About Wujieai Mcp Server
Wujieai Mcp Server connects Wujie AI image generation models and model details to MCP. It is for users generating images through MCP clients, with configurable dimensions and generation parameters.
Key features
- 01Generate images with multiple models
- 02View model descriptions
- 03Set image dimensions
- 04Adjust sampling and prompt parameters
Use cases
- 01Generate images from prompts
- 02Explore Wujie AI image models
- 03Adjust image size and generation settings
MCP support
The server exposes image generation and model information to MCP clients, including the generate_image tool.
Configuration
Local server config is the same for every client. Copy it into your client’s MCP config file.
Tools
3Saved tool list · updated 3w ago
| Parameter | Type | Required | Description |
|---|---|---|---|
| cfg | number | No | Prompt relevance, range [1-30], default 7. (Optional) |
| num | number | No | Number to generate, default 1 image |
| seed | string | No | Random seed, the seed for generating images; defaults to -1 for random generation. (Optional) |
| model | string | No | Model code; defaults to the general-purpose FLUX model |
| steps | number | No | Sampling steps; defaults to 20. (Optional) |
| width | enum | No | Image width; defaults to 512. (Optional)512 | 768 | 1024 | 1360 |
| height | enum | No | Image height; defaults to 512. (Optional)512 | 768 | 1024 | 1360 |
| prompt | string | Yes | Image description; including style and details is recommended |
| uc_prompt | string | No | Negative image description. (Optional) |
| sampler_index | number | No | The sampling mode refers to the sampling mode of the diffusion denoising algorithm. (Optional) |
| init_image_url | string | No | Base image URL. (Optional) |
Details
From the project README无界AI生图的MCP服务集成指南
一、服务核心功能
- AI图像生成：通过MCP协议，可调用无界AI数十种模型生成图像
- 模型信息列表：可查看无界AI数十种作画生图模型介绍
- 多分辨率支持：支持512~4094主流尺寸的任意宽高组合
- 参数自定义：可调节采样步数、采样器类型、提示词相关性等专业参数
二、快速接入流程
步骤1：获取API密钥
- 访问无界AI控制台
- 注册/登录后进入「开发者中心」
- 在「密钥管理」模块创建新密钥
- 记录生成的
WUJIEAI_API_KEY
步骤2 ：环境准备
# 验证Node.js环境（要求v18.0.0或更高版本）
node -v
步骤3：Server服务配置
# 本地客户端（推荐）
{
"mcpServers": {
"mcp-server-wujieai": {
"command": "npx",
"args": ["-y", "wujieai-mcp-server"],
"env": {
"WUJIEAI_API_KEY": ${YOUR_API_KEY}
}
}
}
}
# HTTP SSE长连接
{
"mcpServers": {
"wujie-ai-sse": {
"url": "https://pref-gate.wujieai.com/open-platform-mcp/sse?key=${YOUR_API_KEY}"
}
}
}
三、开发调用示例
const result = await client.callTool({
name: "generate_image",
arguments: {
prompt: "一只优雅地坐着的猫",
model: "1013"
}
});
四、最佳实践建议
- 提示词优化：
- 使用权重标记符
( )强化关键元素：(neon lights:1.3)
- 使用权重标记符
五、技术支持
- 官方创作中心：https://www.wujieai.cc
- 官方文档中心：https://apifox.com/apidoc/shared/ecc069df-a9d5-4c86-b723-6dcd5cc79f81
- 开发者交流钉钉群：https://cdn.wujiebantu.com/openapi/WechatIMG491.jpg
注：具体API参数请以最新版文档为准。建议通过
npm update @wujieai/wujieai-mcp-server保持SDK版本同步更新。
Comments
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.