NovelAI MCP Server
Enables AI assistants to generate images using NovelAI, supporting text-to-image, image-to-image, and tag suggestions.
README
NovelAI MCP Server
基于 novelai-python SDK 的 MCP 服务器，为 AI 助手提供 NovelAI 图像生成能力。
✨ 功能
| 工具 | 说明 |
|---|---|
generate_image |
文生图，支持多角色定位、Vibe Transfer、Precise Reference |
img2img |
图生图，基于已有图片变换 |
suggest_tags |
Danbooru 标签搜索/自动补全 |
check_subscription |
查询订阅状态和 Anlas 余额 |
支持模型
| 名称 | 模型 ID | 说明 |
|---|---|---|
v4.5-full |
nai-diffusion-4-5-full | 最新最完整（默认） |
v4.5-curated |
nai-diffusion-4-5-curated | 更干净的数据集 |
v4-full |
nai-diffusion-4-full | V4 Full |
v4-curated |
nai-diffusion-4-curated-preview | V4 预览 |
v3 |
nai-diffusion-3 | V3（老款） |
🚀 快速开始
前置条件
- Python 3.11+
- NovelAI API Key（以
pst-开头，从 novelai.net 获取）
方式一：通过 PyPI 安装（推荐）
# 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
方式二：从源码安装
# 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
运行选项
# 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
调试
# 使用 MCP Inspector
uvx mcp dev src/novelai_mcp/server.py
🔧 接入配置
Claude Desktop / Antigravity / Cursor
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"
}
}
}
}
LobeChat / Dify
启动 HTTP 模式后，在客户端配置：
- URL:
http://localhost:3000/mcp - 传输: Streamable HTTP
🌍 环境变量
| 变量 | 必需 | 说明 |
|---|---|---|
NOVELAI_API_KEY |
✅ | NovelAI API Key |
NOVELAI_SAVE_DIR |
❌ | 图片自动保存目录 |
HTTPS_PROXY |
❌ | HTTPS 代理地址 |
📄 许可证
MIT
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.