Conduit cuts MCP tool tokens by routing many servers through one gateway
Conduit is a for managing many MCP servers in one place. AI clients such as Claude, Cursor, VS Code, and Codex can connect to Conduit instead of each being configured separately. Its main cost-saving idea is to avoid sending every tool description to the AI model on every request.
With 3 MCP servers and 62 tools, tool descriptions alone can use about 24,000 tokens before the user asks anything; Conduit reduces that to 3 meta-tools and about 660 tokens. Its benchmark reports up to 91% fewer total tokens while keeping the same task success rate. It also reports 97% less tool-description overhead per request, and 99.6% less overhead with a real 415-.
Secrets stay in the keychain instead of being sent to a cloud service. It also includes controls for limiting which tools each agent can use, hiding risky tools, logging tool calls, detecting changed , and marking suspicious outside content that may try to steer the agent.
Key points
- Conduit lets multiple AI clients share one setup for many MCP servers.
- shows only 3 meta-tools first, instead of the full .
- A 62-tool setup is described as dropping from about 24,000 tool-description tokens to about 660.
- The project reports up to 91% fewer total tokens at the same task success rate.
- Secrets are stored in the keychain, and tool access can be limited per agent.