async/await for LLM agents: spawn and await sub-agents scheduled on your own GPUs
Luftpause is an MCP integration. Async/await for LLM agents: spawn and await sub-agents scheduled on your own GPUs.
The published oci package is ghcr.io/luftpause/runtime:v0.1.4. Its declared MCP transport is streamable-http.
The package declares Runtime__Model (required): Model the sub-agents run on, as served by an engine behind the luftpause dataplane; DataPlane__Url: URL of the luftpause dataplane that places each turn on the engine pool; LUFTPAUSE_TOKEN: Bearer token required on the MCP endpoint and sent to the dataplane; unset leaves both open.
Check the maintainer’s instructions for account access, authentication and the supported client configuration. Once connected, inspect the tools your client receives and try a small task that matches the server’s stated purpose. The registry description does not include a verified, complete tool list.
View the publisher’s registry entry · Project repository · Project website. This profile uses version 0.1.4 from the registry. Registration identifies the publisher namespace; it does not establish that this is a first-party integration for every service it connects.
Browse related developer tools MCP servers for tools that cover the same kind of work.
| Variable | Description | Required |
|---|---|---|
| Runtime__Model | Model the sub-agents run on, as served by an engine behind the luftpause dataplane | Yes |
| DataPlane__Url | URL of the luftpause dataplane that places each turn on the engine pool | Check documentation |
| LUFTPAUSE_TOKEN | Bearer token required on the MCP endpoint and sent to the dataplane; unset leaves both open | Check documentation |
Read, search and edit files inside allowed directories with the Model Context Protocol reference Filesystem server.
Retrieve version-aware library documentation and code examples with Context7 MCP, using resolve-library-id and query-docs.
A Model Context Protocol server for managing GitHub issues as Kanban using gh CLI
Local stdio MCP server that lets AI coding agents read and maintain structured architecture, rules, and decisions directly from your repository.
A comprehensive Model Context Protocol (MCP) server that enables AI assistants to interact with Yandex Tracker APIs. This server provides secure
Dotfiles for AI coding agents: one versioned repo that makes any machine, running any supported harness, behave like the same agent.