Mcpppttranslator MCP Server

A Model Context Protocol (MCP) service that provides PowerPoint translation capabilities using AWS Bedrock models.

Local serverstdioPython

What is the Mcpppttranslator MCP server?

Connect Mcpppttranslator to Claude, Cursor or any other MCP client and it stops being a tab you switch to. A Model Context Protocol (MCP) service that provides PowerPoint translation capabilities using AWS Bedrock models. The mcpppttranslator mcp server is what makes that connection.

What the server does

  • 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

Installation

Setup follows the usual MCP pattern — install or clone the server, register it in your client's configuration file, restart the client.

Available tools

The toolset is worth reading before you wire it up, because it tells you what the integration is really for:

  • 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)

Credentials and setup notes

Configuration is passed through the environment: AWS_REGION, DEFAULT_TARGET_LANGUAGE, AWS_ACCESS_KEY_ID, AWS_SECRET_ACCESS_KEY. Treat anything key-shaped as a real credential — scope it to the minimum the server needs, and rotate it if it ever lands in a shared config.

  • Python 3.8+ - AWS account with Bedrock access - AWS credentials configured (via aws configure or environment variables)

Worth knowing first

  • It runs with your machine's permissions. That is convenient and also the reason to think about what you point it at before you approve a tool call.
  • Missing credentials fail quietly in some clients — if no tools show up, check the environment block first.
  • Keep per-call confirmation enabled while you learn its behaviour; it is the cheapest safeguard you have.

Where it fits

Plenty of cloud and infrastructure servers cover similar ground. The differences that matter in practice are scope of access and how much setup stands between you and a working tool call. Mcpppttranslator's toolset — input_file, target_language, output_file and 1 more — is a fair guide to whether it matches your workflow. It is maintained by zhuermu; worth a glance at recent repository activity before you build anything load-bearing on it.

We check each listing at SyncDev against the project's documentation before it goes live — if something here drifts out of date, it is a bug worth reporting.

Available tools

ToolWhat it does
input_filePath to the input PowerPoint file (required)
target_languageTarget language code (default: zh-CN)
output_filePath to save the translated file (optional)
translation_methodTranslation method, 'nova' or 'claude' (default: nova)

Configuration

  • Python 3.8+ - AWS account with Bedrock access - AWS credentials configured (via aws configure or environment variables)
VariableDescriptionRequired
AWS_REGIONConfiguration value read at startup.Optional
DEFAULT_TARGET_LANGUAGEConfiguration value read at startup.Optional
AWS_ACCESS_KEY_IDCredential the server authenticates with.Yes
AWS_SECRET_ACCESS_KEYCredential the server authenticates with.Yes

Example prompts to try

  • Use Mcpppttranslator to input file.
  • Use Mcpppttranslator to target language.
  • Use Mcpppttranslator to output file.

Frequently asked questions

It connects Mcpppttranslator to MCP-compatible AI assistants such as Claude and Cursor, exposing 4 tools (input_file, target_language, output_file, and more) that the assistant can call on your behalf. Instead of copying data back and forth by hand, the assistant works with Mcpppttranslator directly.