crazyrouter-mcp
Access 627+ AI models through one API key — chat with GPT-5/Claude/Gemini, generate images with DALL-E 3/Midjourney/Flux, create videos with Sora 2/Kling/Veo 3, and more via Crazyrouter.
README
Crazyrouter MCP Server — Access 627+ AI Models with One API
One key. 627+ models. Text, image, video, audio, music, 3D — all through MCP.
An MCP (Model Context Protocol) server that gives your AI assistant access to 627+ AI models through Crazyrouter — the unified AI API gateway. Chat with GPT-5, generate images with DALL-E 3, create videos with Sora 2, compose music with Suno V4, and more — all from a single API key.
✨ Features
- 🌐 627+ Models, One API — GPT-5, Claude Opus 4.6, Gemini 3, DeepSeek R1, Llama 4, Qwen3, Grok 4, and hundreds more
- 🎨 Image Generation — DALL-E 3, Midjourney, Flux, Stable Diffusion, Nano Banana Pro
- 🎬 Video Generation — Sora 2, Kling V2, Veo 3, Seedance, Pika
- 🎵 Music Generation — Suno V4, Chirp
- 🗣️ Text-to-Speech & Speech-to-Text — Multiple TTS/STT engines
- 💰 Competitive Pricing — Below official rates for most models
- 🌍 7 Global Edge Nodes — Low latency worldwide
- 🔄 OpenAI + Anthropic + Gemini Protocol Compatible — Drop-in replacement
- ⚡ Credits Never Expire — Pay once, use anytime
🚀 Quick Start
1. Get Your API Key
Sign up at crazyrouter.com and grab your API key.
2. Install
git clone https://github.com/xujfcn/crazyrouter-mcp.git
cd crazyrouter-mcp
npm install
npm run build
3. Configure Your AI Client
<details> <summary><strong>Claude Desktop</strong></summary>
Edit ~/Library/Application Support/Claude/claude_desktop_config.json (macOS) or %APPDATA%\Claude\claude_desktop_config.json (Windows):
{
"mcpServers": {
"crazyrouter": {
"command": "node",
"args": ["/path/to/crazyrouter-mcp/dist/index.js"],
"env": {
"CRAZYROUTER_API_KEY": "your-api-key-here"
}
}
}
}
</details>
<details> <summary><strong>Cursor</strong></summary>
Edit .cursor/mcp.json in your project root:
{
"mcpServers": {
"crazyrouter": {
"command": "node",
"args": ["/path/to/crazyrouter-mcp/dist/index.js"],
"env": {
"CRAZYROUTER_API_KEY": "your-api-key-here"
}
}
}
}
</details>
<details> <summary><strong>VS Code (Copilot)</strong></summary>
Add to your VS Code settings.json:
{
"mcp": {
"servers": {
"crazyrouter": {
"command": "node",
"args": ["/path/to/crazyrouter-mcp/dist/index.js"],
"env": {
"CRAZYROUTER_API_KEY": "your-api-key-here"
}
}
}
}
}
</details>
<details> <summary><strong>Windsurf</strong></summary>
Edit ~/.codeium/windsurf/mcp_config.json:
{
"mcpServers": {
"crazyrouter": {
"command": "node",
"args": ["/path/to/crazyrouter-mcp/dist/index.js"],
"env": {
"CRAZYROUTER_API_KEY": "your-api-key-here"
}
}
}
}
</details>
<details> <summary><strong>OpenClaw</strong></summary>
Add to your OpenClaw MCP config:
{
"mcpServers": {
"crazyrouter": {
"command": "node",
"args": ["/path/to/crazyrouter-mcp/dist/index.js"],
"env": {
"CRAZYROUTER_API_KEY": "your-api-key-here"
}
}
}
}
</details>
🛠️ Available Tools
| Tool | Description | Key Parameters |
|---|---|---|
chat |
Chat with any AI model | model, messages, temperature |
list_models |
List available models by category | category (chat/image/video/audio/music) |
generate_image |
Generate images with AI | prompt, model, size |
generate_video |
Generate videos with AI | prompt, model |
Usage Examples
Chat with any model:
"Use the chat tool to ask GPT-5 to explain quantum computing"
Generate an image:
"Use generate_image to create a sunset over mountains with DALL-E 3"
Generate a video:
"Use generate_video with Kling V2 to create a 5-second clip of ocean waves"
Discover models:
"Use list_models to show me all available image generation models"
📋 Supported Models
💬 Chat / Text Models
| Provider | Models |
|---|---|
| OpenAI | GPT-5, GPT-5-mini, GPT-4.1, GPT-4o, o3, o4-mini |
| Anthropic | Claude Opus 4.6, Claude Sonnet 4, Claude Haiku 3.5 |
| Gemini 3 Pro, Gemini 2.5 Flash, Gemini 2.0 | |
| DeepSeek | DeepSeek R1, DeepSeek V3 |
| Meta | Llama 4 Scout, Llama 4 Maverick |
| Alibaba | Qwen3 235B, Qwen3 32B, Qwen3 Coder |
| xAI | Grok 4, Grok 3 |
| Mistral | Mistral Large, Codestral |
| And more... | 600+ chat models available |
🎨 Image Generation Models
| Model | Description |
|---|---|
| DALL-E 3 | OpenAI's latest image model |
| Midjourney | Industry-leading artistic image generation |
| Flux Pro 1.1 Ultra | Black Forest Labs' flagship model |
| Flux Kontext Pro/Max | Contextual image generation |
| Stable Diffusion 3.5 Large | Stability AI's open model |
| Stable Diffusion XL | Classic high-quality generation |
| Imagen 4.0 | Google's latest image model |
| Imagen 3.0 | Google's proven image model |
🎬 Video Generation Models
| Model | Description |
|---|---|
| Sora 2 | OpenAI's video generation model |
| Kling V2 | Kuaishou's cinematic video model |
| Veo 3 | Google's video generation model |
| Seedance 1.5 Pro | ByteDance's dance video model |
| Pika 1.5 | Creative video generation |
| Runway VIP | Professional video synthesis |
| MiniMax Hailuo 2.3 | MiniMax's video model |
🎵 Music & Audio Models
| Model | Description |
|---|---|
| Suno Music | AI music composition |
| Suno V3 | Music generation model |
| TTS-1 / TTS-1-HD | OpenAI text-to-speech |
| GPT-4o Mini TTS | Latest OpenAI TTS |
| Gemini TTS | Google text-to-speech |
| Whisper-1 | Speech-to-text transcription |
📖 Full model list: crazyrouter.com/models
🔧 Configuration
Environment Variables
| Variable | Required | Description |
|---|---|---|
CRAZYROUTER_API_KEY |
✅ | Your Crazyrouter API key |
API Endpoints
Crazyrouter is OpenAI-compatible, meaning any tool or library that works with OpenAI can work with Crazyrouter by simply changing the base URL:
Base URL: https://crazyrouter.com/v1
This MCP server uses the following endpoints:
POST /v1/chat/completions— Chat completionsGET /v1/models— List available modelsPOST /v1/images/generations— Image generation
🏗️ Development
# Clone the repo
git clone https://github.com/xujfcn/crazyrouter-mcp.git
cd crazyrouter-mcp
# Install dependencies
npm install
# Build
npm run build
# Run
CRAZYROUTER_API_KEY=your-key node dist/index.js
Project Structure
crazyrouter-mcp/
├── src/
│ └── index.ts # MCP server implementation
├── dist/ # Compiled output
├── package.json
├── tsconfig.json
├── LICENSE
└── README.md
🤔 Why Crazyrouter?
| Feature | Crazyrouter | Direct API |
|---|---|---|
| Models Available | 627+ | 1 provider |
| API Keys Needed | 1 | Multiple |
| Protocol Support | OpenAI + Anthropic + Gemini | Varies |
| Pricing | Below official rates | Official rates |
| Credits Expiry | Never | Varies |
| Global Edge Nodes | 7 | Varies |
One API key. All providers. Better prices.
👉 Get started at crazyrouter.com
📄 License
MIT — use it however you like.
🔗 Links
🌏 中文说明
Crazyrouter MCP 服务器 — 一个 API 访问 627+ AI 模型
Crazyrouter MCP 服务器是一个标准的 MCP(模型上下文协议)服务器,让你的 AI 助手(如 Claude Desktop、Cursor、VS Code 等)通过 Crazyrouter AI API 网关 访问 627+ AI 模型。
核心功能:
- 🌐 627+ AI 模型,一个 API Key 搞定
- 🎨 图片生成(DALL-E 3, Midjourney, Flux, Stable Diffusion)
- 🎬 视频生成(Sora 2, Kling V2, Veo 3)
- 🎵 音乐生成(Suno V4)
- 💰 价格低于官方价格
- ⚡ 充值永不过期
快速开始:
- 在 crazyrouter.com 注册获取 API Key
- 克隆仓库并编译
- 配置到你的 AI 客户端(Claude Desktop / Cursor / VS Code)
详细配置请参考上方英文文档。
<p align="center"> Built with ❤️ for the AI community by <a href="https://crazyrouter.com?utm_source=github&utm_medium=mcp&utm_campaign=dev_community">Crazyrouter</a> </p>
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。