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.
Aucun avis encore. Soyez le premier à donner votre avis !
Connectez-vous pour rejoindre la conversation
Highlight AIGenerate images based on a provided prompt. Requires 'prompt' parameter.
Generate audio content using specified tags and lyrics. Requires 'tags' and 'lyrics' parameters.
Regenerate an existing asset with optional parameter overrides. Requires 'asset_id' parameter.
View generated images inline. Supports images only, not audio or video.
Check the state of the ComfyUI queue, indicating running and pending jobs.
Poll the status of a job by its prompt_id to check if it has finished.
Browse recently generated assets to enable AI memory and iteration.
Retrieve full provenance and parameters for a specific asset, including workflow history.
Cancel a queued or currently running job.
List all available ComfyUI models for use in generation.
Fetch the current default values set in the server.
Set default values for parameters, with optional persistence across server restarts.
List all available workflows that can be run on the server.
Execute any workflow with custom parameters as defined in the workflow JSON.
Show the publish status, including detected project root and any missing setup.
Define the output directory for ComfyUI, recommended for specific installations.
Publish a generated asset into the project's web directory with deterministic compression. Requires 'asset_id' and optional 'target_filename' or 'manifest_key'.
