Wraps another MCP server to allow lifecycle management (start/stop/restart) and proxy its tools, resources, and notifications, enabling iterative development without agent reconnection.
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.
Reference MCP server for the mcp-longjobs library: durable long-running tasks with progress polling, mid-flight input, and cooperative cancellation, plus chunked file transfers with resume cursors and sha256 verification. Works on every MCP client today — no Tasks-extension support required.