Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@ComfyUI MCP Hub Generate an image of a mountain landscape at sunset"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
MCP Hub is a Model Context Protocol server packaged as a ComfyUI custom node. It exposes 79 tools that let any MCP-compatible AI assistant — Claude, Gemini, Codex, Cursor, and more — interact with your local ComfyUI instance: inspect workflows, generate images, manage models, install packages, and manipulate the canvas in real time.
One install. Zero cloud dependency. Fully local.
Canvas control — AI agents can read the graph, add/remove/connect nodes, update parameters, capture screenshots, execute workflows, and arrange the layout (move, align, collapse, resize, fit view) directly on the canvas.
CivitAI & HuggingFace integration — Search models, download with progress tracking, content-safety filtering, hash-based exact matching.
Smart resolver — Submit any workflow: MCP Hub automatically detects missing nodes, missing models, and broken Python dependencies, then fixes them.
Multi-instance — Register ComfyUI instances across your LAN and route any command to any machine.
Activity tracking — Real-time log of every agent action, download progress bars, and toast notifications in the ComfyUI UI.
One-click client setup — Auto-detects 10 AI clients and writes their MCP config for you.
Related MCP server: ComfyUI MCP Server
Option A — ComfyUI-Manager (recommended)
Search for "MCP Hub" in ComfyUI-Manager's custom node browser, then click Install.
Option B — Git clone
cd /path/to/ComfyUI/custom_nodes
git clone https://github.com/ArboRithmDev/comfyui-arbo-mcp-hub.gitOption C — Download ZIP
Download the latest release, extract into ComfyUI/custom_nodes/comfyui-arbo-mcp-hub/.
Restart ComfyUI. On first load, MCP Hub will automatically:
Install its Python dependencies (mcp, aiohttp, websockets)
Install ComfyUI-Manager if not present
Register a sidebar panel in ComfyUI Desktop
Open the MCP Hub panel in ComfyUI's sidebar → AI Clients tab → Configure All.
That's it. Your AI clients are ready to talk to ComfyUI.
Add this to your MCP client's config file:
{
"mcpServers": {
"comfyui-arbo-mcp-hub": {
"command": "/path/to/ComfyUI/.venv/bin/python",
"args": ["/path/to/ComfyUI/custom_nodes/comfyui-arbo-mcp-hub/mcp_server/main.py"]
}
}
}For TOML-based clients (Codex, Mistral Vibe):
[mcp_servers.comfyui-arbo-mcp-hub]
command = "/path/to/ComfyUI/.venv/bin/python"
args = ["/path/to/ComfyUI/custom_nodes/comfyui-arbo-mcp-hub/mcp_server/main.py"]Ask your AI assistant:
"What models do I have installed?"
"Search CivitAI for a realistic SDXL LoRA"
"Look at my current workflow and describe it"
"Add a KSampler node connected to the checkpoint loader"
"Generate an image of a mountain landscape at sunset"
"Why did my last execution fail?"MCP Hub auto-detects installed clients and writes the correct config format (JSON or TOML):
Client | Format | Config path |
Claude Code (CLI) | JSON |
|
Claude Desktop | JSON |
|
Gemini CLI | JSON |
|
Codex CLI (OpenAI) | TOML |
|
Mistral Vibe | TOML |
|
Cursor | JSON |
|
Windsurf | JSON |
|
Continue.dev | JSON |
|
VS Code | JSON | Platform-specific |
Ollama | — | Detected, no native MCP support (info shown) |
Paths shown are for macOS. Linux and Windows equivalents are handled automatically.
MCP Hub adds a sidebar panel to ComfyUI Desktop:
Tab | Description |
Server | Start/stop the MCP server, toggle autostart with ComfyUI |
Activity | Live feed of agent actions, download progress bars with speed indicators |
Tools | Enable/disable tool categories per domain |
AI Clients | Detected clients with install status, one-click configuration |
Instances | Manage ComfyUI instances on your LAN |
Settings | API tokens (CivitAI, HuggingFace), content-safety filter level, auto-resolve toggle |
Tool | Description |
| List all available nodes, filter by category or search term |
| Detailed inputs, outputs, and defaults for a specific node |
| List models by type — any directory, including custom ones like |
| Discover all model directories with file counts |
| GPU, VRAM, queue depth, uptime |
Tool | Description |
| List saved workflow files |
| Get a workflow JSON by name |
| Save a workflow to disk |
| Submit a workflow for execution, returns a job ID |
| Poll job status (queued, running, completed, error) |
| Retrieve output files (images, video, audio) |
| Cancel a queued or running job |
Tool | Description |
| Text-to-image with prompt, model, size, steps, CFG, seed |
| Image-to-image with source, prompt, denoise strength |
| Video generation (delegates to workflow) |
| Audio generation (delegates to workflow) |
Tool | Description |
| Download via ComfyUI-Manager |
| Two-step safe deletion with size preview |
| Execute confirmed deletion |
| Size, partial SHA-256, modification date |
| Free VRAM/RAM |
Tool | Description |
| Search the ComfyUI registry |
| Install a custom node |
| Update a custom node |
| Remove a custom node |
| Installed nodes with versions |
| Available updates |
| Dependency conflict detection and suggestions |
Tool | Description |
| Full pipeline: missing nodes → install, missing models → find, broken deps → fix |
| Search CivitAI with type filter and safety control |
| Download with real-time progress tracking |
| Hash lookup (exact) → name search (fuzzy) → interactive candidates |
| Three-tier: auto-fix → diagnose root cause → propose solutions |
Tool | Description |
| Rules-based L→R flow layout with auto-coloring and named groups |
| Color by category, connected branch, or custom per-node mapping |
| Detect logical sections and create named groups (by category or branch) |
| Add visual annotation frame with title, position, size, color |
Tool | Description |
| Detect/merge duplicate model loaders |
| Extract prompts and seeds into |
| Load template and inject input values with optional overrides |
| Browse saved templates with their variable names |
| Full git versioning: init, commit, log, diff, restore, remote, push, pull |
Tool | Description |
| Full instance state in one call (system, models, nodes, canvas) |
| Create nodes + connections + layout in a single call |
| Update multiple nodes (widgets, position, color, collapse) at once |
| Template → resolve → load → execute in one call |
Tool | Description |
| Serialize the canvas graph |
| Selected nodes with types, positions, widgets |
| All widget names and current values for a node |
| Screenshot as base64 PNG — for multimodal agents |
| Replace the canvas with a workflow JSON |
| Wipe the canvas |
| Place a node with position and widget values |
| Delete a node |
| Wire source output → target input |
| Change widgets, title, or color |
| Position a node at exact coordinates |
| Set dimensions or auto-fit to content |
| Toggle collapsed/expanded state |
| Auto-layout all nodes |
| Align nodes horizontally or vertically with configurable spacing |
| Visual grouping |
| Reset canvas zoom to show all nodes |
| Refresh the interface (soft: redraw + reload dropdowns, hard: full page reload) |
| Queue canvas workflow — returns |
| Node preview as base64 PNG |
| Toast notification in ComfyUI |
Tool | Description |
| Last validation/execution error with node-level detail |
| Recent server log lines, filterable by level ( |
Tool | Description |
| All registered instances |
| Add a LAN instance by name, host, port |
| Remove an instance |
| Connectivity, GPU name, free VRAM |
| Route commands to a specific instance by default |
┌──────────────────────────────────────┐
│ ComfyUI Desktop │
│ │
│ ┌──────────────────────────────┐ │
│ │ MCP Hub Panel (JS) │ │
│ │ + Bridge (WebSocket + API) │ │
│ └─────────────┬────────────────┘ │
│ │ REST / WS │
│ ┌─────────────▼────────────────┐ │
│ │ Backend (Python) │ │
│ │ Routes, UI Bridge, │ │
│ │ Activity Log, Process Mgr │ │
│ └─────────────┬────────────────┘ │
└─────────────────┼────────────────────┘
│ subprocess (stdio)
┌─────────────────▼────────────────────┐
│ MCP Server (separate process) │
│ 79 tools · 4 resources │
│ Auto-detects Manager v1/v2 API │
└────────┬────────────────┬────────────┘
│ │
┌────▼─────┐ ┌─────▼────┐
│ ComfyUI │ │ ComfyUI │
│ (local) │ │ (LAN) │
└──────────┘ └──────────┘The MCP server runs as an isolated subprocess communicating over stdio. It never imports ComfyUI internals — all interaction goes through HTTP and WebSocket APIs. This keeps the server compatible with any ComfyUI version and allows it to target remote instances.
MCP Hub generates mcp_server/hub_config.json on first run (git-ignored — contains your tokens):
{
"comfyui_url": "http://127.0.0.1:8188",
"autostart": true,
"civitai_token": "",
"huggingface_token": "",
"safety_filter": "soft",
"auto_resolve_on_execute": true,
"enabled_tools": {
"introspection": true,
"workflows": true,
"generation": true,
"models": true,
"packages": true,
"instances": true
},
"instances": [
{ "name": "local", "host": "127.0.0.1", "port": 8188, "default": true }
]
}The config auto-syncs with ComfyUI's actual address and port on every startup. No manual editing needed.
CivitAI results respect your preference:
Level | Visible content |
| SFW only |
| SFW + Soft (hides Mature, X) |
| SFW + Soft + Mature (hides X) |
| Everything |
Set via the Settings tab or directly in hub_config.json.
MCP Hub is designed for ComfyUI Desktop and handles its differences from standalone ComfyUI:
Feature | How it's handled |
Manager V2 API | Auto-detects |
Port detection | Reads |
Sidebar UI | Registers via |
Shutdown |
|
Empty responses | HTTP client gracefully handles |
MCP Hub also works with standalone ComfyUI using legacy Manager routes and the classic .comfy-menu.
Requirement | Version |
ComfyUI | Desktop or standalone |
Python | 3.10+ |
Git | For installation |
Python dependencies (mcp, aiohttp, websockets) are installed automatically on first startup.
Smart layout engine — rules-based L→R flow positioning, context-aware branch coloring, auto-group detection, annotation frames
Workflow optimizer — detect and merge duplicate model loaders with automatic connection rewiring
Template system — extract prompts/seeds into {{variables}}, separate creative content from shareable workflow structure
Git versioning — init, commit, diff, log, restore, remote push/pull for the workflows directory
Combo tools — get_overview, build_workflow, batch_update_nodes, setup_and_execute to reduce round-trips for interaction-limited clients (Gemini, etc.)
Pagination — list_nodes now paginated (limit/offset) to avoid context flooding
79 MCP tools total
CivitAI & HuggingFace integration — search models, download with progress tracking, content-safety filtering, hash-based exact matching
Resolver pipeline — resolve_workflow auto-detects and fixes missing nodes, models, and Python dependency conflicts (three-tier: auto → diagnose → propose)
Activity log — real-time tracking of all agent actions with toast notifications and download progress bars in the UI
UI Bridge — bidirectional canvas control: read/write graph, add/remove/connect nodes, capture screenshots, execute workflows, get previews
Layout tools — move_node, resize_node, collapse_node, align_nodes, fit_view, refresh_ui
Debugging tools — get_last_error (validation + execution errors with node detail), get_logs (grouped tracebacks, stderr capture)
execute_current fixed — uses app.queuePrompt() for full extension hook support (cg-use-everywhere, rgthree GetNode/SetNode)
ComfyUI Desktop compatibility — Manager V2 auto-detection (/v2/ routes), empty response handling, config auto-sync
list_models extended — supports any model directory (ultralytics/bbox, text_encoders, LLM, etc.) via filesystem fallback
list_model_types — discover all model directories with file counts
Settings tab — CivitAI/HuggingFace tokens, content-safety filter, auto-resolve toggle
Autostart — MCP server starts with ComfyUI, clean shutdown on exit
Initial release: 32 tools across 6 domains
Introspection, workflows, generation, models, packages, instances
Sidebar panel with Server, Tools, AI Clients, Instances tabs
Auto-detection and configuration of 10 AI CLIs
Auto-install dependencies on startup
Issues and pull requests are welcome at github.com/ArboRithmDev/comfyui-arbo-mcp-hub.
This server cannot be deployed
Remote MCP for RunComfy: ComfyUI deployments, hosted models, LoRA training. 31 tools.
Give your AI agents the tools to build, manage, and run automation workflows.
Build and run visual creative-production workflows from your AI agent.
Free public MCP for AI agents — 193 tools, 44 workflows. No API key.
