← Back to directory

comfyui-mcp

Community

Drive ComfyUI with natural language.

GitHub source repository ↗

★ 454 Stars Category · Other Very popular

55FMRS · C

Reliability

9/20

Security and permissions

8/20

Maintenance

11/20

Documentation

14/20

Setup experience

13/20

This is a community MCP server and Claude Code plugin maintained by artokun, version 0.5.0, under the MIT license. It offers broad ComfyUI workflow, generation, model, node, diagnostics, and process-control capabilities. stdio is the default transport, with Streamable HTTP also supported.

Read the FMRS scoring method →

comfyui-mcp is a local-first, agent-native control plane for ComfyUI, distributed as an MCP server and Claude Code plugin. It generates images, video, and audio; creates, executes, validates, visualizes, and modifies workflows; manages models, embeddings, VRAM, and custom nodes; and edits the live ComfyUI graph. It supports local installs, LAN, VPS, remote ComfyUI, and Comfy Cloud.

Tools

generate_image

Generate an image from a text prompt and build a workflow automatically.

generate_with_controlnet

Generate an image using a ControlNet image condition and prompt.

generate_with_ip_adapter

Generate an image guided by a reference image's style or subject.

generate_audio

Generate music, instruments, or sound effects from a text prompt.

view_image

Return a generated asset as an inline image for agent inspection.

regenerate

Re-run the workflow that produced an asset, with optional parameter overrides.

list_assets

Browse recently generated assets by time.

get_asset_metadata

Return full asset provenance, workflow, and metadata.

get_defaults

Show merged generation defaults with source attribution.

set_defaults

Update runtime generation defaults and optionally persist them.

enqueue_workflow

Submit an API-format workflow and return a prompt ID.

get_job_status

Check the execution status of a job.

get_queue

View running and pending jobs in the queue.

cancel_job

Interrupt a running job and optionally clear pending jobs.

get_system_stats

Return GPU, VRAM, Python, and operating-system information.

visualize_workflow

Convert a workflow into a Mermaid flowchart grouped by category.

mermaid_to_workflow

Convert a Mermaid diagram into executable workflow JSON.

create_workflow

Create txt2img, img2img, upscale, inpaint, and related workflows from templates.

modify_workflow

Set inputs, add or remove nodes, and connect nodes.

get_node_info

Query node types available in ComfyUI.

validate_workflow

Check nodes, connections, output indices, and model files without executing.

list_workflows

List saved workflows in ComfyUI's user library.

get_workflow

Load a saved workflow by filename.

strip_workflow

Expand virtual links, reroutes, subgraphs, and bypassed nodes into a flat graph.

slice_workflow

Extract one standalone enabled pipeline from a toggle-template workflow.

save_workflow

Save a workflow to ComfyUI's user library.

upload_image

Copy a local image into ComfyUI's input directory.

workflow_from_image

Extract workflow metadata from a ComfyUI-generated PNG.

list_output_images

Browse recent images and videos in the output directory.

search_models

Search Hugging Face for compatible models.

download_model

Download a model URL to the appropriate ComfyUI subdirectory.

list_local_models

List installed local models by type.

clear_vram

Free GPU VRAM through ComfyUI's endpoint.

get_embeddings

List installed textual-inversion embeddings.

search_custom_nodes

Search the ComfyUI Registry for custom node packs.

get_node_pack_details

Return a node pack's description, author, nodes, and installation information.

generate_node_skill

Generate node-pack skill documentation from a Registry ID or GitHub URL.

get_logs

Return ComfyUI server logs with optional keyword filtering.

get_history

Return execution history, errors, traces, and timing details.

stop_comfyui

Stop the running ComfyUI process.

start_comfyui

Start ComfyUI using saved process information.

restart_comfyui

Restart ComfyUI while preserving launch arguments.

suggest_settings

Suggest sampler, scheduler, steps, and CFG settings from local generation history.

generation_stats

Show local generation tracking statistics.

Setup

Install ComfyUI, then add the server configuration from server.json to an MCP client. For Claude Code, place command npx and args ["-y","comfyui-mcp"] under mcpServers.comfyui in ~/.claude/settings.json. Start ComfyUI and request generation or workflow operations in natural language. Streamable HTTP is available with npx -y comfyui-mcp@latest --http; remote instances can be selected with --comfyui-url.

claude_desktop_config.json

{"mcpServers":{"comfyui":{"command":"npx","args":["-y","comfyui-mcp"],"env":{"CIVITAI_API_TOKEN":""}}}}

Generate and validate client config

Fit and risk

Best for

Users who want an agent to operate ComfyUI rather than only relay prompts.
Local GPU, LAN, VPS, RunPod, and Comfy Cloud users.
Creators who need model-specific generation skills, workflow recipes, and troubleshooting.
Users of Claude Code, Claude Desktop, or other MCP-capable agents.

Not for

Minimal connector use cases that only forward prompts and return images.
Users without a ComfyUI instance or reachable remote ComfyUI.
Models that do not support tool calling.
Users seeking official Comfy maintenance or an official cloud-service guarantee.

Required permissions

Requires access to the ComfyUI REST API and WebSocket.
Local mode may read and write model, input, output, and workflow-library directories.
Process-control features may start, stop, or restart local ComfyUI.
Model and node discovery or downloads may access Hugging Face, CivitAI, GitHub, and the ComfyUI Registry; some features require tokens.
Comfy Cloud mode requires COMFYUI_API_KEY.

Risks and side effects

Workflow execution can consume local GPU VRAM, compute, and disk space.
Downloaded models and custom nodes can be large and may include third-party code.
stop_comfyui, restart_comfyui, and queue operations can interrupt jobs or unsaved workflow changes.
Remote HTTP, tunnel, or bridge deployments increase network exposure and should use tokens and access controls.
Hosted API nodes may consume paid API credits.

Troubleshooting

Confirm that ComfyUI is running; the server probes ports 8188 and 8000 by default.
Set COMFYUI_PATH if installation-path auto-detection fails.
Use --comfyui-url or COMFYUI_URL for remote instances; use --force-remote for port-forwarded remote installs.
Check HUGGINGFACE_TOKEN or CIVITAI_API_TOKEN when model downloads fail.
Use get_history, get_logs, or /comfy:debug to inspect node, model, and Python errors.
Use clear_vram and check model VRAM requirements when memory is insufficient.
Ensure the selected model supports tool calling; the documentation also strongly recommends thinking and vision capabilities.

Use cases

Generate images, video, and audio from prompts.

Create, modify, validate, and execute ComfyUI workflows through an agent.

Search, download, and manage models and custom nodes.

Diagnose workflow failures using logs, history, and VRAM information.

Load, slice, and flatten complex workflows on the live canvas.

Supported clients

Claude DesktopFull support

Claude CodeFull support

MCP InspectorFull support

HermesPartial support

OpenClawPartial support

Copilot CLIPartial support

OllamaPartial support

Related MCP servers

Compare with other MCP servers