Deepl Mcp Server

Deepl Mcp Server

What is Deepl Mcp Server about?

Provides translation and rephrase tools that invoke DeepL's API, exposing them through a Model Context Protocol (MCP) server. The server can be called by MCP‑compatible clients such as Claude Desktop.

How to use Deepl Mcp Server?

1. Run without installation: npx deepl-mcp-server
2. Install locally: npm install deepl-mcp-server then run npx deepl-mcp-server or node ./node_modules/deepl-mcp-server/src/index.mjs.
3. Configure for clients: Set the environment variable DEEPL_API_KEY with your DeepL API key and point the client (e.g., Claude Desktop) to the command npx deepl-mcp-server.

Key features of Deepl Mcp Server

• Translate text between dozens of languages.
• Rephrase text while preserving meaning.
• Automatic language detection.
• Formality control for supported languages.
• Access to all DeepL API features (glossaries, split sentences, etc.).
• Simple CLI usage via npx.

Use cases of Deepl Mcp Server

• Integrating real‑time translation into AI assistants.
• Providing multilingual support for chatbots.
• Enabling developers to add translation/rephrase tools to custom applications.
• Automating content localization pipelines.

FAQ from the Deepl Mcp Server

• Do I need a DeepL API key? Yes, the server requires a valid DEEPL_API_KEY.
• Is there a free tier? DeepL offers a free API tier up to 500,000 characters per month.
• Can I control formality? Yes, use the formality parameter with values like less, more, default, prefer_less, or prefer_more.
• What languages are supported? All languages listed by the DeepL API; retrieve them via get-source-languages and get-target-languages tools.
• How do I debug issues? Consult the MCP debugging documentation at https://modelcontextprotocol.io/docs/tools/debugging.

deepl-mcp-server

A Model Context Protocol (MCP) server that provides translation capabilities using the DeepL API.

Features

• Translate text between numerous languages
• Rephrase text using DeepL's capabilities
• Access to all DeepL API languages and features
• Automatic language detection
• Formality control for supported languages

Usage

The easiest way to run this server is to use the npm package without installing anything:

npx deepl-mcp-server

If you want to install this locally, so you can play with it to your heart's content, you can do so using npm:

npm install deepl-mcp-server

Alternately, if you want to contribute, you can clone this repository and install dependencies:

git clone https://github.com/DeepLcom/deepl-mcp-server.git
cd deepl-mcp-server
npm install

Configuration

DeepL API Key

You'll need a DeepL API key to use this server. You can get one by signing up at DeepL API. With a DeepL API Free account you can translate up to 500,000 characters/month for free.

Using with Claude Desktop

This MCP server integrates with Claude Desktop to provide translation capabilities directly in your conversations with Claude.

Configuration Steps

1. Install Claude Desktop if you haven't already

2. Create or edit the Claude Desktop configuration file:

   • On macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
   • On Windows: %AppData%\Claude\claude_desktop_config.json
   • On Linux: ~/.config/Claude/claude_desktop_config.json

3. Add the DeepL MCP server configuration. If you want to use the npm package without installing anything, as described above:

{
  "mcpServers": {
    "deepl": {
      "command": "npx",
      "args": ["deepl-mcp-server"],
      "env": {
        "DEEPL_API_KEY": "{YOUR_API_KEY}"
      }
    }
  }
}

Or, if you installed this locally, give Claude an absolute path to the JS file, like this:

{
  "mcpServers": {
    "deepl": {
      "command": "node",
      "args": ["/{ABSOLUTE_PATH_TO_SERVER}/deepl-mcp-server/src/index.mjs"],
      "env": {
        "DEEPL_API_KEY": "{YOUR_API_KEY}"
      }
    }
  }
}

If you've pulled down this code, but you haven't done an npm install, or if you just prefer to, you can use npx /{ABSOLUTE_PATH_TO_SERVER}/deepl-mcp-server here instead of node /{ABSOLUTE_PATH_TO_SERVER}/deepl-mcp-server/src/index.mjs.

4. Replace {ABSOLUTE_PATH_TO_SERVER} with an absolute path to your local copy of this repository - for example, /Users/robotwoman/Code/deepl-mcp-server
5. Replace {YOUR_API_KEY} with your actual DeepL API key
6. Restart Claude Desktop

Once configured, Claude will be able to use the DeepL translation tools when needed. You can ask Claude to translate text between languages, and it will use the DeepL API behind the scenes.

Available Tools

This server provides the following tools:

• get-source-languages: Get list of available source languages for translation
• get-target-languages: Get list of available target languages for translation
• translate-text: Translate text to a target language
• rephrase-text: Rephrase text in the same or different language

Tool Details

translate-text

This tool translates text between languages using the DeepL API.

Parameters:

• text: The text to translate
• targetLang: Target language code (e.g., 'en-US', 'de', 'fr')
• formality (optional): Controls formality level of the translation:
  • 'less': use informal language
  • 'more': use formal, more polite language
  • 'default': use default formality
  • 'prefer_less': use informal language if available, otherwise default
  • 'prefer_more': use formal language if available, otherwise default

rephrase-text

This tool rephrases text in the same or different language using the DeepL API.

Parameters:

• text: The text to rephrase

Supported Languages

The DeepL API supports a wide variety of languages for translation. You can use the get-source-languages and get-target-languages tools to see all currently supported languages.

Some examples of supported languages include:

• English (en, en-US, en-GB)
• German (de)
• Spanish (es)
• French (fr)
• Italian (it)
• Japanese (ja)
• Chinese (zh)
• Portuguese (pt-BR, pt-PT)
• Russian (ru)
• And many more

Debugging

For debugging information, visit the MCP debugging documentation.

Error Handling

If you encounter errors with the DeepL API, check the following:

• Verify your API key is correct
• Make sure you're not exceeding your API usage limits
• Confirm the language codes you're using are supported

License

MIT

Links

• DeepL API Documentation
• Model Context Protocol Documentation