DeepL MCP Server
MCP serverDeepL maintains this official local MCP server and publishes it as deepl-mcp-server on npm. It exposes text and document translation, rephrasing, language metadata, glossary lookup and read-only style-rule lookup over stdio.
Not for: Editing style rules or using DeepL without an API plan. Style rules are read-only here, and the local server exits if DEEPL_API_KEY is missing.
Source and setup verified on 2026-11-05
AI & MLQuick facts
- Maintainer
- DeepL (official)
- npm package
- deepl-mcp-server 1.3.15
- Transport
- stdio
- Authentication
- DEEPL_API_KEY
- UI
- None; tools only
What you can do
- translate-text with formality, glossary and style options
- translate-document for PDF, DOCX, PPTX, XLSX, HTML, TXT and other formats
- rephrase-text with style and tone
- List and inspect glossaries
- Read style rules and custom instructions
Requirements
- Node.js 18 or newer
- A DeepL API plan
- A DeepL API key from the account
DEEPL_API_KEY=your-api-key npx -y deepl-mcp-serverUse the JSON configuration below or the documented claude mcp add command.
{
"mcpServers": {
"deepl": {
"command": "npx",
"args": ["-y", "deepl-mcp-server"],
"env": {
"DEEPL_API_KEY": "your-api-key"
}
}
}
}Always confirm the latest setup instructions with the maintainer before installing.
>Questions
Is this the official DeepL MCP server?
Yes. DeepL owns the repository and publishes the deepl-mcp-server npm package.
Can it translate files?
Yes. translate-document reads a local input file and writes the translated file on the machine running the server.
Does DeepL MCP have inline UI?
No. The repository documents stdio tools and does not register a ui:// MCP App resource.
>Related Apps
Google Gemini server with embedded viewers for generated and edited images, videos, SVG graphics, and landing pages
Official Azure multimodal image-search sample with an embedded viewer for image files returned from Azure AI Search and Blob Storage
AI service marketplace server with an optional embedded run viewer for live job progress and generated image, video, audio, table, and file outputs