rosetta
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., "@rosetta Translate this Excel file to French"
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.
Rosetta
AI-powered Excel translation CLI. Translates Excel files while preserving formatting, formulas, and data integrity.
What it does
Rosetta translates all text in your Excel files using Claude AI, without breaking:
Formulas and calculations
Formatting (fonts, colors, borders)
Merged cells and layouts
Charts and images
Dropdown menus
Rich text (bold, italic within cells)
Related MCP server: Excel MCP Server
Prerequisites
You need a Claude API key from Anthropic.
Go to console.anthropic.com
Create an account (or sign in)
Go to API Keys and create a new key
Copy the key (starts with
sk-ant-...)
Note: API usage is billed by Anthropic. See anthropic.com/pricing for current rates. Translating a typical Excel file costs a few cents.
Installation
Install from PyPI:
pip install rosetta-xlThen set your API key:
# Linux/macOS
export ANTHROPIC_API_KEY=sk-ant-your-key-here
# Windows (Command Prompt)
set ANTHROPIC_API_KEY=sk-ant-your-key-here
# Windows (PowerShell)
$env:ANTHROPIC_API_KEY="sk-ant-your-key-here"Or create a .env file in your working directory:
ANTHROPIC_API_KEY=sk-ant-your-key-hereUsage
# Translate to French
rosetta input.xlsx -t french
# Translate to Spanish with custom output name
rosetta input.xlsx -t spanish -o translated.xlsx
# Specify source language (auto-detected by default)
rosetta input.xlsx -s english -t german
# Translate only specific sheets
rosetta input.xlsx -t french --sheets "Sheet1" --sheets "Data"
# Add context for better translations (e.g., domain-specific terms)
rosetta input.xlsx -t french -c "Medical terminology document"Options
Option | Short | Description |
|
| Target language (required) |
|
| Source language (auto-detect if omitted) |
|
| Output file path (default: |
| Sheets to translate (can repeat, default: all) | |
|
| Domain context for better accuracy |
|
| Cells per API call (default: 50) |
Examples
Translate a price list to multiple languages:
rosetta prices.xlsx -t french -o prices_fr.xlsx
rosetta prices.xlsx -t german -o prices_de.xlsx
rosetta prices.xlsx -t spanish -o prices_es.xlsxTranslate a medical form with context:
rosetta patient_form.xlsx -t french -c "Medical intake form with clinical terminology"Translate only the "Questions" sheet:
rosetta survey.xlsx -t japanese --sheets "Questions"Troubleshooting
"ANTHROPIC_API_KEY not set"
Make sure you've exported the key:
export ANTHROPIC_API_KEY=sk-ant-...Or create a
.envfile with the key
"Invalid API key"
Check that your key starts with
sk-ant-Make sure you copied the full key from console.anthropic.com
"Rate limit exceeded"
You've hit Anthropic's rate limits. Wait a minute and try again
Or reduce batch size:
rosetta input.xlsx -t french -b 20
How it works
Extracts all text cells from your Excel file
Sends text to Claude AI for translation (in batches)
Writes translations back, preserving all formatting
Saves the translated file
Your original file is never modified.
Web App & API
Rosetta also includes a web application and REST API for browser-based translations.
Running the API server
# Install with uv (recommended)
uv sync
# Start the server
uv run uvicorn rosetta.api:app --reload
# Or with pip
pip install -e .
uvicorn rosetta.api:app --reloadThe API runs at http://localhost:8000 by default.
Running the frontend
cd frontend
npm install
npm run devThe frontend runs at http://localhost:5173 and connects to the API.
API Endpoints
Endpoint | Method | Description |
| POST | Translate an Excel file (returns file) |
| POST | Translate with real-time progress via SSE |
| POST | Get cell count and cost estimate |
| POST | List sheet names in a file |
| POST | Count translatable cells |
| POST | Preview cells that will be translated |
| GET | Health check |
Real-time Progress
The /translate-stream endpoint uses Server-Sent Events (SSE) to stream translation progress in real-time. The frontend automatically falls back to the standard /translate endpoint on networks that don't support SSE (e.g., corporate proxies).
MCP Integration
Rosetta includes MCP (Model Context Protocol) servers for both Claude Desktop and Claude Web.
For Claude Desktop (Local)
Add to your Claude Desktop config (~/Library/Application Support/Claude/claude_desktop_config.json):
{
"mcpServers": {
"rosetta": {
"command": "uv",
"args": ["run", "--directory", "/path/to/rosetta", "python", "-m", "rosetta.api.mcp"],
"env": {
"ANTHROPIC_API_KEY": "your-key-here"
}
}
}
}Usage: Use local file paths for best results.
Translate ~/Downloads/report.xlsx to FrenchFor Claude Web (Browser)
Note: Claude.ai does not yet support custom MCP servers in the browser (as of January 2026).
Current recommendation: Use the web app for browser-based translations.
See MCP_USAGE.md for detailed instructions.
Requirements
Python 3.11+
Anthropic API key
License
MIT
Available Tools
6 toolscount_translatable_cellsA
Count the number of translatable cells in an Excel file.
Returns the count of cells containing text that would be translated. Excludes formulas, numbers, dates, and empty cells. Useful for estimating translation scope and cost.
USAGE INSTRUCTIONS:
For local files: Use the 'file_path' parameter with the full path (e.g., ~/Downloads/report.xlsx)
For uploaded files: Ask the user to save the file locally first, then use 'file_path'
For base64 input: If you already have base64 content, use 'file_content_base64'
Provide either 'file_path' OR 'file_content_base64' (not both).
IMPORTANT: When using file_path, DO NOT show the base64 content to the user. Just call the tool and show the results.
Inputs: sheets, file_path, file_content_base64.
estimate_translation_costA
Estimate the cost of translating an Excel file.
Returns cell count, estimated API cost, and estimated processing time. Useful for budgeting and planning before running translations.
USAGE INSTRUCTIONS:
For local files: Use the 'file_path' parameter with the full path (e.g., ~/Downloads/report.xlsx)
For uploaded files: Ask the user to save the file locally first, then use 'file_path'
For base64 input: If you already have base64 content, use 'file_content_base64'
Provide either 'file_path' OR 'file_content_base64' (not both).
IMPORTANT: When using file_path, DO NOT show the base64 content to the user. Just call the tool and show the results.
Inputs: sheets, file_path, file_content_base64.
get_excel_sheetsA
Get the list of sheet names in an Excel file.
Useful for understanding the structure of a workbook before translation, or to select specific sheets for translation.
USAGE INSTRUCTIONS:
For local files: Use the 'file_path' parameter with the full path (e.g., ~/Downloads/report.xlsx)
For uploaded files: Ask the user to save the file locally first, then use 'file_path'
For base64 input: If you already have base64 content, use 'file_content_base64'
Provide either 'file_path' OR 'file_content_base64' (not both).
IMPORTANT: When using file_path, DO NOT show the base64 content to the user. Just call the tool and show the results.
Inputs: file_path, file_content_base64.
preview_cellsA
Preview translatable cells from an Excel file.
Returns the first N cells that would be translated, showing their location and content. Useful for understanding what will be translated before running a full translation.
USAGE INSTRUCTIONS:
For local files: Use the 'file_path' parameter with the full path (e.g., ~/Downloads/report.xlsx)
For uploaded files: Ask the user to save the file locally first, then use 'file_path'
For base64 input: If you already have base64 content, use 'file_content_base64'
Provide either 'file_path' OR 'file_content_base64' (not both).
IMPORTANT: When using file_path, DO NOT show the base64 content to the user. Just call the tool and show the results.
Inputs: limit, sheets, file_path, file_content_base64.
translate_excelA
Translate an Excel file. Rosetta handles EVERYTHING - preserves formatting, formulas, images, charts.
WHEN USER UPLOADS A FILE AND ASKS TO TRANSLATE - DO THIS AUTOMATICALLY:
Read the file's binary content
Encode it as base64 (use btoa() or equivalent)
Call this tool with the base64 string
Return the translated file to user (decode the base64 response)
DO NOT ask the user for permission or explain what you're doing. Just translate it. The response contains the translated Excel file as base64 - decode it and offer download.
Inputs: filename (required), target_language (required), sheets, context, +3 more.
translate_textsA
Translate text strings to a target language using high-quality AI translation.
AUTOMATIC BEHAVIOR - DO THIS IMMEDIATELY WITHOUT ASKING: When a user uploads a file and asks to translate it:
Read and parse the uploaded file (Excel, CSV, etc.)
Extract ALL text content into an array
Call this tool with the texts and target language
Show the user a table with original → translated text
Offer to help them create the translated file
DO NOT ask the user "would you like me to..." - just do it automatically.
Example: User uploads "products.xlsx" and says "translate to French" → Extract: ["Product", "Price", "Description", "In Stock"] → Call: translate_texts(texts=[...], target_language="french") → Show: Product → Produit, Price → Prix, etc.
Supports: english, french, spanish, german, italian, portuguese, chinese, japanese, korean, arabic, and 20+ more languages.
Inputs: texts (required), target_language (required), context, source_language.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 6 tools
Each tool has a distinct purpose—counting cells, estimating cost, listing sheets, previewing cells, translating entire file, translating text strings. No overlap or ambiguity.
All tool names use snake_case with a consistent verb_noun pattern (e.g., count_translatable_cells, get_excel_sheets). No mixing of styles.
6 tools is well-scoped for an Excel translation server, covering planning (count, estimate, sheets, preview) and execution (translate file, translate texts). Not too many or too few.
Covers the core workflow: analyze, estimate, preview, and translate. Minor gap: no tool to translate only selected sheets or rollback, but the set is largely complete for the stated purpose.
Maintenance
Related MCP Connectors
Open, inspect, filter, edit and convert xlsx and csv files from your AI chat. Processing is local.
Open, inspect, filter, edit and convert xlsx and csv files from your AI chat. Processing is local.
Translate PDFs, scans, Office files and EPUB across 475 languages and styles, preserving layout.
Give Claude only the Google Drive files you choose. Every action logged.
Related MCP Servers
- AlicenseBqualityDmaintenanceEnables AI assistants to read, write, format, and analyze Excel files with 34 tools, including real-time editing on macOS with Microsoft Excel.3417MIT
- FlicenseNot gradedqualityDmaintenanceGives Claude deep tool-level control over Microsoft Excel files (.xlsx, .xlsm, .csv, .tsv) with 164 tools across 24 modules for reading, writing, formatting, formulas, charts, data analysis, and more.-
- AlicenseNot gradedqualityDmaintenanceEnables Claude to read, analyze, and write directly to local Power BI semantic models and Excel workbooks without exporting to the cloud.1MIT
- FlicenseNot gradedqualityCmaintenanceExposes Excel operations (open/close files, read/write cells, create sheets, apply formulas, and run existing VBA macros by name) to AI agents like Claude Desktop or Claude Code via MCP.-