LibreTranslate

live TranslationAI

Open-source ML translation. Bring-your-own LibreTranslate-compatible instance (self-host, paid, or community).

3 tools
0ms auth
free tier 50 calls/day
🔑 Authentication

Free public LibreTranslate instances have largely shut down. You must supply your own: self-hosted, libretranslate.com (paid), or a community instance. The pack accepts an endpoint URL + optional API key.

Config with credentials
{
  "mcpServers": {
    "pipeworx-libretranslate": {
      "command": "npx",
      "args": [
        "-y",
        "mcp-remote@latest",
        "https://gateway.pipeworx.io/libretranslate/mcp?_endpoint=https%3A%2F%2Fyour-instance%2F&_apiKey=optional"
      ]
    }
  }
}

Tools

translate required: text, target

Translate text. Source can be "auto".

Parameters
Name Type Description
text req string Text to translate
source opt string Source code or "auto"
target req string Target language code
format opt string text | html
Try it
detect_language required: text

Detect source language.

Parameters
Name Type Description
text req string Text to analyze
Try it
list_languages

Supported languages on the configured instance.

No parameters required.

Try it

Test with curl

The gateway speaks JSON-RPC 2.0 over HTTP POST. You can test any pack directly from the terminal.

List available tools
bash
curl -X POST https://gateway.pipeworx.io/libretranslate/mcp \
  -H "Content-Type: application/json" \
  -d '{"jsonrpc":"2.0","id":1,"method":"tools/list"}'
Call a tool
bash
curl -X POST https://gateway.pipeworx.io/libretranslate/mcp \
  -H "Content-Type: application/json" \
  -d '{"jsonrpc":"2.0","id":2,"method":"tools/call","params":{"name":"translate","arguments":{"text": "hello world", "target": "en"}}}'

Use with the SDK

Install @pipeworx/sdk to call tools from any TypeScript/Node project.

TypeScript
import { Pipeworx } from '@pipeworx/sdk';
const px = new Pipeworx();
const result = await px.call("translate", {"text":"example","target":"example"});
ask_pipeworx
// Or ask in plain English:
const answer = await px.ask("open-source ml translation");