Skip to main content

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.

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.

Comfy Cloud MCP

Connect to the hosted MCP server at 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 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 MCPComfy Partner MCP
TypeRemote (hosted)Local (runs on your machine)
RequiresComfy Cloud subscriptionComfy API key
ModelsComfy Cloud models (pre-installed)30+ partner providers (BFL, Ideogram, Kling, Runway, Veo, ElevenLabs, etc.)
WorkflowsFull ComfyUI workflow executionPartner API generation (no custom workflows)
GPUCloud GPUs (no local GPU needed)No GPU needed (API-based)
AccessClosed 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
…all through natural language conversation, without writing API calls manually.