ComfyUI MCP Server

ComfyUI MCP server enabling AI agents to control ComfyUI — the powerful node-based Stable Diffusion UI — submitting image generation workflows, querying generation status, retrieving generated images, and integrating ComfyUI's local AI image generation into agent-driven creative and image processing workflows.

Evaluated Mar 07, 2026 (0d ago) vcurrent
Homepage ↗ Repo ↗ File Management comfyui stable-diffusion image-generation mcp-server ai-art generative-ai workflow
⚙ Agent Friendliness
73
/ 100
Can an agent use this?
🔒 Security
72
/ 100
Is it safe for agents?
⚡ Reliability
60
/ 100
Does it work consistently?

Score Breakdown

⚙ Agent Friendliness

MCP Quality
65
Documentation
68
Error Messages
62
Auth Simplicity
95
Rate Limits
85

🔒 Security

TLS Enforcement
75
Auth Strength
68
Scope Granularity
62
Dep. Hygiene
65
Secret Handling
88

Local ComfyUI. Bind to localhost only. No credentials for local use. Community MCP. Review model licenses.

⚡ Reliability

Uptime/SLA
65
Version Stability
60
Breaking Changes
58
Error Recovery
58
AF Security Reliability

Best When

An agent needs to generate AI images via local Stable Diffusion using ComfyUI workflows — for complex multi-step image generation pipelines, LoRA/ControlNet workflows, or local GPU-based generation.

Avoid When

You prefer cloud APIs (DALL-E, Midjourney) or don't have GPU hardware for local Stable Diffusion inference.

Use Cases

  • Generating AI images via Stable Diffusion from creative assistant agents
  • Running ComfyUI workflows programmatically from automation agents
  • Batch generating images with different prompts from creative pipeline agents
  • Checking image generation progress from monitoring agents
  • Integrating AI image generation into multi-step creative workflows
  • Generating product images and variations from e-commerce agents

Not For

  • Teams without ComfyUI installed locally (requires local GPU or ComfyUI server)
  • Cloud-based image generation (use DALL-E or Stability AI APIs)
  • Simple prompt-based generation without ComfyUI workflow complexity

Interface

REST API
Yes
GraphQL
No
gRPC
No
MCP Server
Yes
SDK
No
Webhooks
No

Authentication

Methods: none
OAuth: No Scopes: No

No authentication — connects to locally running ComfyUI server (default http://localhost:8188). ComfyUI must be running before MCP can be used.

Pricing

Model: free
Free tier: Yes
Requires CC: No

ComfyUI is free open source. MCP server is free. GPU hardware costs are separate. Cloud hosting with GPU adds cost.

Agent Metadata

Pagination
none
Idempotent
Partial
Retry Guidance
Not documented

Known Gotchas

  • ComfyUI must be running with API access enabled (--listen flag for remote access)
  • Workflow JSON format is ComfyUI-specific — agents must understand node graph format
  • Generation is async — agents must poll for completion status
  • Image generation can take seconds to minutes depending on GPU and workflow complexity
  • Community MCP from lalanikarim — ComfyUI API changes with new versions
  • Output images are stored in ComfyUI output directory — agents must retrieve from there

Alternatives

Full Evaluation Report

Comprehensive deep-dive: security analysis, reliability audit, agent experience review, cost modeling, competitive positioning, and improvement roadmap for ComfyUI MCP Server.

AI-powered analysis · PDF + markdown · Delivered within 30 minutes

$99

Package Brief

Quick verdict, integration guide, cost projections, gotchas with workarounds, and alternatives comparison.

Delivered within 10 minutes

$3

Score Monitoring

Get alerted when this package's AF, security, or reliability scores change significantly. Stay ahead of regressions.

Continuous monitoring

$3/mo

Scores are editorial opinions as of 2026-03-07.

6470
Packages Evaluated
26150
Need Evaluation
173
Need Re-evaluation
Community Powered