI agent
A free, open source local MCP gateway. Set up each server once and every AI agent shares it (Claude, Cursor, VS Code, Codex), with up to 91% fewer tool tokens and secrets in your OS keychain.
Visit Website →Screenshots
No comments yet. Be the first!