
Deepl MCP server
online · 100% uptimeDeepL MCP.
not scanned yet
0 stars
Reviews
Write oneNobody has reviewed Deepl yet.
If you have run it, two minutes of your experience saves the next person an afternoon.
Deepl tools
Tool list not cached yet. `describe` through the gateway fetches it live.
How Deepl compares
Against every graded MCP server, from our own scans and uptime checks. Updated after each scan run.
- Safety score
- 77/100
- higher than 50% of 48,255 servers
- Uptime
- 100%
- of our recent checks; the typical remote server answers 100%
- Response time
- 106 ms
- faster than 83% of 30,031 servers
Release history: 8 versions in the registry since 2026-05-20, latest 2026-11-01, typically one every 4 days.
Install Deepl in Claude Code, Cursor or VS Code
claude mcp add --transport http deepl https://gateway.pipeworx.io/deepl/mcp
What the publisher says
From the Deepl repository's README, as published. We do not edit it. Read it on GitHub
@pipeworx/deepl
DeepL API MCP — high-quality machine translation. Free tier 500k chars/mo.
Part of Pipeworx — an MCP gateway connecting AI agents to 1679+ live data sources.
Auth
character quota: measured 2026-08-28, usage on the same key answers charactercount: 0 against a full characterlimit while translate 456s in the next call. Zero successes in the seven days before that. Waiting does not clear it — pass your own key as apiKey. The read-only tools (usage, sourcelanguages, targetlanguages, glossarylanguage_pairs) still answer on the shared key. Fleet #577.
- Platform: PLATFORMDEEPLKEY. BYO: ?_apiKey=….
- Free-tier keys end with :fx (auto-detected → free endpoint).
- translate is currently refused on the Pipeworx shared key (HTTP 456), and it is not a
Tools
- translate(text, targetlang, sourcelang?, splitsentences?, preserveformatting?, formality?, glossaryid?, taghandling?, outlinedetection?, nonsplittingtags?, splittingtags?, ignore_tags?) — translate text (one or many strings)
- usage() — current month's usage + limits
- source_languages() — supported source languages
- target_languages() — supported target languages
- glossarylanguagepairs() — supported glossary language pairs
text accepts a string or array of strings. targetlang: e.g. EN-US, DE, JA, ES, FR. formality: default | more | less | prefermore | prefer_less.
Data source
https://api.deepl.com/v2 (paid) | https://api-free.deepl.com/v2 (free, auto-selected when key ends with :fx)
Quick Start
Add to your MCP client (Claude Desktop, Cursor, Windsurf, etc.):
{
"mcpServers": {
"deepl": {
"url": "https://gateway.pipeworx.io/deepl/mcp"
}
}
}What this endpoint actually serves
tools/list at https://gateway.pipeworx.io/deepl/mcp returns the tools in the table above plus the shared Pipeworx meta-tools — askpipeworx, discovertools, search_within, remember/recall and the rest of the gateway-wide set. So the tool count you see is larger than this table: a single-pack endpoint currently lists roughly 30 shared tools alongside the pack's own. The connection's initialize response states its exact scope, and is the authoritative answer for a given day.
This is deliberate, not multiplexing by accident. The meta-tools are what let a scoped connection answer a question this pack does not cover — via ask_pipeworx, which routes across the whole catalog — without you adding a second MCP server. There is currently no way to mount a pack endpoint without them; if the extra schemas cost you more context than the routing is worth, connect to the full gateway once rather than to several pack endpoints.
Or connect to the full Pipeworx gateway to get every pack's tools listed directly, instead of just this one's:
{
"mcpServers": {
"pipeworx": {
"url": "https://gateway.pipeworx.io/mcp"
}
}
}Both URLs reach the same gateway and the same 1679+ data sources. The only difference is which pack's tools are listed directly; ask_pipeworx reaches all of them from either one.
No MCP client? Call it over HTTP
Our deepl key is reserved for signed-up accounts (free at https://pipeworx.io), so an anonymous call to POST https://gateway.pipeworx.io/v1/tools/deepltranslate needs your own key passed as apiKey alongside the arguments. Inspect any tool: GET https://gateway.pipeworx.io/v1/tools/deepltranslate. Find one: POST https://gateway.pipeworx.io/v1/tools/searchpacks with {"query":"..."}.
Standalone (no gateway account)
This package also runs as a local stdio MCP server — no Pipeworx account, no gateway round-trip:
{
"mcpServers": {
"deepl": {
"command": "npx",
"args": ["-y", "@pipeworx/mcp-deepl"]
}
}
}Or run it directly to confirm it starts:
Shortened. The full README is on GitHub.
Nothing above is checked by us. What we check is on the safety report.
Deepl: common questions
- Is Deepl MCP server safe?
- Mostly: it is graded B (77/100). Read the Deepl safety report
- How do I install Deepl?
- It runs remotely at gateway.pipeworx.io. Add it to Claude Code, Cursor, VS Code or Claude Desktop with the snippets above, or call it through the mcp.market gateway without installing anything.
- Does Deepl need an API key?
- Yes. The registry entry asks for
PIPEWORX_API_KEY. - Is Deepl maintained?
- The last commit was 40 days ago (2026-09-24). The latest release is v0.2.1.
- Is Deepl up?
- 100% of our last 28 checks got an answer. We check remote servers about four times a day.
- How does Deepl compare with other MCP servers?
- safety score 77/100 (higher than 50% of 48,255 servers); uptime 100% (of our recent checks; the typical remote server answers 100%); response time 106 ms (faster than 83% of 30,031 servers). Full comparison.