novelai-mcp-tools

novelai-mcp-tools is a skill for Claude Code, Codex from xinvxueyuan/NovelAI-Image-MCP. It costs 56 tokens per session (4,571 once invoked), scanned A, original, MIT.

A set of 11 tools for using NovelAI, an image-generation service, from an AI agent through MCP, a standard way for agents to call external tools.

In plain words
What is it for?
Use it to generate, edit, enlarge, annotate, or inspect NovelAI images during an agent session.
Why use it?
It gives an agent a guided way to choose image models, set generation options, and check the image-generation cost before calling the service.

Skill for Claude CodeCodex

Which agent this was written for is unclear — built for cline. Also seen: built for cline.

Good fit Use it to generate, edit, enlarge, annotate, or inspect NovelAI images during an agent session.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/xinvxueyuan/novelai-image-mcp/novelai-mcp-tools
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 xinvxueyuan/NovelAI-Image-MCP --skill novelai-mcp-tools
Clone the repo
git clone --depth 1 https://github.com/xinvxueyuan/NovelAI-Image-MCP

Made for: Claude Code, Codex.

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.

agentmods badge for novelai-mcp-tools

README.md
[![agentmods](https://agentmods.dev/badge/skills/xinvxueyuan/novelai-image-mcp/novelai-mcp-tools/github.svg)](https://agentmods.dev/skills/xinvxueyuan/novelai-image-mcp/novelai-mcp-tools)
Your own site
<a href="https://agentmods.dev/skills/xinvxueyuan/novelai-image-mcp/novelai-mcp-tools"><img src="https://agentmods.dev/badge/skills/xinvxueyuan/novelai-image-mcp/novelai-mcp-tools/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for novelai-mcp-tools

Your own site · 80×15
<a href="https://agentmods.dev/skills/xinvxueyuan/novelai-image-mcp/novelai-mcp-tools"><img src="https://agentmods.dev/badge/skills/xinvxueyuan/novelai-image-mcp/novelai-mcp-tools.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 56 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,571 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00056 $0.04571
Opus 5 $0.00028 $0.02286
Sonnet 5 $0.00011 $0.00914
Haiku 4.5 $0.00006 $0.00457

Measured 12d ago against content hash e959be26c1bd, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

novelai-mcp-tools 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 12d 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.

skills/novelai-mcp-tools/SKILL.md · 368 lines

How it starts

The opening of the file, as written. The whole thing — 368 lines — stays where its author put it; the contents beside it link to each section on GitHub.

novelai-mcp-tools

Instructions for the agent to follow when invoking NovelAI MCP tools from an MCP host.

When to use

Use this skill when an MCP host (Claude Desktop, Cline, or a custom agent) needs to invoke a single NovelAI tool — picking a model, setting parameters, or generating/transforming an image interactively during an agent session. For shell scripting, batch jobs, or headless pipelines, use the novelai-cli skill instead; for multi-step recipes that orchestrate several tools, use the novelai-workflows skill.

Instructions

  1. Pick the right model — see ### Model selection below for the decision tree.
  2. Set generation parameters — see ### Parameter guide for the full parameter tables.
  3. Check Anlas cost — see ### Anlas cost awareness before expensive generations.
  4. Call the tool — see ### Practical tool-call patterns for examples.

Model selection

Model ids live in Model (nai/constants.py). Pick by quality need and content domain:

Want best overall quality / natural language / multi-character?
  → nai-diffusion-5-full             (V5, best quality, EN/JP natural language,
                                      true alpha; vibes not yet supported)
  → nai-diffusion-5-curated          (V5 curated, tighter aesthetics)

Solid all-rounder with vibes?
  → nai-diffusion-4-5-full            (V4.5, default, supports character_prompts + vibes)
  → nai-diffusion-4-5-curated         (V4.5 curated, tighter aesthetics, fewer Anlas)

Good quality, slightly faster, still V4 family?
  → nai-diffusion-4-full              (V4)
  → nai-diffusion-4-curated-preview   (V4 curated)

Pure anime, fastest, cheapest?
  → nai-diffusion-3                   (V3 anime)

Furry content?
  → nai-diffusion-furry-3             (Furry v3)

Inpainting (any family)?
  → append "-inpainting" to the model id, e.g.
     nai-diffusion-4-5-full-inpainting, nai-diffusion-3-inpainting,
     nai-diffusion-furry-3-inpainting

Endpoint split (handled automatically by the client):

Read the full file on GitHub · 368 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.

  1. 12d ago First seen · 368 lines · 56 tokens per session scan A e959be26c1bd

Subscribe to this mod's changes

novelai-mcp-tools is a skill published in the GitHub repository xinvxueyuan/NovelAI-Image-MCP (4 stars, last pushed yesterday), licensed MIT. It adds 56 tokens to every session and 4,571 once invoked, about $0.0003 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.