The deepl-mcp-server package provides a Model Context Protocol (MCP) server that integrates DeepL's translation capabilities. It allows other applications, notably Claude Desktop, to leverage DeepL's API for features like text and document translation, rephrasing, automatic language detection, formality control, and glossary support. The current stable version is 1.1.0. This package is primarily designed as a standalone server or CLI tool, rather than a library for programmatic import. Its key differentiator is simplifying DeepL API access for MCP-compatible clients, particularly its direct configuration support for Claude Desktop, enabling AI assistants to perform high-quality translations. Release cadence is infrequent, focusing on stability and integration enhancements. It abstracts the complexities of the DeepL API, offering a streamlined interface via the MCP specification.
npm install deepl-mcp-serverVerified import paths — ran on the pinned version, not inferred.
This quickstart demonstrates how to launch the DeepL MCP server via npx with an API key, then interact with it using curl to call one of its available tools, like fetching source languages.
Set the `DEEPL_API_KEY` environment variable before running the server (e.g., `DEEPL_API_KEY="your_key" npx deepl-mcp-server`).
Run the server as a separate process using `npx deepl-mcp-server` or `node /path/to/src/index.mjs`. Interact with it via HTTP requests from your application.
Use a full path like `/Users/youruser/Code/deepl-mcp-server/src/index.mjs` in your Claude Desktop configuration (`claude_desktop_config.json`).
Inspect the console output when the server starts to confirm the active port, and adjust any client requests (e.g., `curl`) accordingly.
Set the `DEEPL_API_KEY` environment variable, e.g., `DEEPL_API_KEY="YOUR_KEY" npx deepl-mcp-server`.
Ensure `npx` is installed and updated (`npm install -g npm@latest`) or install the package globally (`npm install -g deepl-mcp-server`). Alternatively, provide the full path to the executable if running locally.
Verify the `command` and `args` paths in your `claude_desktop_config.json` are correct and absolute, and that the specified `DEEPL_API_KEY` is valid. Check Claude Desktop logs for more specifics.
No dependency data recorded yet.