Wraps another MCP server to allow lifecycle management (start/stop/restart) and proxy its tools, resources, and notifications, enabling iterative development without agent reconnection.
A zero-dependency stdio proxy that wraps any MCP server so slow tool calls are moved to the background instead of hitting client timeouts, handing back a task or job id immediately. Callers then collect the finished result later through Tasks (2025-11-25 or 2026-07-28) or built-in coatcheck_result, coatcheck_status, and coatcheck_cancel tools.
Async MCP server for running long-running AI tasks with real-time progress monitoring, enabling users to start, monitor, and manage complex AI workflows across multiple models.