$ loading_
Run ComfyUI workflows and manage models directly from your AI coding assistant.
Copy the install command and let the AI configure it · recommended for beginners
No copy-paste install info for "comfyui-mcp" yet — see the docs or source repo.
Connect to my ComfyUI and run this text-to-image workflow: use SDXL to generate a cyberpunk city night scene, then return each node's execution status, the final image, and troubleshooting advice for any failed nodes.
Returns the workflow result, generated image, node statuses, and actionable troubleshooting advice.
Visualize the current ComfyUI workflow, explain the relationships among the sampler, prompt encoding, VAE, and upscaling nodes, and give three suggestions to improve speed or image quality.
Provides a pipeline explanation plus optimization recommendations for performance and image quality.
List the available checkpoints, LoRAs, and custom nodes in my ComfyUI setup, inspect current VRAM usage, and suggest how to unload unused models to reduce memory pressure.
Returns model and node inventories, VRAM status, and concrete resource management suggestions.
Let Claude Code inspect and edit ComfyUI workflows through MCP and terminal.
Connect to ComfyUI, run workflows, and return generated images inline.
Expose ComfyUI workflows as MCP tools for LLM-driven image generation.
Generate image and 3D assets through ComfyUI workflows from AI assistants.
Connect to ComfyUI to inspect assets and run workflow jobs.
Generate PNG images via remote ComfyUI and manage its lifecycle through MCP.