lalanikarim_comfy-mcp-server
If you are the rightful owner of lalanikarim_comfy-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.
A server using FastMCP framework to generate images based on prompts via a remote Comfy server.
The Comfy MCP Server is designed to facilitate image generation based on user prompts by leveraging the FastMCP framework. It connects to a remote Comfy server, where it submits prompts and retrieves the generated images. The server is configured using environment variables that specify the Comfy server URL, the workflow JSON file, and node IDs for the prompt and output. The server listens for requests and processes them to generate images using a specified workflow. The script requires Python 3.x and several packages, including mcp, json, urllib, time, and os. Users must export their workflow from Comfy UI and set the environment variables accordingly. The server can be run directly, and it will handle the image generation process by submitting prompts, polling for status, and retrieving the final images.
Features
- Remote Image Generation: Connects to a remote Comfy server to generate images based on prompts.
- Environment Configuration: Uses environment variables to configure server URL, workflow file, and node IDs.
- Prompt Submission: Submits prompts to the Comfy server and retrieves generated images.
- Polling Mechanism: Polls the server for the status of prompt processing.
- Direct Execution: Can be run directly to start the server and listen for image generation requests.
