ComfyUI provides two MCP servers that let AI agents (Claude Desktop, Claude Code, Cursor, Amp, and other MCP-compatible clients) generate images, video, audio, and 3D content — with no local ComfyUI installation or GPU required.Documentation Index
Fetch the complete documentation index at: https://docs.comfy.org/llms.txt
Use this file to discover all available pages before exploring further.
Comfy Cloud MCP
Connect to the hosted MCP server at
Closed beta — sign up for the waitlist.
cloud.comfy.org. Runs workflows on Cloud GPUs, uses pre-installed models, and searches the full template library.Closed beta — sign up for the waitlist.
Comfy Partner MCP
Run a local MCP server using the Comfy Partner-Node SDK. Provides unified
Waitlist — sign up for early access.
generate_image, generate_video, generate_3d, and more tools across 30+ partner providers.Waitlist — sign up for early access.
Which One Should I Use?
| Comfy Cloud MCP | Comfy Partner MCP | |
|---|---|---|
| Type | Remote (hosted) | Local (runs on your machine) |
| Requires | Comfy Cloud subscription | Comfy API key |
| Models | Comfy Cloud models (pre-installed) | 30+ partner providers (BFL, Ideogram, Kling, Runway, Veo, ElevenLabs, etc.) |
| Workflows | Full ComfyUI workflow execution | Partner API generation (no custom workflows) |
| GPU | Cloud GPUs (no local GPU needed) | No GPU needed (API-based) |
| Access | Closed beta (waitlist) | Waitlist |
What is MCP?
The Model Context Protocol (MCP) is an open standard that allows AI assistants to interact with external tools and services through a standardized interface. Instead of an AI agent needing to know custom API formats for every service, MCP provides a uniform way to expose tools. When you connect an MCP server to Claude Desktop, Claude Code, Cursor, or Amp, the AI assistant can:- Generate images from text descriptions
- Create videos from text or images
- Generate 3D models from text or images
- Generate audio and music using AI models
- Search models and templates to find the right tools for your task