PowerPoint Translator MCP Service
Enables translation of PowerPoint presentations to multiple languages using AWS Bedrock models while preserving formatting. Supports 8 languages including Chinese, Japanese, Korean, and major European languages.
README
PowerPoint Translator MCP Service
A Model Context Protocol (MCP) service that provides PowerPoint translation capabilities using AWS Bedrock models.
Features
- Translate PowerPoint presentations to multiple languages
- Preserve formatting during translation
- Support for AWS Bedrock Nova models
- Intelligent handling of proper nouns, brand names, and special content
- Full MCP protocol compliance with proper initialization and tool handling
- Fallback implementation when MCP library is not available
Supported Languages
- Simplified Chinese (zh-CN)
- Traditional Chinese (zh-TW)
- English (en)
- Japanese (ja)
- Korean (ko)
- French (fr)
- German (de)
- Spanish (es)
Prerequisites
- Python 3.8+
- AWS account with Bedrock access
- AWS credentials configured (via
aws configureor environment variables)
Installation
Quick Setup
# Clone the repository
git clone https://github.com/yourusername/mcpppttranslator.git
cd mcpppttranslator
# Install dependencies
python server.py --install-deps
# Or use uv for faster installation
python server.py --install-deps --use-uv
Virtual Environment Setup (Recommended)
# Create virtual environment with uv
python server.py --install-deps --use-uv --venv
# Or specify custom path
python server.py --install-deps --use-uv --venv --venv-path /path/to/custom/venv
MCP Configuration
Option 1: AWS CLI Configuration (Recommended)
First, configure your AWS credentials:
aws configure
Then add to your Amazon Q configuration:
{
"mcpServers": {
"ppt-translator": {
"timeout": 300,
"type": "stdio",
"command": "python",
"args": [
"/path/to/mcpppttranslator/server.py",
"--mcp"
],
"env": {
"AWS_REGION": "us-east-1",
"DEFAULT_TARGET_LANGUAGE": "zh-CN"
}
}
}
}
Option 2: Direct Credential Configuration
{
"mcpServers": {
"ppt-translator": {
"timeout": 300,
"type": "stdio",
"command": "python",
"args": [
"/path/to/mcpppttranslator/server.py",
"--mcp"
],
"env": {
"AWS_ACCESS_KEY_ID": "your-access-key",
"AWS_SECRET_ACCESS_KEY": "your-secret-key",
"AWS_REGION": "us-east-1",
"DEFAULT_TARGET_LANGUAGE": "zh-CN"
}
}
}
}
Usage
With Amazon Q
Once configured, you can use natural language commands:
Translate my presentation.pptx to Japanese using the Nova model
Command Line Usage
# Run in MCP mode
python server.py --mcp
# Direct translation
python server.py --translate --input-file presentation.pptx --target-language ja
# List supported languages
python server.py --list-languages
Available Tools
-
translate_ppt - Translate a PowerPoint document
input_file: Path to the input PowerPoint file (required)target_language: Target language code (default: zh-CN)output_file: Path to save the translated file (optional)translation_method: Translation method, 'nova' or 'claude' (default: nova)
-
list_supported_languages - List all supported target languages
Command Line Arguments
--mcp: Run in MCP mode--translate: Translate a PowerPoint file--input-file: Path to the input PowerPoint file--target-language: Target language code--output-file: Path to save the translated file--model-id: Translation model ID (choices: 'amazon.nova-micro-v1:0', 'amazon.nova-lite-v1:0')--list-languages: List supported languages--install-deps: Install required dependencies--use-uv: Use uv package manager instead of pip--venv: Create and use a virtual environment with uv--venv-path: Path for the virtual environment (default: ./venv)
Testing
Test the MCP server functionality:
python test_mcp.py
Troubleshooting
Common Issues
-
AWS Credentials: Ensure AWS credentials are properly configured via
aws configureor environment variables. -
Missing Dependencies: Run
python server.py --install-depsto install required packages. -
MCP Protocol Errors: The server implements full MCP protocol compliance. If you encounter initialization errors, ensure you're using a compatible MCP client.
-
File Permissions: Ensure the server.py file has execute permissions:
chmod +x server.py
Development
Local Development
-
Clone and setup:
git clone https://github.com/yourusername/mcpppttranslator.git cd mcpppttranslator python server.py --install-deps --use-uv --venv -
Test the server:
python test_mcp.py
MCP Protocol Compliance
This server implements the full MCP protocol specification including:
- Proper
initializemethod handling - Standard
tools/listandtools/callmethods - Correct JSON-RPC 2.0 response formatting
- Error handling and graceful degradation
- Backward compatibility with legacy MCP methods
License
MIT
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。