comfyui-mcp-server
If you are the rightful owner of comfyui-mcp-server and would like to certify it and/or have it hosted online, please leave a comment on the right or send an email to henry@mcphub.com.
ComfyUI MCP Server is a full-featured implementation of the Model Context Protocol (MCP) for ComfyUI, enabling AI agents to generate and manipulate images using a standardized API.
ComfyUI MCP Server bridges the gap between AI agents and image generation by implementing the Model Context Protocol (MCP) for ComfyUI. The Model Context Protocol is a standardized way for AI agents to discover and interact with tools through rich metadata and schema information. This implementation allows any AI assistant to easily generate and manipulate images using Stable Diffusion models through ComfyUI. The server supports a variety of image generation capabilities, including text-to-image, image-to-image transformation, inpainting, and more. It also features advanced infrastructure for job management, progress tracking, and session persistence.
Features
- Full MCP Protocol Implementation: Tool discovery with metadata and schemas, session and context management, real-time communication.
- Rich Image Generation Capabilities: Includes text-to-image, image-to-image transformation, inpainting, ControlNet support, and LoRA model integration.
- Advanced Infrastructure: Features job queue with priority support, progress tracking, real-time updates, authentication, rate limiting, and session persistence.
Tools
generate_image
Generate image from text with parameters like prompt, width, height, negative_prompt, model.
img2img
Transform an image based on text with parameters like prompt, image, strength, width, height.
get_job_status
Check status of a job using job_id.
list_models
List available models.
get_tools_manifest
Get complete tools manifest.
