Command Palette

Search for a command to run...

UnylyUnyly
Browse all

Translate

FreeNot checked

Wraps LibreTranslate API to enable translation capabilities for AI agents via MCP.

GitHubEmbed

About

Wraps LibreTranslate API to enable translation capabilities for AI agents via MCP.

README

Translate text, detect a language, or list supported languages against any LibreTranslate-compatible instance.

Part of Pipeworx — an MCP gateway connecting AI agents to 1857+ live data sources. This is an independent, unofficial integration — not affiliated with, endorsed by, or published by the upstream provider.

You need to bring an instance or a key. For translation that works with no key of your own, use mymemory — mymemory_translate is keyless. deepl_translate also covers this when its shared platform key has monthly budget left.

Tools

Tool What it does
translate Translate text between two languages
detect_language Detect the language of a string, with confidence
list_languages Language codes the configured instance supports

Auth

Bring your own, one of:

Given neither, every tool returns {found: false, reason: "requires_key_or_endpoint"} with a pointer to deepl_translate. It does not attempt the call.

Why it is gated

This pack used to hardcode libretranslate.com and call it with no key. That endpoint moved behind an API key, so every call returned the upstream's raw 400 — "Visit portal.libretranslate.com to get an API key" — which reads to a caller as Pipeworx being broken rather than as a source needing a key.

The obvious fallback was a free public mirror. There aren't any left. Checked 2026-08-06:

Instance Result
translate.argosopentech.com does not resolve
libretranslate.com 400, key required
translate.terraprint.co 502
lt.vern.cc 502
translate.fedilab.app 403
libretranslate.eownerdead.dedyn.io 403
trans.zillyhuhn.com 403

So the pack is honestly BYO rather than quietly broken. It is registered in the gateway's BYO_ONLY_KEY_PACKS, which sinks it below the keyless mymemory_translate in routing and labels it, so an agent asking to translate something reaches the tool that can answer.

Data source

LibreTranslate API v1 — https://github.com/LibreTranslate/LibreTranslate#api

Quick Start

Add to your MCP client (Claude Desktop, Cursor, Windsurf, etc.):

{
  "mcpServers": {
    "translate": {
      "url": "https://gateway.pipeworx.io/translate/mcp"
    }
  }
}

What this endpoint actually serves

tools/list at https://gateway.pipeworx.io/translate/mcp returns the tools in the table above plus the shared Pipeworx meta-tools — ask_pipeworx, discover_tools, 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 1857+ 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

This pack takes your own API key (_apiKey) — we don't front one for it, so there's no curl here that would run without it. Inspect any tool: GET https://gateway.pipeworx.io/v1/tools/translate_translate. Find one: POST https://gateway.pipeworx.io/v1/tools/search_packs with {"query":"..."}.

Run it from npm

@pipeworx/mcp-translate is a local stdio bridge to the Pipeworx gateway: your MCP client starts it with npx, and it forwards every call to the same https://gateway.pipeworx.io/translate/mcp endpoint shown above. It needs network access; there is no offline mode.

{
  "mcpServers": {
    "translate": {
      "command": "npx",
      "args": ["-y", "@pipeworx/mcp-translate"]
    }
  }
}

Without a key it calls anonymously, capped at 50 calls a day. A free account raises that to 200 a day: get a key at https://pipeworx.io/signup and add "env": { "PIPEWORX_API_KEY": "<your key>" } to the server entry. The key is sent as a Bearer token, the same way a hosted connection sends it, so calls are metered and billed exactly as they are there.

It lists only this pack's tools by default. Set PIPEWORX_META_TOOLS=1 to also list ask_pipeworx and the other gateway-wide tools.

Behind an HTTPS proxy: Node's built-in fetch does not read HTTPS_PROXY by default. Newer Node releases honour it when NODE_USE_ENV_PROXY=1 is set; check your Node version's documentation.

Using with ask_pipeworx

Instead of calling tools directly, you can ask questions in plain English — this works on the pack endpoint above as well as on the full gateway:

ask_pipeworx({ question: "your question about Translate data" })

The gateway picks the right tool and fills the arguments automatically.

More

License

MIT

from github.com/pipeworx-io/mcp-translate

Installing Translate

This server has no published package — it is built from source. Open the repository and follow its README.

▸ github.com/pipeworx-io/mcp-translate

FAQ

Is Translate MCP free?

Yes, Translate MCP is free — one-click install via Unyly at no cost.

Does Translate need an API key?

No, Translate runs without API keys or environment variables.

Is Translate hosted or self-hosted?

A hosted option is available: Unyly runs the server in the cloud, no local setup required.

How do I install Translate in Claude Desktop, Claude Code or Cursor?

Open Translate on unyly.org, pick your client tab (Claude Desktop, Claude Code, Cursor) and press Install — the config is generated automatically, no JSON editing.

Related MCPs

Compare Translate with

Not sure what to pick?

Find your stack in 60 seconds

Author?

Embed badge for your README

Browse similar

All ai MCPs