Community

io.github.vmedvedovskiy/luftpause

async/await for LLM agents: spawn and await sub-agents scheduled on your own GPUs

Install

Add the config to your client settings. Replace values in <angle brackets> with your own.

claude_desktop_config.json

{
  "mcpServers": {
    "luftpause": {
      "command": "docker",
      "args": [
        "run",
        "-i",
        "--rm",
        "-e",
        "Runtime__Model",
        "-e",
        "DataPlane__Url",
        "-e",
        "LUFTPAUSE_TOKEN",
        "ghcr.io/luftpause/runtime:v0.1.2"
      ],
      "env": {
        "Runtime__Model": "<Runtime__Model>",
        "DataPlane__Url": "http://dataplane:8080/",
        "LUFTPAUSE_TOKEN": "<LUFTPAUSE_TOKEN>"
      }
    }
  }
}

Details

Name: io.github.vmedvedovskiy/luftpause
Version: 0.1.2
Updated: Oct 19, 2026
Source: Official MCP Registry
Repository: https://github.com/luftpause/luftpause
Website: https://github.com/luftpause/luftpause