> ## Documentation Index
> Fetch the complete documentation index at: https://developers.deepl.com/llms.txt
> Use this file to discover all available pages before exploring further.

# DeepL MCP Server

> Use the DeepL MCP Server to add translation capabilities to Claude, Cursor, and other AI agents.

**This page shows you:**

* What the DeepL MCP Server does and when to use it
* How to install and configure it for Claude Code and Claude Desktop
* What tools are available to your AI agent

The [DeepL MCP Server](https://github.com/DeepLcom/deepl-mcp-server) is an open-source (MIT license) [Model Context Protocol](https://modelcontextprotocol.io/) server that gives AI agents access to DeepL's translation, text improvement, and glossary capabilities. MCP lets AI agents discover and call external tools through a standardized protocol — your agent sends a tool request to the MCP server, which calls the DeepL API and returns the result.

<Note>
  If you want to build a custom MCP server from scratch using the DeepL API, see the [MCP Server Cookbook](/docs/learning-how-tos/examples-and-guides/deepl-mcp-server-how-to-build-and-use-translation-in-llm-applications).
</Note>

## Prerequisites

* [Node.js](https://nodejs.org/) v18 or later
* A DeepL API key ([create a free account](https://www.deepl.com/en/pro/change-plan#developer))

## Quick start

Run the server directly with npx:

```bash theme={null}
npx deepl-mcp-server
```

Or install it locally:

```bash theme={null}
npm install deepl-mcp-server
```

## Configuration

<Tabs>
  <Tab title="Claude Code">
    Add the MCP server to Claude Code with a single command:

    ```bash theme={null}
    claude mcp add deepl -e DEEPL_API_KEY=your-api-key -- npx deepl-mcp-server
    ```

    Claude Code will now have access to DeepL translation tools in every session.
  </Tab>

  <Tab title="Claude Desktop">
    Add the following to your Claude Desktop configuration file:

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

    ```json theme={null}
    {
      "mcpServers": {
        "deepl": {
          "command": "npx",
          "args": ["deepl-mcp-server"],
          "env": {
            "DEEPL_API_KEY": "your-api-key"
          }
        }
      }
    }
    ```

    Restart Claude Desktop to activate the server.
  </Tab>

  <Tab title="Other MCP clients">
    The DeepL MCP Server works with any MCP-compatible client. Configure it using the `npx deepl-mcp-server` command and pass your API key via the `DEEPL_API_KEY` environment variable.

    Refer to your client's documentation for how to add MCP servers.
  </Tab>
</Tabs>

## Available tools

Once configured, your AI agent can use the following tools:

| **Tool**               | **Description**                                                                 |
| ---------------------- | ------------------------------------------------------------------------------- |
| `translate-text`       | Translate text between languages with automatic source language detection       |
| `translate-document`   | Translate documents (PDF, DOCX, PPTX, XLSX, HTML, TXT) with format preservation |
| `rephrase-text`        | Improve and rephrase text with customizable writing style and tone              |
| `get-source-languages` | List all available source languages                                             |
| `get-target-languages` | List all available target languages                                             |
| `get-glossary-info`    | Retrieve details about a specific glossary                                      |
| `get-glossary-entries` | Fetch dictionary entries from a glossary                                        |
| `list-glossaries`      | List all glossaries in your account                                             |

## Example usage

Once the MCP server is connected, you can ask your AI agent things like:

* "Translate this email into German with formal tone"
* "Translate my report.pdf into French"
* "Rephrase this paragraph to sound more professional"
* "What languages does DeepL support?"
* "Show me the entries in my marketing glossary"

The agent will automatically use the appropriate DeepL tool to fulfill the request.

## Next steps

Now that you know how to use the DeepL MCP Server:

* **Explore the source:** Review the [DeepL MCP Server on GitHub](https://github.com/DeepLcom/deepl-mcp-server) for full documentation and source code
* **Build your own:** Follow the [MCP Server Cookbook](/docs/learning-how-tos/examples-and-guides/deepl-mcp-server-how-to-build-and-use-translation-in-llm-applications) to create a custom MCP server from scratch
* **Set up authentication:** Learn about [DeepL API authentication](/docs/getting-started/auth) and key management
* **Use client libraries:** Explore the [official SDKs](/docs/getting-started/client-libraries) for Python, Node.js, and more