PPT Translator

Provides PowerPoint translation using Amazon Bedrock, preserving formatting and enabling FastMCP integration.

python

GitHub Stars

python

Language

6 months ago

First Indexed

2 months ago

Catalog Refreshed

Documentation & install

Readme and setup notes from the catalogue, plus a client-ready config you can copy for your MCP host.

Installation

Add the following to your MCP client configuration file.

Configuration

View docs

{
  "mcpServers": {
    "daekeun-ml-ppt-translator": {
      "command": "uv",
      "args": [
        "run",
        "mcp_server.py"
      ],
      "env": {
        "DEBUG": "false",
        "AWS_REGION": "us-east-1",
        "BATCH_SIZE": "20",
        "MAX_TOKENS": "4000",
        "AWS_PROFILE": "default",
        "TEMPERATURE": "0.1",
        "BEDROCK_MODEL_ID": "us.anthropic.claude-3-7-sonnet-20250219-v1:0",
        "ENABLE_POLISHING": "true",
        "CONTEXT_THRESHOLD": "5",
        "DEFAULT_TARGET_LANGUAGE": "ko"
      }
    }
  }
}

You can run a PowerPoint translation service that uses Amazon Bedrock models to translate slides while preserving formatting. This MCP server can operate as a standalone command-line tool or be integrated with AI assistants through FastMCP, enabling seamless translation workflows for PowerPoint content.

How to use

Connect to the PowerPoint translation MCP server from your MCP client. You can run the server locally and then send translation requests for entire presentations, specific slides, or batches of PowerPoint files. Use the server to translate content while maintaining formatting, fonts, and styles.

How to install

Prerequisites you need before starting: Python 3.11 or higher, an AWS account with Bedrock access, and AWS CLI configured with credentials.

Install the MCP server package by cloning the repository, installing dependencies, and preparing the environment.

Configuration and usage notes

The PowerPoint translation service relies on environment variables to control language, model, and processing parameters. You will configure AWS credentials, Bedrock model IDs, and translation settings. The server supports running in FastMCP mode and exposes translation actions you can approve and invoke from an AI assistant.

Key environment variables include region, profile, the default target language, and the Bedrock model to use. You can adjust token limits, temperature, batch size, and post-processing options to tailor translations to your needs.

To run the FastMCP server, choose one of the following runtime commands. The server responds to translation requests, slide information queries, and preview requests from integrated assistants.

Troubleshooting and tips

If you encounter issues connecting to Bedrock or accessing credentials, verify AWS CLI configuration and permissions for Bedrock in your chosen region. Check the FastMCP configuration and ensure the server process has the necessary environment variables. Review logs from the MCP client and server for error messages and confirm the server is running.

Examples

Translate an entire presentation from English to Korean using the MCP server once it is running and connected to your client.

Recommended start commands

uv run mcp_server.py

Alternative start command using Python directly

python mcp_server.py

Available tools

translate_powerpoint

Translate an entire PowerPoint presentation while preserving formatting and styles.

translate_specific_slides

Translate only specific slides within a PowerPoint presentation.

get_slide_info

Retrieve metadata and a preview overview of slides in a presentation.

get_slide_preview

Get a detailed preview for a specific slide.

list_supported_languages

List all languages supported for translation.

list_supported_models

List all supported Amazon Bedrock models.

get_translation_help

Provide help information for using the translator.

Built by

VeilStrat

AI signals for GTM teams