model shunt for Windsurf

io.github.yasmanycastillo/model-shunt

Model routing for AI agents: delegate bulk reads & boilerplate to cheap worker models.

client:Windsurf transport:stdio runtime:pypi

Install model shunt in Windsurf

~/.codeium/windsurf/mcp_config.json · windows: %USERPROFILE%\.codeium\windsurf\mcp_config.json

{
  "mcpServers": {
    "model-shunt": {
      "command": "uvx",
      "args": [
        "model-shunt"
      ]
    }
  }
}

Global only — Windsurf has no per-project MCP config. Refresh Cascade after saving. Windsurf docs