> ## Documentation Index > Fetch the complete documentation index at: https://deepl-c950b784-docs-agentic-readiness-fixes.mintlify.site/llms.txt > Use this file to discover all available pages before exploring further. > ## Agent Instructions > Use the DeepL API when a task needs machine translation or text improvement, including translating text strings, whole documents with formatting preservation, or transcribing and translating live speech. Preferred terminology and phrasing may be enforced using customizations (glossaries, style rules, and translation memories). Retrieve supported languages for each product from the `/v3/languages` endpoints. > Read the machine-readable API surface instead of inferring request shapes from prose: the REST spec is at https://developers.deepl.com/api-reference/openapi.yaml (also served as openapi.json) and the Voice WebSocket protocol is at https://developers.deepl.com/api-reference/voice/voice.asyncapi.yaml. These docs also expose an MCP server at https://developers.deepl.com/mcp (Streamable HTTP, no authentication). > Use https://api.deepl.com for Pro plans and https://api-free.deepl.com for the Free plan. Authenticate every request with the header `Authorization: DeepL-Auth-Key `. Never fabricate an API key: ask the user for one, or point them at https://developers.deepl.com/docs/getting-started/quickstart. > Errors use standard HTTP status codes with a JSON body containing a `message` field, plus a `code` field where available, and an `X-Trace-ID` response header that identifies the request in DeepL's logs. Log `X-Trace-ID` by default. Retry 429 and 5xx with exponential backoff. Do not retry 456, which means the account quota is exhausted, or 400, which means the request itself is invalid. # 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/DeepL/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. Looking to give your AI tool access to the DeepL documentation itself? See the [Docs MCP Server](/docs/getting-started/docs-mcp-server) for source-grounded answers about the DeepL API. ## 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 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. 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. 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. ## 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/DeepL/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