A guide that connects Civitai, a community website for AI models and images, with ComfyUI tools. It supports discovering Civitai models and using local ComfyUI tools to download and generate with them.

Use it to search Civitai, browse images for ideas, download models, and prepare them for local ComfyUI workflows.

It separates online model discovery from local installation, so developers can find checkpoints, LoRAs, and embeddings and then use them in ComfyUI.

civitai — Skill for Claude Code by sandyup

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent

npx skills add sandyup/comfyui-mcp --skill civitai

Clone the repo

git clone --depth 1 https://github.com/sandyup/comfyui-mcp

Made for: Claude Code.

Or install comfy, the plugin that ships this one along with the rest of its 32 skills, 11 commands, 4 agents, 2 hooks.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/skills/sandyup/comfyui-mcp/civitai.svg)](https://agentmods.dev/skills/sandyup/comfyui-mcp/civitai)

Your own site

<a href="https://agentmods.dev/skills/sandyup/comfyui-mcp/civitai"><img src="https://agentmods.dev/badge/skills/sandyup/comfyui-mcp/civitai.svg" alt="Measured on agentmods" height="20"></a>

Per session 107 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,371 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

Model	Per session	Once invoked
Fable 5.1	$0.00107	$0.01371
Opus 5	$0.00053	$0.00685
Sonnet 5	$0.00021	$0.00274
Haiku 4.5	$0.00011	$0.00137

Measured 7d ago against content hash 8ab0693bdba3, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

civitai scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 7d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

plugin/skills/civitai/SKILL.md · 108 lines

How it starts

The opening of the file, as written. The whole thing — 108 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Civitai + comfyui-mcp

Civitai ships an official remote MCP server — discovery and the whole community surface — and comfyui-mcp owns the local machine: download, wire, queue, tag. They compose. comfyui-mcp deliberately does not proxy or re-expose Civitai's tools; MCP clients connect to both servers at once, so the right pattern is pairing, not wrapping.

Is the Civitai MCP connected?

Look for mcp__civitai__* tools in your session (e.g. mcp__civitai__search_models).

The comfy plugin bundles it — its .mcp.json declares the Civitai remote server alongside comfyui, so plugin users get mcp__civitai__* automatically with no manual setup and no key required (the Authorization header defaults to an empty Bearer, which Civitai accepts for its read/browse tools). It just works headless.

Present → use it for discovery (this skill's main path).
Absent (standalone MCP install, not the plugin) → either install the plugin, or add the server once:
```
claude mcp add --transport http civitai https://mcp.civitai.com/mcp \
  --header "Authorization: Bearer YOUR_CIVITAI_API_KEY"
```
Until then, fall back to search_models (HuggingFace) + download_civitai_model by id/URL.

API key (optional). Browsing/search needs none. To unlock the user's account context (favorites, posting, gated/early-access downloads), set CIVITAI_API_TOKEN (from civitai.com/user/account) in the environment — the same variable comfyui-mcp uses for its own downloads, so one secret powers both the Civitai MCP header and download_civitai_model.

The handoff that makes this work

Civitai's discovery tools return a model id and a model-version id — exactly what comfyui-mcp's download_civitai_model takes. No URL scraping:

mcp__civitai__search_models  ──▶  pick a result, read modelVersions[].id
        │
        ▼
download_civitai_model({ model_version_id, target_subfolder })   # local fetch
        │
        ▼
list_local_models  →  panel_add_node loader / generate_image      # use it

Read the full file on GitHub · 108 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

7d ago First seen · 108 lines · 107 tokens per session scan A 8ab0693bdba3

Subscribe to this mod's changes

civitai is a skill published in the GitHub repository sandyup/comfyui-mcp (1 stars, last pushed 2mo ago), licensed MIT. It adds 107 tokens to every session and 1,371 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Creative and media Data and AI

stable-diffusion

Text-to-image generation, inpainting, and img2img.

NousResearch/hermes-agent · 18 tokens

huggingface-lora-space-builder

Build and publish a Gradio demo on Hugging Face Spaces for a user-provided LoRA. Use when someone asks to create, generate, ship, or publish a Space, demo, Gradio app, or playground for a LoRA — including LoRAs for Qwen-Image, Qwen-Image-Edit, LTX-Video, Wan, FLUX, SDXL, or other diffusion base models. Also triggers…

huggingface/skills · 187 tokens

baoyu-danger-gemini-web

Generates images and text via reverse-engineered Gemini Web API. Supports text generation, image generation from prompts, reference images for vision input, and multi-turn conversations. Use when other skills need image generation backend, or when user requests "generate image with Gemini", "Gemini text generation"…

JimLiu/baoyu-skills · 74 tokens

seedance-antislop

This skill should be used when a Seedance 2.0 prompt contains generic AI filler, hollow superlatives, vague cinematic language, bloated adjectives, weak verbs, or needs sharper production-specific wording.

Emily2040/seedance-2.0 · 48 tokens

seedance-filter

This skill should be used when a Seedance 2.0 prompt is blocked, rejected, silently degraded, or likely to trigger a content filter; or when the user asks for a safer rewrite without losing the creative intent.

Emily2040/seedance-2.0 · 49 tokens

seedance-vocab-en

This skill should be used when an English Seedance 2.0 prompt is slop-heavy, generic, padded with empty quality words, tripping false-positive filters, or needs precise English production vocabulary for camera, lighting, motion, VFX, audio, and constraints.

Emily2040/seedance-2.0 · 61 tokens