A free, open source, local MCP gateway. Set up each server once and every AI agent shares it (Claude, Cursor, VS Code, Codex, and 29 more). Instead of dumping every tool definition into context, it exposes a few meta-tools your agent searches on demand. Benchmarked and graded for correct answers, that's up to 91% fewer tokens at the same task success. Secrets live in your OS keychain, not client configs. Rug-pulls and tool poisoning get flagged, and destructive calls can wait for your approval.

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.

Set up your team's MCP servers once; every member's AI client gets them (Claude, Cursor, Codex, +18 more). Only the server set syncs, never a secret: keys stay in each member's OS keychain, so there's no central vault to breach. Govern centrally: access control, roles, spend budgets, tighten-only safety policy, rug-pull alerts, CSV audit trail. Up to 91% fewer tokens via lazy discovery. Hosted or self-hosted. Free for up to 5; Team is $39/mo flat, then $12/person past 5. 14-day trial, no card.