Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/xinvxueyuan/NovelAI-Image-MCPnpx agentmods add skills/xinvxueyuan/novelai-image-mcp/novelai-cliWrote 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.
[](https://agentmods.dev/skills/xinvxueyuan/novelai-image-mcp/novelai-cli)<a href="https://agentmods.dev/skills/xinvxueyuan/novelai-image-mcp/novelai-cli"><img src="https://agentmods.dev/badge/skills/xinvxueyuan/novelai-image-mcp/novelai-cli/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.
<a href="https://agentmods.dev/skills/xinvxueyuan/novelai-image-mcp/novelai-cli"><img src="https://agentmods.dev/badge/skills/xinvxueyuan/novelai-image-mcp/novelai-cli.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00044 | $0.03255 |
| Opus 5 | $0.00022 | $0.01628 |
| Sonnet 5 | $0.00009 | $0.00651 |
| Haiku 4.5 | $0.00004 | $0.00326 |
Grade A, and why
novelai-cli 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.
How it starts
The opening of the file, as written. The whole thing — 298 lines — stays where its author put it; the contents beside it link to each section on GitHub.
novelai-cli
Instructions for the agent to follow when driving the NovelAI image CLI from a shell.
When to use
Use this skill when driving NovelAI image generation from a shell script, CI job, or one-off command instead of through an MCP host like Claude Desktop. The novelai-image-mcp package ships a Typer-based sync CLI (entry point: novelai-image-mcp) that wraps the same async NovelAIClient the MCP server uses. This skill covers the CLI only — for the MCP tool interface (the 11 registered tools exposed over stdio / streamable-http), see the novelai-mcp-tools skill instead, and do not duplicate that reference here.
Instructions
- Install the CLI — see Installation.
- Configure credentials — see Credentials.
- Run a command — see Commands for the six subcommands (
serve,generate,upscale,director,annotate,info). - Read the output — see Output behavior.
Installation
# From PyPI
pip install novelai-image-mcp
# Or run ad-hoc without installing
uvx novelai-image-mcp <command>
# From source (monorepo)
uv sync
uv run --directory apps/server novelai-image-mcp <command>
Credentials
The CLI needs exactly one auth method configured via environment variables
(see .env.example):
- Preferred —
NOVELAI_TOKEN: a persistent API token. Get it from https://novelai.net > Account (thepst-...string). - Fallback —
NOVELAI_USERNAME+NOVELAI_PASSWORD: the access key is derived with argon2id. Requiresargon2-cffi(a core dependency).
If neither is set, every command (except serve without credentials loaded)
exits with code 2 and prints a reminder. Set credentials inline for one-shot
use:
export NOVELAI_TOKEN=pst-xxxxxxxxxxxxxxxx
novelai-image-mcp info
Useful environment variables
All are optional; defaults shown.
| Variable | Default | Purpose |
|---|---|---|
NOVELAI_TOKEN |
— | API token (preferred auth) |
NOVELAI_USERNAME / NOVELAI_PASSWORD |
— | Alt auth (derived) |
NOVELAI_OUTPUT_DIR |
outputs |
Where PNGs are saved |
NOVELAI_DEFAULT_MODEL |
nai-diffusion-4-5-full |
Default model id |
NOVELAI_DEFAULT_WIDTH / NOVELAI_DEFAULT_HEIGHT |
832 / 1216 |
Default size |
NOVELAI_DEFAULT_STEPS |
28 |
Default step count |
NOVELAI_DEFAULT_SCALE |
5.0 |
Default CFG scale |
NOVELAI_DEFAULT_SAMPLER |
k_euler_ancestral |
Default sampler |
NOVELAI_TIMEOUT |
120 |
HTTP timeout (seconds) |
MCP_TRANSPORT |
stdio |
serve transport (stdio or streamable-http) |
MCP_HOST / MCP_PORT |
127.0.0.1 / 8000 |
serve HTTP bind |
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.
- 12d ago First seen · 298 lines · 44 tokens per session scan A 0bc3ed5862ed
novelai-cli is a skill published in the GitHub repository xinvxueyuan/NovelAI-Image-MCP (4 stars, last pushed yesterday), licensed MIT. It adds 44 tokens to every session and 3,255 once invoked, about $0.0002 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.
Other skills, from other repositories
officecli-word-form
Use this skill to create fillable Word forms (.docx) with real Content Controls (SDT) + legacy FormField checkboxes + MERGEFIELD mail-merge placeholders + document protection. Trigger on: 'fillable form', 'form fields', 'content controls', 'SDT', 'word form', 'fill in', 'only editable fields', 'protect document'…
new
Create a new project to start development quickly.
oss-upload
Upload local files to Tencent COS (oss.1024code.com CDN) using coscli. Use when user wants to upload a file to CDN/OSS, or deploy static assets.
agent-coverage-check
Check agent configuration coverage across hierarchy levels and phases. Use to ensure complete agent system coverage.
meeting-summarizer
Summarize a completed meeting from its transcript. Produces a structured summary with key decisions, action items, and discussion highlights. Triggered automatically when a meeting ends.
openagentskill-registry
Discover, compare, audit, and safely install reusable AI Agent Skills with OpenAgentSkill. Use whenever an agent needs a capability it does not already have, must compare Skill alternatives, or needs evidence before installing third-party instructions.