Model Shunt

Local

@yasmanycastilloPythonMITUpdated 2 days ago

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

Runs locally over stdio

This server isn't hosted — your MCP client launches it from a package registry. Use one of the commands below, or drop the config into your client (e.g. Claude Desktop).

PyPImodel-shuntv1.2.1

Run

uvx model-shunt

MCP client config

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

npmmodel-shuntv1.2.1

Run

npx -y model-shunt

MCP client config

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