Manga-Translation-MCP
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., "@Manga-Translation-MCPTranslate the manga in D:/comics/chapter1 and save to D:/comics/translated"
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.
Manga-Translation-MCP
基于 MCP(Model Context Protocol)的自动化漫画翻译服务器。通过组合 RT-DETR 文字区域检测与 GLM-OCR 光学字符识别,自动完成漫画中文字区域的定位、文字提取、翻译请求编排,并将译文回填到漫画图像中。
⚠️ 重要提示:
1.后端使用的模型必须支持多模态推理,否则无法识别图像。
2.yolo_server.py 在运行过程中会通过 mcp_rpc_utils 的 sendRequest 向 LLM 持续发送翻译请求。由于 市面大多数agent 原生不支持流程化的自我调用,本 MCP 必须搭配 特定deepseek Harness插件。
开始
创建虚拟环境(推荐)
# Windows
python -m venv venv
venv\Scripts\activate
# Linux / macOS
python3 -m venv venv
source venv/bin/activate安装依赖
安装 PyTorch 2.13.0+cu132
pip3 install torch torchvision --index-url https://download.pytorch.org/whl/cu132这里使用的pytorch版本较高,如有需要可自行降级。
pip install -r requirements.txt下载模型文件
从huggingface或其它途径下载运行服务时所需的模型文件: ogkalu/comic-text-and-bubble-detector zai-org/GLM-OCR
将其放入项目中对应的文件夹。
配置mcp服务示例
在agent的配置文件中:
{
"mcpServers": {
"yoloServer": {
"type": "stdio",
"command": "C:/你的mcp服务所在目录/.venv/Scripts/python.exe",
"args": ["C:/你的目录mcp服务所在/yolo_server.py"]
}
}
}
This server cannot be deployed
Maintenance
Related MCP Connectors
Create manga and anime art from text. 24 styles, multi-panel stories, BYOK.
OCR and document understanding: extract text from images, then summarize or translate it.
LLM chat, text tools, image generation, editing, batch image jobs, and asynchronous video generation
Turn any LLM multimodal; generate images, voices, videos, 3D models, music, and more.
Related MCP Servers
- AlicenseAqualityDmaintenanceEnables vision LLMs to read PDFs by automatically detecting text corruption and switching between text extraction and image rendering modes, while preserving reading order and filtering unnecessary images to prevent token overflow.3MIT
- AlicenseNot gradedqualityCmaintenanceA local MCP server that gives LLMs eyes for images by performing object detection (YOLOv8) and text recognition (EasyOCR), outputting descriptive statements about objects and text positions without any API key or cloud dependency.MIT
- AlicenseNot gradedqualityBmaintenanceEyes for text-only LLMs: decodes screenshots into exact structured text (words, coordinates, sizes, colors) using pure-code CV and OCR. Enables text-only models to reason about UI layouts without vision models or VRAM usage.2MIT
- FlicenseNot gradedqualityCmaintenanceEnables generating original English-dialogue manga with configurable Japanese art styles through an MCP server, including story scripting, panel image generation, and page composition.-