This MCP server implementation provides a bridge between ComfyUI and MCP clients for image generation tasks. It uses WebSockets for communication, allowing clients to send image generation requests with customizable parameters like prompt, width, and height. The server processes these requests through ComfyUI and returns the generated image URL. It's designed for easy integration into applications requiring on-demand AI image generation capabilities.
No reviews yet. Be the first to review!
Sign in to join the conversation
Highlight AIGenerate images based on a given prompt. Requires: prompt (string)
Generate audio content based on specified tags and lyrics. Requires: tags (string), lyrics (string)
Regenerate an existing asset with optional parameter overrides. Requires: asset_id (string)
View generated images inline. Supports images only, not audio/video.
Check the state of the ComfyUI queue (running/pending jobs) for async awareness.
Poll the completion status of a job by prompt_id to check if it has finished.
Browse recently generated assets, enabling AI memory and iteration.
Retrieve full provenance and parameters for a specific asset, including workflow history.
Cancel a queued or running job.
List all available ComfyUI models.
Get the current default values set for the server.
Set default values for parameters with optional persistence.
List all available workflows that can be executed.
Run any specified workflow with custom parameters.
Show the publish status including detected project root and any missing setup.
Set the ComfyUI output directory, persisted across restarts.
Publish a generated asset into the project's web directory with deterministic compression. Requires: asset_id (string), target_filename (string), manifest_key (optional string)
