
Comfyui Mcp
- Updated June 8, 2026
- miller-joe/comfyui-mcp
Gives an AI assistant a ComfyUI image pipeline: text-to-image, variations, img2img refine, upscale, and an image proxy.
About
ComfyUI MCP is an MCP server that fronts a ComfyUI instance for an AI assistant, exposing text-to-image, variations, img2img refinement, upscaling, and an image proxy. A solo builder reaches for it when they run ComfyUI locally or in Docker and want their agent to generate and refine images through simple tool calls, with a public-URL override so returned image links stay reachable across network boundaries.
- Text-to-image, variations, img2img
- Upscale and image proxy
- Public URL override for Docker networks
Comfyui Mcp by the numbers
- Data as of Jul 7, 2026 (Skillselion catalog sync)
claude mcp add ComfyuiMcp -- npx -y miller-joe/comfyui-mcpAdd your badge
Show developers this MCP server is listed on Skillselion. Paste this into your README.
| Last updated | June 8, 2026 |
|---|---|
| Repository | miller-joe/comfyui-mcp ↗ |
What it does
Gives an AI assistant a ComfyUI image pipeline: text-to-image, variations, img2img refine, upscale, and an image proxy.
Who is it for?
Driving a local or Docker ComfyUI pipeline from an agent.
Skip if: Users without a ComfyUI backend to point at.
What you get
- generated and refined images