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.
暂无评论. 成为第一个评论的人！
登录以参与讨论
Generate images based on a provided prompt.
Generate audio using provided tags and lyrics.
Regenerate an existing asset with optional parameter overrides, requires an asset ID.
View generated images inline; supports images only, not audio or video.
Check the current state of the ComfyUI queue, indicating running or pending jobs.
Poll the completion status of a job by its prompt ID to check if it has finished.
Browse recently generated assets to enable AI memory and support iterative processes.
Retrieve full provenance and parameters for a specific asset, including workflow history.
Cancel a job that is either queued or currently running.
List all available models that can be used in ComfyUI.
Retrieve the current default values used by the server.
Set new default values for the server, with optional persistence.
List all workflows that are available for execution.
Execute a specified workflow with custom parameters.
Show the current publish status, including detected project root and publish directory.
Set the output directory for ComfyUI, which will persist across server restarts.
Publish a generated asset into the project's web directory with deterministic compression.
