Enables an agent to control a running ComfyUI instance by submitting workflows, running randomized batch generation with LoRA stacks and IP-Adapter blending, and reading back provenance for every generated image.
Exposes the workflows saved in a ComfyUI server (local, remote, or vast.ai) as MCP tools, letting agents list them, inspect their inputs, and run them with their own prompts, images, seeds, and per-run node toggles. It also reports server/GPU status, tracks and downloads job outputs, and uploads images or browses model folders.
Enables local, provider-independent image generation and editing through named connections, multiple image protocols, and configured ComfyUI workflows, with saved outputs, job tracking, and explicit tool operations.
Enables comprehensive ComfyUI workflow automation including image generation, workflow management, node discovery, and system monitoring through natural language interactions with local or remote ComfyUI servers.
Enables AI assistants to interact with local ComfyUI installations to list nodes, validate workflows, and execute image generation workflows directly without requiring an HTTP server.