Libretranslate

@pipeworx/libretranslate

LibreTranslate MCP — thin abstraction over any LibreTranslate-compatible instance.

Part of Pipeworx — an MCP gateway connecting AI agents to 1476+ live data sources.

Tools

• translate(text, target, source?, format?)
• detect_language(text)
• list_languages()

Auth / endpoint

LibreTranslate's free public instances have largely shut down or migrated to paid. You must provide an instance:

• Self-host: https://github.com/LibreTranslate/LibreTranslate
• Paid: https://libretranslate.com (BYO their API key)
• Community instance that's still up

Configure via:

• Platform: gateway env vars PLATFORM_LIBRETRANSLATE_ENDPOINT (URL) and optionally PLATFORM_LIBRETRANSLATE_KEY.
• BYO: pass ?_endpoint=https://your-instance/&_apiKey=... on the gateway URL.

Data shape

Standard LibreTranslate v1 API — see the spec.

Public instances (verified 2026-08-06)

Every free public instance this pack could have defaulted to is gone, so there is no keyless path. Checked on the date above:

Unconfigured, every tool now returns {found: false, reason: "requires_endpoint"} naming deepl_translate — rather than throwing, which booked as a tool error and was indistinguishable in the logs from the upstream being down. The pack is in the gateway's BYO_ONLY_KEY_PACKS so routing sinks it below the translation tool that can answer without the caller's key.

Quick Start

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

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

What this endpoint actually serves

tools/list at https://gateway.pipeworx.io/libretranslate/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 1476+ data sources. The only difference is which pack's tools are listed directly; ask_pipeworx reaches all of them from either one.

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 Libretranslate data" })

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

More

• Docs and guides
• pipeworx.io

License

MIT

No MCP client? Call it over HTTP

curl -X POST https://gateway.pipeworx.io/v1/tools/libretranslate_translate \
  -H 'Content-Type: application/json' \
  -d '{"text":"Hello, how are you?","target":"es"}'

No account needed for the first calls. Inspect any tool: GET https://gateway.pipeworx.io/v1/tools/libretranslate_translate. Find one: POST https://gateway.pipeworx.io/v1/tools/search_packs with {"query":"..."}.