Polyglot MCP translate everything, locally.
An MCP server that translates text between 55 languages using TranslateGemma on your GPU via Ollama. No API keys, no cloud, no rate limits — everything runs on your machine.
Translate
translate("Hello world", "en", "ja")
Result
"こんにちは世界" // ~600ms on GPU
Setup
ollama pull translategemma:12b
Why Local Translation
Your data never leaves your machine.
Private
Translations run entirely on your GPU. No text is sent to any cloud service — ever.
Fast
~600ms per translation after cold load. TranslateGemma 12B runs at full speed on consumer GPUs.
Free
No API keys, no subscriptions, no rate limits. Ollama + TranslateGemma are fully open source (Apache 2.0).
Capabilities
55 Languages
From Afrikaans to Vietnamese — including CJK, Arabic, Hindi, and all major European languages.
Smart Chunking
Long text is split at paragraph and sentence boundaries, preserving context across chunks.
Model Choice
Default to 12B for quality, switch to 4B for speed, or 27B for maximum accuracy.
Setup
Claude Code / Claude Desktop
// Add to your MCP config (.mcp.json)
{
"mcpServers": {
"polyglot": {
"command": "npx",
"args": ["-y", "@mcptoolshop/polyglot-mcp"]
}
}
}Prerequisites
# 1. Install Ollama (ollama.com)
# 2. Pull the translation model:
ollama pull translategemma:12b # 8.1 GB
# 3. Start Ollama:
ollama serveMCP Tools
Three tools exposed to your LLM agent.
Model Options
Choose the right balance of quality and speed.
Supported Languages
55 languages powered by Google TranslateGemma.