How to Use the DeepL MCP in Claude Code

Q: How do I use glossaries with DeepL in Claude Code?

Ask Claude Code to translate your text. The agent will run translatewithglossary via the MCP Server to ensure terminology is translated correctly.

Q: Can Claude Code check which languages DeepL supports?

Yes, Claude Code can run listsourcelanguages and listtargetlanguages to print all supported language codes. This helps you verify language pairs before running translation commands.

Pipe terminal outputs directly to DeepL using Claude Code for headless, automated translations.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect DeepL MCP to Claude Code

Create your Vinkius account to connect DeepL to Claude Code and route execution through our secure gateway. The platform manages server hosting, runtime updates, and security layers. Configuration requires no manual server provisioning.

GDPR Free for Subscribers

Setup DeepL with Claude Code

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Build terminal translation pipelines with Claude Code

This DeepL MCP Server lets you translate text files directly from your CLI using Claude Code. You can run terminal commands to send raw text or files to `translate_text` and pipe the output to other CLI utilities. It makes translating log files, database exports, or documentation files fast and scriptable. Because Claude Code runs headlessly, you can integrate these translation tools into your local shell scripts. The agent handles the API requests and outputs clean, translated text straight to stdout.

Manage translation dictionaries via CLI

Claude Code uses `list_glossaries` and `get_glossary_entries` to display your active dictionaries directly in your terminal. You can audit your brand terms or check language pairs without opening a web browser. If you need to clean up old dictionaries, Claude Code can run `delete_glossary` on command. This terminal integration lets you script your glossary management. You can feed local text files to Claude Code and let it build new translation glossaries using `create_glossary` instantly.

Monitor translation budgets from the command line

This MCP Server exposes `get_usage` to let you monitor your API usage directly from Claude Code. You can check your consumed character count before running automated translation scripts in your terminal. It helps you keep your API costs under control during heavy localization runs. Claude Code prints the usage details directly to your terminal. You can easily integrate this check into your pre-translation shell scripts to prevent overages.

Setup guide

Set up DeepL MCP in Claude Code

Prerequisites

Claude Code CLI installed (npm install -g @anthropic-ai/claude-code)
Active Vinkius subscription with a valid endpoint token

1

Run the add command

Open your terminal and run the command shown on the right. Replace [YOUR_TOKEN_HERE] with your endpoint token from cloud.vinkius.com. Use --scope user to make it available across all projects.
2

Verify the connection

Start a Claude Code session and type /mcp to list connected servers. You should see deepl-alternative-mcp with a green status indicator.
3

Start using tools

Ask Claude Code something like "Check my latest DeepL transactions." It will automatically discover and invoke the available DeepL tools.

Terminal

claude mcp add --transport http deepl-alternative-mcp https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp

Get your connection token →

Prerequisites

Claude Code CLI installed
Active Vinkius subscription with a valid endpoint token

1

Open the config file

Create or edit .mcp.json in your project root for project-level scope, or ~/.claude.json for user-level scope.
2

Add the DeepL MCP

Paste the JSON snippet shown on the right into the mcpServers object. Replace [YOUR_TOKEN_HERE] with your endpoint token from cloud.vinkius.com.
3

Restart Claude Code

Start a new Claude Code session. Type /mcp to confirm the server is connected. The tools will be automatically available in your conversation.

.mcp.json

{
  "mcpServers": {
    "deepl-alternative-mcp": {
      "type": "url",
      "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    }
  }
}

Get your connection token →

Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by DeepL. All third-party trademarks, logos, and brand names are the property of their respective owners. Their use on this website is strictly for informational purposes to identify service compatibility and interoperability.

Why Choose Vinkius

Vinkius connects your tools to AI with real-time monitoring and automatic cost savings — all from one dashboard.

Connect DeepL now

Real-time monitoring

Live

visibility into every interaction

Connect your favorite tools to your AI and see exactly what's happening — every request, every response, in real time.

Built-in savings

60%

lower AI costs

Vinkius compresses data between your apps and your AI automatically. Lower bills every month — no configuration required.

Single dashboard

One

place for every integration

Every tool your AI connects to, managed from a single screen. One account, complete control.

Common questions about DeepL MCP in Claude Code

Run the install command to register the MCP Server in your config file. Claude Code will load the tools and make them instantly accessible in your terminal sessions.

Yes, you can tell Claude Code to read a file from a terminal path and run `translate_text` on it. The agent will output the translated content directly to your terminal or save it to a new file.

Ask Claude Code to translate your text. The agent will run `translate_with_glossary` via the MCP Server to ensure terminology is translated correctly.

Yes, Claude Code can run `list_source_languages` and `list_target_languages` to print all supported language codes. This helps you verify language pairs before running translation commands.

Your terminal text and glossary entries are transmitted via an encrypted Vinkius sandbox connection directly to DeepL. No translation data is cached or stored by Vinkius, keeping your command-line operations private.

Use it with your favorite AI tools

Connect this server to Cursor, Claude, VS Code, and more.

OpenAI Agents SDK sdk-python

Google ADK sdk-python

Pydantic AI sdk-python

Vercel AI SDK sdk-typescript