DeepL MCP Server
OfficialThe DeepL MCP Server provides translation and text rephrasing capabilities using the DeepL API. Key features include:
Translate text between numerous languages with automatic language detection
Control formality level of translations (less, more, default, prefer_less, prefer_more)
Rephrase text with customizable writing styles (academic, business, casual, simple) and tones (confident, diplomatic, enthusiastic, friendly)
Retrieve lists of supported source and target languages
Get available writing styles and tones for rephrasing
Integration with Claude Desktop for translation in conversations
Provides translation capabilities using the DeepL API, including text translation between numerous languages, rephrasing, automatic language detection, and formality control for supported languages.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@DeepL MCP Server translate 'Hello, how are you?' to Spanish"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
deepl-mcp-server
For the best experience and the latest features check out theDeepL remote MCP server to use DeepL in your AI agent. No installation required, just add it to Claude, ChatGPT, Microsoft Copilot or any MCP client and sign in with your DeepL account.
Working in a terminal or with a coding agent? Try the DeepL CLI. It covers translation, documents, glossaries and i18n file sync with your API key.
A Model Context Protocol (MCP) server that exposes DeepL text translation, document translation, rephrasing, and glossary and style rule lookups as MCP tools.
Usage
You need Node.js 18 or newer and a DeepL API key. Pick an API plan and create a key in your DeepL account.
The server communicates over stdio, so it is normally started by an MCP client rather than by hand. To try it directly:
DEEPL_API_KEY=your-api-key npx -y deepl-mcp-serverIt exits immediately if DEEPL_API_KEY is not set.
To work on the server itself:
git clone https://github.com/DeepL/deepl-mcp-server.git
cd deepl-mcp-server
npm installRelated MCP server: DeepL MCP Server
Configuration
Register it as a stdio server with DEEPL_API_KEY in the server's environment. In Claude Code:
claude mcp add deepl --env DEEPL_API_KEY=your-api-key -- npx -y deepl-mcp-serverFor clients configured through a JSON file:
{
"mcpServers": {
"deepl": {
"command": "npx",
"args": ["-y", "deepl-mcp-server"],
"env": {
"DEEPL_API_KEY": "your-api-key"
}
}
}
}Where that file lives and how each client expects local stdio servers to be declared:
To run a local checkout instead of the published package, use node as the command and the absolute path to src/index.mjs as the argument.
Tools
Tool | Description | Parameters |
| Translates text into a target language. |
|
| Translates a document file (PDF, DOCX, PPTX, XLSX, HTML, TXT, and more) and writes the result to disk. |
|
| Rephrases text, optionally into another language. |
|
| Lists the language codes accepted as a translation source. | none |
| Lists the language codes accepted as a translation target. | none |
| Lists the | none |
| Lists the | none |
| Lists every glossary in the account with its id, name, dictionaries, and creation time. | none |
| Returns the same metadata as |
|
| Returns the term entries of one glossary dictionary, meaning one language pair in one direction. |
|
| Lists the style rules in the account with their id, name, language, and timestamps. |
|
| Returns one style rule in full, including its configured rules and custom instructions. |
|
| Returns a single custom instruction belonging to a style rule. |
|
Notes:
texttakes either a single string or an array of strings. Each entry is translated or rephrased independently.Language codes are ISO 639-1, optionally with a region (
en-US). OmittingsourceLangCodetriggers automatic detection. A target code whose language requires a region gets a default applied:enbecomesen-US,ptbecomespt-BR,zhbecomeszh-Hans.Glossary dictionaries are keyed by non-regional codes, so
get-glossary-dictionary-entriesdrops any region you pass.Translating with a glossary requires an explicit
sourceLangCode.formalityacceptsless,more,default,prefer_less, andprefer_more. Theprefer_*values fall back to the default when the target language has no formality support.translate-documentreads and writes files on the machine running the server. WithoutoutputFile, the output path is derived from the input by appending the target language code, for examplereport_de.pdf. WithoutputFormat, the derived path uses that extension instead.Style rules and custom instructions are read-only here. Create and edit them in your DeepL account.
License
MIT
Available Tools
13 toolsget-custom-instructionA
Get a single custom instruction belonging to a style rule. Use the get-style-rule tool to find out which custom instructions a style rule contains.
Inputs: styleId (required), instructionId (required).
get-glossary-dictionary-entriesA
Retrieve all the entries from a given glossary dictionary. (A glossary consists one of one or more dictionaries, each of which contains entries for a specific language pair, in one direction. For example, one dictionary could contain entries for translations from German to English, and another dictionary could contain entries for translations from English to German.) To retrieve all entries for a glossary with multiple dictionaries, use the get-glossary-info or list-glossaries tool to find out what dictionaries it contains, then use this tool for each dictionary.
Inputs: glossaryId (required), sourceLangCode (required), targetLangCode (required).
get-glossary-infoA
Given an id, get metadata about the glossary with that id - its name, available dictionaries, and creation time. This does not fetch any glossary entries. Use the get-glossary-dictionary-entries tool to fetch entries.
Inputs: glossaryId (required).
get-source-languagesA
Get list of available source languages for translation
Inputs: no named parameters.
get-style-ruleA
Given an id, get a single style rule with its full detail - configured rules and custom instructions.
Inputs: styleId (required).
get-target-languagesA
Get list of available target languages for translation
Inputs: no named parameters.
get-writing-stylesA
Get list of writing styles the DeepL API can use while rephrasing text
Inputs: no named parameters.
get-writing-tonesA
Get list of writing tones the DeepL API can use while rephrasing text
Inputs: no named parameters.
list-glossariesA
Get a list of all glossaries with metadata for each - name, dictionaries available, and creation time. This does not fetch any glossary entries. Use the get-glossary-dictionary-entries tool to fetch entries.
Inputs: no named parameters.
list-style-rulesA
Get a list of all style rules with metadata for each - id, name, language, and timestamps. Style rules can be applied when translating text or documents. Use the get-style-rule tool to fetch the configured rules and custom instructions of a single style rule.
Inputs: page, detailed, pageSize.
rephrase-textB
Rephrase text in the same language, or into a different language, using DeepL API
Inputs: text (required), tone, style, targetLangCode.
translate-documentC
Translate a document file using DeepL API
Inputs: inputFile (required), targetLangCode (required), styleId, formality, +4 more.
translate-textA
Translate text to a target language using DeepL API. Review all available optional parameters and use those applicable to your scenario for best results. When the translation includes a glossary, you must specify the source language as well as the target language. If the user requests a glossary by name instead of by id, you can use the list-glossaries tool to get a name for each id.
Inputs: text (required), targetLangCode (required), context, styleId, +6 more.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 13 tools
Each tool targets a distinct resource or action: language listing, translation, rephrasing, glossary listing/detail/entries, and style rule listing/detail/custom instructions. The only pairs that could be confused (writing styles vs tones, style rule vs custom instruction) are distinguished by their descriptions, so ambiguity is minimal.
All tools follow a consistent verb_noun pattern using lowercase with hyphens (get-, list-, translate-, rephrase-). There are no mixed conventions or vague verbs like 'process'.
13 tools is within the ideal 3-15 range. The count reflects the breadth of DeepL features (translation, rephrasing, glossaries, style rules) without being overwhelming.
Core translation and rephrasing workflows are covered (language lists, translate text/document, rephrase, styles/tones). However, the server only offers read operations for glossaries and style rules (list/get), with no create/update/delete, leaving a notable gap for managing these resources.
Maintenance
Related MCP Connectors
A Model Context Protocol server for Wix AI tools
A comprehensive Model Context Protocol (MCP) server that enables AI assistants to interact with yo…
Model Context Protocol server for the Apideck Unified API. Connect any MCP-compatible agent framework to 100+ accounting systems, HRIS platforms, file storage providers, and more through one integration. More information https://www.apideck.com/mcp-server
AI-powered translation for 48 languages with context-aware quality
Related MCP Servers
- FlicenseNot gradedqualityDmaintenanceA ModelContextProtocol server providing high-quality translation services with a three-stage translation workflow (analysis, segmented translation, full-text review) that supports multiple languages and integrates with Claude and OpenAI-compatible models.26-
- AlicenseNot gradedqualityDmaintenanceA Model Context Protocol server that provides DeepL translation capabilities, allowing AI assistants to translate text between supported languages via the DeepL API.3MIT
- AlicenseNot gradedqualityDmaintenanceAn AI-driven text translation service supporting 20+ languages, based on the Model Context Protocol (MCP) for integration with Claude Desktop and other MCP-compatible applications.MIT
- AlicenseNot gradedqualityDmaintenanceEnables translation and text rephrasing using DeepL's API through a cloud-deployed MCP server. Provides translation between multiple languages, text rephrasing, and language detection capabilities with professional deployment features.MIT