Agent Tools

Use ComfyUI with AI agents through Comfy MCP, Comfy CLI, and Comfy Agent.

Comfy MCP

Connect any AI agent to ComfyUI, on Comfy Cloud or on your own machine. Start here.

Comfy Agent

Built-in ComfyUI assistant for building, editing, and running workflows.

Comfy CLI

ComfyUI in the terminal. Install and update ComfyUI, manage models and nodes, and generate from scripts, CI, or batch jobs.

---

Which one should I use?

	Comfy MCP Cloud Connection	Comfy MCP Local Connection	Comfy Agent
What is it	Run Comfy Cloud workflows with your own agent.	Drive your own local ComfyUI with your own agent.	Chat with an Agent inside ComfyUI to understand, build, edit, and run a selected workflow.
Best for	Running Cloud workflows from an external agent. Sharing workflows.	Using an external agent with local models, custom nodes, and files.	Building and editing workflows while viewing the canvas.
Requires	Your own agent. An active Comfy Cloud subscription.	Your own agent. A local ComfyUI setup.	A Comfy account and a supported Cloud or local installation.
GPU	Cloud GPUs (no hardware requirements)	Your local GPU	Cloud GPUs for Cloud workflows. Local hardware for local workflows.
Models	Comfy Cloud models. You can import your own models.	Local models downloaded to your machine.	Cloud or local models, depending on whether you use Comfy Cloud or Comfy Desktop.
Custom nodes	The custom nodes supported on Comfy Cloud.	You can install any custom node.	Cloud-supported nodes in Cloud. Local nodes in a supported local setup.

Both connections use Comfy MCP, and you can configure them together.

---

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.