NovelAI Image MCP Server

NovelAI Image MCP

An MCP (Model Context Protocol) server that exposes NovelAI image generation as tools for AI agents (Claude Desktop, Cline, custom agents, remote clients).

Built on the official MCP Python SDK v2 (MCPServer), it lets an agent generate images (txt2img / img2img / inpaint), upscale, run Director tools (line art, emotion, background removal, …), annotate with ControlNet, suggest tags, encode vibes, and query account subscription — all through the standard MCP tool interface.

📖 Documentation: https://xinvxueyuan.github.io/NovelAI-Image-MCP/

Features

• 11 MCP tools covering the full NovelAI image API surface.
• Two transports: stdio (local agents) + streamable-http (remote / multi-client).
• Dual image return: base64 Image content blocks (the agent sees the image) and PNG saved to disk (path returned as text).
• Async + sync: async tool handlers + a typer CLI for direct invocation.
• Monorepo: uv workspace (Python) + pnpm workspace (Node tooling) orchestrated by Turbo; MIT-licensed, Docker-ready, GitHub Pages docs.

Repository layout

This is a uv + pnpm monorepo:

NovelAI-Image-MCP/
├── apps/
│   ├── server/                 # MCP server (the installable PyPI package)
│   │   ├── src/novelai_image_mcp/   # 11 MCP tools + NovelAI HTTP client
│   │   ├── tests/
│   │   ├── docker/              # smoke-test entrypoint
│   │   ├── Dockerfile           # built with repo root as context
│   │   └── pyproject.toml       # ruff / pyright / pytest config
│   └── docs/                    # Sphinx documentation site
│       ├── source/              # MyST Markdown + conf.py
│       ├── Makefile
│       └── pyproject.toml
├── .github/                     # workflows, CODEOWNERS, issue templates
├── pyproject.toml               # uv workspace root (virtual)
├── uv.lock                      # single shared lockfile
├── pnpm-workspace.yaml          # pnpm workspace declaration
├── pnpm-lock.yaml               # Node toolchain lockfile
├── turbo.json                   # cross-workspace task graph
├── package.json                 # root scripts + dev toolchain
└── docker-compose.yml           # local container orchestration

See CONTRIBUTING.md for the developer guide and apps/docs/source/ for the full documentation source.

Quick start

Install from source (development)

# 1. Clone
git clone https://github.com/xinvxueyuan/NovelAI-Image-MCP.git
cd NovelAI-Image-MCP

# 2. Sync the uv workspace (installs server + docs + dev tools)
uv sync

# 3. Configure credentials
cp .env.example .env
#   set NOVELAI_TOKEN=...  (preferred)
#   or  NOVELAI_USERNAME + NOVELAI_PASSWORD

# 4. Run (stdio — for local agents)
uv run python -m novelai_image_mcp serve

# 5. Or over HTTP
MCP_TRANSPORT=streamable-http uv run python -m novelai_image_mcp serve
#   → http://127.0.0.1:8000/mcp

Install from PyPI (runtime only)

pip install novelai-image-mcp
export NOVELAI_TOKEN=pst-...
novelai-image-mcp serve

Optional: Node tooling (contributors)

If you plan to contribute, install the cross-cutting Node toolchain (turbo, husky, markdownlint) via pnpm:

corepack enable pnpm      # one-time
pnpm install --frozen-lockfile

This wires the husky pre-commit + commit-msg hooks and gives you turbo / markdownlint-cli2 for local development. The MCP server has zero Node runtime dependencies — this step is only for contributors.

Connect an agent

The MCP server supports two transports (stdio + http), all configured under mcpServers:

stdio (local agent — Claude Desktop / Cline)

claude_desktop_config.json:

{
  "mcpServers": {
    "novelai-image": {
      "type": "stdio",
      "command": "uv",
      "args": [
        "run",
        "--directory",
        "/path/to/NovelAI-Image-MCP",
        "python",
        "-m",
        "novelai_image_mcp",
        "serve"
      ],
      "env": {
        "NOVELAI_TOKEN": "${input:novelai_token}"
      }
    }
  }
}

Alternative: uvx (published package)

{
  "mcpServers": {
    "novelai-image": {
      "command": "uvx",
      "args": ["--prerelease=allow", "novelai-image-mcp", "serve"],
      "env": { "NOVELAI_TOKEN": "pst-xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx" }
    }
  }
}

Set NOVELAI_TOKEN (or NOVELAI_USERNAME + NOVELAI_PASSWORD) in the host environment before launching — uvx inherits the parent shell env.

http (remote / Docker deployment)

After docker compose up --build (server listens on http://HOST:8000/mcp):

{
  "mcpServers": {
    "novelai-image-http": {
      "type": "http",
      "url": "http://127.0.0.1:8000/mcp",
      "headers": {
        "Authorization": "Bearer pst-xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx"
      }
    }
  }
}

Replace http://127.0.0.1:8000/mcp with your self-deployed endpoint (e.g. https://mcp.example.com/mcp behind a TLS-terminating reverse proxy). Swap the literal token placeholder for a host-managed secret reference if your MCP host supports one (Claude Desktop, Cline, etc. expose this via their own secrets UI).

CLI (sync, for scripting)

uv run python -m novelai_image_mcp generate --prompt "a cat, masterpiece" --width 832 --height 1216
uv run python -m novelai_image_mcp upscale --image ./in.png --factor 4
uv run python -m novelai_image_mcp info          # subscription / Anlas balance
uv run python -m novelai_image_mcp --help

Tools

See the tools reference on the docs site for parameters and examples.

Configuration

All settings are environment variables (see .env.example). Key ones:

NovelAI API reference: https://image.novelai.net/docs/index.html

Development

The project is a uv + pnpm monorepo orchestrated by Turbo. See CONTRIBUTING.md for the full setup; the short version:

uv sync                              # Python workspace (server + docs + dev)
pnpm install --frozen-lockfile       # Node toolchain (turbo + husky + markdownlint)

pnpm check                           # lint + typecheck + test (all workspaces)
pnpm docs:build                       # build the docs site
pnpm server:serve                     # run the MCP server
pnpm docs:serve                       # sphinx-autobuild with live reload

Per-member commands (via uv):

uv run --directory apps/server ruff check src tests    # lint
uv run --directory apps/server -m pyright              # typecheck
uv run --directory apps/server -m pytest               # tests

Docker

docker compose up --build      # builds and runs the server (HTTP transport)

The Dockerfile lives at apps/server/Dockerfile but the build context is the repository root (so uv can resolve the workspace graph). See docker-compose.yml.

Documentation

The Sphinx documentation site is built with Furo + MyST Markdown and auto-deploys to GitHub Pages on every push to main:

• Live site: https://xinvxueyuan.github.io/NovelAI-Image-MCP/
• Source: apps/docs/source/
• Build locally: pnpm docs:serve

License

MIT — see LICENSE. Per-file SPDX annotations live in REUSE.toml. Contributions are subject to the Developer Certificate of Origin (the commit-msg hook signs off commits automatically).