Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@NovelAI MCP Server Generate an image of a fantasy castle on a hill with a dragon flying above"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
基于 novelai-python SDK 的 MCP 服务器，为 AI 助手提供 NovelAI 图像生成能力。
工具 | 说明 |
| 文生图，支持多角色定位、Vibe Transfer、Precise Reference |
| 图生图，基于已有图片变换 |
| Danbooru 标签搜索/自动补全 |
| 查询订阅状态和 Anlas 余额 |
名称 | 模型 ID | 说明 |
| nai-diffusion-4-5-full | 最新最完整（默认） |
| nai-diffusion-4-5-curated | 更干净的数据集 |
| nai-diffusion-4-full | V4 Full |
| nai-diffusion-4-curated-preview | V4 预览 |
| nai-diffusion-3 | V3（老款） |
Related MCP server: Artifex MCP
Python 3.11+
NovelAI API Key（以 pst- 开头，从 novelai.net 获取）
# 使用 uvx 直接运行（无需手动安装）
NOVELAI_API_KEY=pst-xxx uvx novelai-mcp
# 或者用 pip 安装
pip install novelai-mcp
NOVELAI_API_KEY=pst-xxx novelai-mcp# 克隆项目
git clone https://github.com/hesoyamlp1/MCP-NovelAI.git
cd MCP-NovelAI
# 使用 uv 安装依赖
uv sync
# 运行
NOVELAI_API_KEY=pst-xxx uv run novelai-mcp# Stdio 模式（默认，Claude Desktop / Antigravity / Cursor）
NOVELAI_API_KEY=pst-xxx novelai-mcp
# HTTP 模式（LobeChat / Dify）
NOVELAI_API_KEY=pst-xxx novelai-mcp --transport streamable-http --port 3000
# 或者使用 .env 文件
cp .env.example .env
# 编辑 .env 填入你的 API Key
novelai-mcp# 使用 MCP Inspector
uvx mcp dev src/novelai_mcp/server.py通过 PyPI（推荐）：
{
"mcpServers": {
"novelai": {
"command": "uvx",
"args": ["novelai-mcp"],
"env": {
"NOVELAI_API_KEY": "pst-xxx"
}
}
}
}从源码：
{
"mcpServers": {
"novelai": {
"command": "uv",
"args": ["run", "--directory", "/path/to/MCP-NovelAI", "novelai-mcp"],
"env": {
"NOVELAI_API_KEY": "pst-xxx"
}
}
}
}启动 HTTP 模式后，在客户端配置：
URL: http://localhost:3000/mcp
传输: Streamable HTTP
变量 | 必需 | 说明 |
| ✅ | NovelAI API Key |
| ❌ | 图片自动保存目录 |
| ❌ | HTTPS 代理地址 |
MIT
This server cannot be deployed
Generate AI images, videos, music, SFX & speech in any AI assistant. Results appear inline in chat.
Generate AI images, video, music, and sound effects, and upscale them, from any MCP client.
Generate AI images and videos from any compatible MCP client.
Create images and videos from prompts, with options for image mixing, reference images, and start/…
