translate_textLABSCO SUMMARY
One tool, two transports, a translation engine that is not the model's own.
There is little surface here, text in and translation out, and that is the point: it is the smallest way to give a client a dedicated translation engine. The Lingvanex account is the gate; the server itself is a thin wrapper.
What it is
An MCP server that exposes Lingvanex machine translation as a single tool, running either over stdio for a desktop client or as a local HTTP server for testing.
What you get
- Text translated with an explicit source and target language (translate_text)
- Stdio transport for desktop clients, and streamable HTTP on a port you set
- A ping endpoint that reports status and transport when running over HTTP
- Debuggable through the MCP Inspector against the local streamable HTTP endpoint
Requirements
Node.js 18 or newer, and a Lingvanex account: the Cloud API key is generated after the billing address is filled in, and the free trial does not require a card.
Setup effort
Build from source — git clone https://github.com/lingvanex-mt/MCP-Lingvanex-Translate.git
USE CASES
01
Translating a document into a language the model handles poorly
Send the text with the source and target languages set explicitly.
02
Answering a customer in their own language
Draft the reply, then run it through the translation engine before sending.
03
Localising interface strings
Push each string through the same engine rather than translating them ad hoc.
04
Reading something written in a language you do not have
Translate it into your own language before working with it.
1 tool
Listed in project docs. Your client may show a different list.
BEFORE YOU INSTALL
What to know first
Tools you get
1 tool named in the project's documentation.
Requires
- Node.js >= 18
- L7X_TRANSLATE_API_KEY in your environment
Where it runs
The documented client runs the server on your machine.
INSTALLATION
Connect your client
You clone and build this one yourself.
Server setup
TERMINAL
git clone https://github.com/lingvanex-mt/MCP-Lingvanex-Translate.git
cd MCP-Lingvanex-Translate
yarn install
yarn buildMCP Clients
Claude Desktop
CLAUDE DESKTOP · JSON
{
"mcpServers": {
"translate": {
"command": "node",
"args": [
"<YOUR_PATH_TO_PROJECT>\\dist\\index.js"
],
"env": {
"L7X_TRANSLATE_API_KEY": "<YOUR_L7_X_TRANSLATE_API_KEY>",
"L7X_TRANSLATE_API_URL": "https://api-b2b.backenster.com/b1/api/v3"
}
}
}
}C:\Users\path\to\project is the folder you cloned (the build writes dist/index.js there), and <YOUR_L7_X_TRANSLATE_API_KEY> is the key shown in the Cloud API tab of your Lingvanex account. The server reads the key from L7X_TRANSLATE_API_KEY and the API address from L7X_TRANSLATE_API_URL; the address shown is the one in the project's .env.example.
