How to Use the DeepL MCP in Claude

Q: Can Claude Desktop use DeepL glossaries?

Yes. Claude uses the translatewithglossary tool to apply your custom terminology. It creates new dictionaries on the fly with createglossary.

Connect DeepL to Claude Desktop and translate text across 30 languages with native nuance.

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 Desktop

Create your Vinkius account to connect DeepL to Claude Desktop 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 Desktop

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Run Neural Translations Inside Claude Desktop

The `translate_text` tool gives your AI client direct access to a neural translation engine that understands context. You ask Claude to draft an email in Japanese, and it hits the API to generate text that actually sounds natural instead of machine-generated. Tone matters when you talk to clients. The `translate_formal` and `translate_informal` tools force the output to match your professional or casual context automatically. You don't have to guess which languages work. Claude pulls the exact supported pairs using `list_source_languages` and `list_target_languages`. If you need to check a massive file, `get_document_status` lets the agent track the progress without you clicking refresh on a web dashboard.

Build Custom Glossaries for Your MCP Server

The `create_glossary` tool lets Claude build specific dictionaries for your company jargon. You upload your technical terms once. From then on, Claude uses `translate_with_glossary` to guarantee that your brand names and proprietary terms remain untouched during translation. Managing these dictionaries happens right in the chat interface. You can pull the full list of your terms using `get_glossary_entries` or check which languages support custom dictionaries via `list_glossary_language_pairs`. When a project ends, Claude cleans up the workspace by firing `delete_glossary`.

Track API Quotas Automatically

The `get_usage` tool checks your account limits before Claude kicks off a massive localization job. Hitting rate limits mid-translation breaks your workflow. Your agent verifies the available character count first, guaranteeing the job finishes. You manage multiple workspaces with `list_glossaries` and `get_glossary` to keep client data separated. Claude handles the administrative busywork. You just ask for the translation and get the final text back in your local file system or browser window.

Setup guide

Set up DeepL MCP in Claude Web or Desktop

1

Open Claude Settings

Go to claude.ai, click your profile icon, then navigate to Customize → Connectors.
2

Add Custom Connector

Click the "+" button and select Add custom connector. Paste your Vinkius endpoint URL: https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. For OAuth-protected servers, expand Advanced settings to add credentials.
3

Start a conversation

Open a new chat. The DeepL MCP tools are available immediately — no restart needed.

Endpoint URL

https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp

No configuration file needed — paste the URL directly in the Claude web interface.

Available on Free (1 connector), Pro, Max, Team, and Enterprise plans.

Prerequisites

Claude Desktop installed (macOS or Windows)
Active Vinkius subscription with a valid endpoint token

1

Open Claude Desktop Settings

Click the menu icon at the top-left corner, go to Settings → Developer → Edit Config. This opens claude_desktop_config.json in your default text editor.
2

Paste the DeepL MCP configuration

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

Restart Claude Desktop

Close and reopen the application. Claude needs a full restart to load new MCPs — refreshing a conversation is not enough.
4

Verify the connection

Open a new conversation. Click the 🔌 icon at the bottom of the message input. You should see tools listed under deepl-alternative-mcp.

json

{
  "mcpServers": {
    "deepl-alternative-mcp": {
      "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 Desktop

Open Settings, then Developer, and click Edit Config. Add the server details to your `claude_desktop_config.json` file. Save the file and restart the application completely.

Yes. Claude uses the `translate_with_glossary` tool to apply your custom terminology. It creates new dictionaries on the fly with `create_glossary`.

You can paste the Vinkius remote MCP URL directly into the Custom Connectors section under Settings. Tools appear instantly without touching your local file system.

You need to specify the tone in your prompt. Tell Claude to use the `translate_formal` tool instead of the default translation endpoint. This forces the API to use professional phrasing.

Your raw text and proprietary glossaries run through a Vinkius V8 Isolate Sandbox. The environment is entirely ephemeral and shuts down the millisecond the API returns your translated text. Zero-trust architecture means nothing gets stored on disk.

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