Ketchup Draw 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., "@Ketchup Draw MCP Server draw a cute cat in cyberpunk style"
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.
Ketchup Draw MCP Server
这是一个 MCP (Model Context Protocol) 服务器,集成了 Ketchup AI 的专业绘图能力和 URUSAI! 的图床服务。
它可以让 Claude Desktop 等 MCP 客户端具备“画图”能力:不仅仅是生成图片,还能自动优化提示词,并将生成的图片自动上传至云端,返回可永久访问的 URL。

✨ 特性
智能提示词优化 (Prompt Engineering): 将简单的中文/英文短语(如“一只可爱的狗”)自动改写为包含光影、风格、细节描述的专业绘图提示词。
高质量绘图 (AI Generation): 调用 Ketchup AI 引擎生成高分辨率图像。
自动图床上传 (Auto Upload): 生成的图片会自动上传至 URUSAI!,并在对话中直接展示图片预览,同时提供永久链接。
代理支持 (Proxy Support): 内置
undici代理配置,完美解决国内网络环境下无法访问 URUSAI! 或 API 的问题。
Related MCP server: Replicate Minimax Image-01 MCP Server
🧰 工具详情 (Tools)
本服务器向 MCP 客户端暴露了以下两个工具,大模型可根据上下文自动调用:
1. optimize_prompt
用于将用户的简短描述转化为专业的英文绘图提示词。
描述: Optimize a simple drawing prompt into a detailed professional prompt using Ketchup AI.
输入参数 (Input Schema):
参数名 | 类型 | 必填 | 说明 |
|
| ✅ | 需要优化的原始提示词(例如:"cyberpunk city at night" 或 "赛博朋克城市") |
2. generate_image
用于执行实际的绘图操作并上传。
描述: Generate an image using Ketchup AI and upload it to URUSAI!. Returns the image URL.
输入参数 (Input Schema):
参数名 | 类型 | 必填 | 说明 |
|
| ✅ | 详细的绘图提示词(建议先调用 |
|
| ✅ | 图片比例,必须是下方列表中的值之一(如 |
📐 支持的图片比例 (ratio)
在调用 generate_image 时,ratio 参数支持以下枚举值:
比例代码 | 尺寸 (WxH) | 适用场景 |
1x1 | 1024 x 1024 | 头像、Instagram |
16x9 | 1344 x 768 | 壁纸、视频封面 |
9x16 | 768 x 1344 | 手机壁纸、Stories |
4x3 | 1152 x 896 | 传统照片 |
3x4 | 896 x 1152 | 肖像 |
21x9 | 1536 x 640 | 电影宽银幕 |
9x21 | 640 x 1536 | 长条幅 |
3x2 | 1280 x 832 | 风景 |
2x3 | 832 x 1280 | 海报 |
🚀 使用方法 (Claude Desktop)
无需克隆代码,直接修改 Claude Desktop 的配置文件即可使用 npx 运行。
1. 找到配置文件
Windows:
%APPDATA%\Claude\claude_desktop_config.jsonmacOS:
~/Library/Application Support/Claude/claude_desktop_config.json
2. 添加配置
将以下内容添加到 mcpServers 对象中:
{
"mcpServers": {
"ketchup-draw": {
"command": "npx",
"args": [
"-y",
"ketchup-draw-mcp-server"
],
"env": {
"HTTPS_PROXY": "http://127.0.0.1:7890"
}
}
}
}⚠️ 网络配置重要提示: 由于 URUSAI! 和 Ketchup AI 的服务器在海外,如果你在中国大陆,必须配置
env中的HTTPS_PROXY。
请将
127.0.0.1:7890替换为你本地代理软件(如 Clash, v2rayN 等)的实际 HTTP 端口。如果没有配置代理,图片上传大概率会失败。
🛠️ 本地开发
如果你想贡献代码或进行本地调试:
# 1. 克隆仓库
git clone https://github.com/Komorebi-yaodong/ketchup-draw-mcp-server.git
cd ketchup-draw-mcp-server
# 2. 安装依赖
pnpm install
# 3. 编译
pnpm build
# 4. 运行
node dist/index.jsLicense
Available Tools
2 toolsgenerate_imageA
Generate images based on a list of prompts. Each prompt in the list generates one image.
Inputs: ratio (required), prompts (required).
optimize_promptA
Optimize a simple drawing prompt into a detailed professional prompt using Ketchup AI.
Inputs: prompt (required).
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 clearly distinct roles: optimize_prompt refines a prompt, while generate_image produces images from prompts. There is no overlap in functionality.
Both tools follow the same verb_noun pattern: optimize_prompt and generate_image. This is consistent and predictable.
With only two tools, the server feels minimal. While the tools cover a basic prompt-to-image workflow, the count is borderline for a full-featured server.
The core workflow of optimizing a prompt and generating an image is covered. Minor gaps exist, such as no options for adjusting generation parameters, but the essential functionality is present.
Related MCP Connectors
Generate, edit and upscale images with references, batch jobs, cost previews and original downloads.
Generate and upscale AI images, videos and audio.
Generate and upscale AI images, video and audio with leading models, right from your AI chat.
Generate AI images, video, music, and sound effects, and upscale them, from any MCP client.
Related MCP Servers
- AlicenseNot gradedqualityDmaintenanceEnables AI image generation through multiple providers including OpenAI GPT-Image-1, Google Imagen 4, Gemini 2.5 Flash (Nano Banana), Flux 1.1, Qwen Image, and SeedDream-4, supporting various formats, sizes, and advanced features like background control and seed-based reproduction.59 npm11MIT
- AlicenseNot gradedqualityNot gradedmaintenanceEnables AI image generation using the minimax/image-01 model via Replicate API. Supports multiple aspect ratios, batch generation of up to 9 images, prompt optimization, and character reference images for consistent character generation.-
- FlicenseNot gradedqualityDmaintenanceEnables MCP-compatible clients like Claude or ChatGPT to generate images from text prompts using AI, with options for aspect ratio and quality.-
- AlicenseAqualityDmaintenanceEnables AI image generation via multiple providers (Yunwu, Gemini) with customizable aspect ratios, resolutions, and output settings, seamlessly integrating with MCP-compatible clients.111 npmMIT