README.md
Generate and iteratively refine images, audio, and video via ComfyUI.
Enables AI agents to generate and iteratively refine images, audio, and video by interacting with a local ComfyUI instance through natural conversation. It provides comprehensive tools for workflow management, node introspection, and publishing generated assets.
Tools (3)
get_workflowsRetrieve a list of available ComfyUI workflows.run_workflowExecute a specific ComfyUI workflow with provided parameters.inspect_nodesGet detailed information about nodes within a workflow.Environment Variables
COMFYUI_BASE_URLrequiredThe base URL of your local ComfyUI instance (e.g., http://127.0.0.1:8188)Configuration
claude_desktop_config.json
{"mcpServers":{"comfy_mcp":{"command":"npx","args":["-y","@jaewilson07/comfy_mcp"],"env":{"COMFYUI_BASE_URL":"http://127.0.0.1:8188"}}}}Try it
→List all the workflows available in my local ComfyUI instance.
→Run my text-to-image workflow with the prompt 'a futuristic cyberpunk city at night'.
→Inspect the nodes in my current workflow to see which parameters I can adjust for the sampler.
→Generate a short video using my ComfyUI video-to-video workflow.