Qwen Image MCP Server
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., "@Qwen Image MCP Server Generate a watercolor painting of a mountain lake at sunset"
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.
Qwen Image 3.0 MCP Server
基于阿里云百炼 DashScope API 的千问图像生成与编辑 MCP 服务,提供文生图(T2I)和图生图/图像编辑(I2I)能力。
功能
工具 | 功能 | 说明 |
| 文生图(T2I) | 根据文本提示词直接生成图像 |
| 图生图/图像编辑(I2I) | 基于 1-3 张参考图结合编辑指令进行精确编辑 |
模型选择
模型 | 特点 |
| 高质量,适合精细创作 |
| 兼顾质量与速度,适合快速生成 |
Related MCP server: Doubao Image/Video Generation MCP Server
前提条件
安装
uvx(无需安装,直接运行)
uvx qwen-image-mcppip
pip install qwen-image-mcp本地开发
git clone https://github.com/wchiway/qwen-image-mcp
cd qwen-image-mcp
uv sync配置
通过环境变量配置 API Key:
export DASHSCOPE_API_KEY="sk-xxxxxxxxxxxx"或创建 .env 文件:
# 必填:阿里云百炼 API Key
DASHSCOPE_API_KEY=sk-xxxxxxxxxxxx
# 可选:业务空间 ID(推荐,性能更优)
WORKSPACE_ID=
# 可选:地域(默认 cn-beijing)
REGION=cn-beijing使用方式
MCP 客户端配置(推荐)
在 Claude Code 的 settings.json 中添加:
{
"mcpServers": {
"qwen-image": {
"command": "uvx",
"args": ["qwen-image-mcp"],
"env": {
"DASHSCOPE_API_KEY": "sk-你的key",
"WORKSPACE_ID": "",
"REGION": "cn-beijing"
}
}
}
}uvx 直接运行
uvx qwen-image-mcp本地安装运行
qwen-image-mcp工具参考
generate_image — 文生图
参数 | 类型 | 必填 | 默认值 | 说明 |
| string | ✅ | — | 正向提示词,描述图像内容、风格和构图,支持中英文 |
| string | — |
| 模型名称 |
| string | — | 自动推荐 | 输出分辨率,格式 |
| integer | — | 1 | 生成数量(1-6) |
| boolean | — | true | 提示词智能改写 |
| string | — | direct | 改写方式: |
| string | — | — | 反向提示词 |
| integer | — | — | 随机种子(0-2147483647) |
| boolean | — | false | 是否添加水印 |
edit_image — 图生图/图像编辑
参数 | 类型 | 必填 | 默认值 | 说明 |
| string | ✅ | — | 编辑指令,描述期望的编辑效果,支持中英文 |
| string[] | ✅ | — | 参考图像列表(1-3 张),URL 或 Base64 |
| string | — |
| 模型名称 |
| string | — | 自动推荐 | 输出分辨率,格式 |
| integer | — | 1 | 生成数量(1-6) |
| boolean | — | true | 提示词智能改写 |
| string | — | direct | 仅支持 |
| string | — | — | 反向提示词 |
| integer | — | — | 随机种子(0-2147483647) |
| boolean | — | false | 是否添加水印 |
图像输入格式
公网 URL:
https://example.com/image.pngBase64 编码:
data:image/png;base64,iVBORw0KGgo...支持格式:JPG、JPEG、PNG、BMP、TIFF、WEBP、GIF
单张不超过 10MB,分辨率建议 384-2048 像素
环境变量
变量 | 必填 | 默认值 | 说明 |
| ✅ | — | 阿里云百炼 API Key |
| — | — | 业务空间 ID,不设则使用旧域名 |
| — |
| 地域: |
| — |
| API 请求超时(秒) |
| — |
| 日志级别: |
示例
文生图 — 生成一张风景照
prompt: "一幅秋日山间晨雾的风景摄影,暖金色阳光穿透薄雾,远山层叠,前景有金黄色的落叶松林"图生图 — 人物换装
images: ["https://example.com/portrait.jpg"]
prompt: "保留人物面部特征,将服装换为深蓝色商务西装,背景改为现代办公室"图生图 — 风格转换
images: ["https://example.com/photo.jpg"]
prompt: "将这张照片转换为宫崎骏动画风格,保持构图不变"响应格式
成功返回的图像 URL 有效期为 24 小时,请及时下载保存。
✅ 文生图完成
**图像 1**
- URL(24h 有效): https://dashscope-result-sz.oss-cn-shenzhen.aliyuncs.com/xxx.png
分辨率: 1024×1024
生成数量: 1
输入图片数: 0
request_id: 571ae02f-5c9d-436c-83c2-f221e6df0xxx技术栈
Python 3.10+
MCP Python SDK 2.0+
uv — 包管理与构建
许可证
MIT
Available Tools
2 toolsedit_imageA
图生图 / 图像编辑(I2I)— 基于 1-3 张参考图结合编辑指令进行精确编辑。
可传入图像 URL 或 Base64 编码,模型会根据文本指令对参考图进行编辑生成。 适用于: 换装、换背景、风格转换、人物保留编辑等场景。
Inputs: images (required), prompt (required), n, seed, +6 more. Returns: result
generate_imageA
文生图(T2I)— 根据文本提示词直接生成图像。
支持中英文提示词,模型会自动根据提示词推荐分辨率。 prompt_extend 默认开启,会对简单提示词进行智能改写以获得更好的效果。
Inputs: prompt (required), n, seed, size, +5 more. Returns: result
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 2 tools
The two tools have completely distinct purposes: generate_image creates images from text prompts, while edit_image modifies existing images using reference images and instructions. There is no overlap or ambiguity between them.
Both tools follow the exact same verb_noun pattern with clear, descriptive verbs: generate_image and edit_image. The naming is predictable and consistent.
Only two tools is on the thinner side, but they cover the two core capabilities of the Qwen image model (text-to-image and image-to-image editing). The server is narrowly scoped and each tool is essential, making the count reasonable for its purpose.
For the domain of image generation and editing, the server provides both fundamental operations. There are no obvious missing functions like image variation or upscaling, but the core workflows of generating from text and editing reference images are fully covered.
Maintenance
Related MCP Connectors
Create images and videos from prompts, with options for image mixing, reference images, and start/…
Generate images and videos with Kling AI Global via OAuth. Generation uses account credits.
Generate images and videos (GPT Image, Seedance, Kling, Wan, Qwen) with one API key.
Image generation, image editing and text/image-to-video with credit quotes and connection budgets.
Related MCP Servers
- AlicenseCqualityDmaintenanceEnables users to generate high-quality images using ModelScope's Qwen-Image model through natural language prompts. Supports async task processing with both image URL and base64 encoded data output options.12MIT
- AlicenseAqualityDmaintenanceEnables AI image generation using Doubao Seedream models and video generation using Doubao Seedance models through Volcano Engine's API, supporting text-to-image, image-to-image, text-to-video, and task status queries.342 npm4MIT
- AlicenseBqualityDmaintenanceEnables text-to-image generation through the ModelScope platform using the Qwen/Qwen-Image model. It supports customizable parameters such as negative prompts, resolution, and sampling steps within MCP-compatible clients.116 npm1MIT
- AlicenseAqualityBmaintenanceEnables image editing, remixing, and text-to-image generation using Qwen 2 models via RunAPI. Supports task polling and pricing checks.5109 npmApache 2.0