> ## Documentation Index
> Fetch the complete documentation index at: https://dripart-docs-nav-cta-ab-test-try-cloud-free.mintlify.site/llms.txt
> Use this file to discover all available pages before exploring further.

# Overview

> Using ComfyUI as a Developer

ComfyUI is a modular GenAI inference engine that can be run as a server, accessed via API, extended with custom nodes, and managed from the command line. Choose your path below.

## Build on ComfyUI

Run ComfyUI workflows from your own application and get the results back. The official SDKs sit on a versioned HTTP API, and the same code works against Comfy Cloud or a ComfyUI instance you host yourself.

<Card title="Comfy SDKs" icon="code" href="/development/api-development/sdks">
  Install the Python or TypeScript SDK, submit a workflow, and download the outputs. Currently in beta.
</Card>

See also: [Design Notes](/development/api-development/sdks-design) · [Comfy API v2 Reference](/api-reference/v2/overview) · [APIs Overview](/development/api-development/overview)

## Deploy ComfyUI as a Server

Run ComfyUI in your own environment and expose it as an API endpoint. Learn about the WebSocket message protocol, available routes, and execution modes.

<Card title="ComfyUI Server API" icon="server" href="/development/comfyui-server/comms_overview">
  Run ComfyUI as a server on your own machine. Start, configure, and call it via REST and WebSocket APIs.
</Card>

See also: [API Examples](/development/comfyui-server/api-examples) · [Partner Node API Integration](/development/comfyui-server/api-key-integration)

## Cloud API

Run workflows programmatically on Comfy Cloud without managing your own hardware. Use the REST API, browse the OpenAPI spec, and integrate Partner Nodes via API Key.

<Card title="Cloud API Overview" icon="cloud" href="/development/cloud/overview">
  Learn how to authenticate, submit jobs, check status, and download results from Comfy Cloud.
</Card>

See also: [API Reference](/development/cloud/api-reference) · [OpenAPI Specification](/development/cloud/openapi) · [Getting an API Key](/development/api-development/getting-an-api-key) · [APIs Overview](/development/api-development/overview)

## Agent Tools / MCP

Connect AI agents to ComfyUI via the Model Context Protocol (MCP). Start with the hosted Cloud MCP, or use Local MCP and Comfy CLI for other setups.

<Card title="MCP Overview" icon="robot" href="/agent-tools">
  Compare Cloud MCP, Local MCP, and Comfy CLI, and find the right setup for your AI agent integration.
</Card>

See also: [Comfy MCP](/agent-tools/mcp) — cloud and local connections

## Comfy CLI

Manage your ComfyUI installation, custom nodes, and workflows from the command line. Install, update, configure, and automate with ease.

<Card title="CLI Getting Started" icon="terminal" href="/comfy-cli/getting-started">
  Learn how to install, update, and manage ComfyUI from the terminal.
</Card>

See also: [CLI Reference](/comfy-cli/reference) · [Troubleshooting](/comfy-cli/troubleshooting)

## Custom Nodes

Extend ComfyUI with Python backends, JavaScript UI extensions, and integrations. Start with the [Custom Nodes overview](/custom-nodes/overview).

## Registry

Package and publish custom nodes through the Comfy Registry. Start with the [Registry overview](/registry/overview) or the [publishing tutorial](/registry/publishing).