Connects Claude to Tatoeba's 13 million sentence corpus covering 400+ languages. Exposes four tools: search sentences by language pair using ISO 639-3 codes, fetch individual sentences by ID, retrieve translations for a sentence, and list supported languages. Useful when you need real world example sentences for translation work, language learning applications, or building multilingual datasets. Part of the Pipeworx gateway ecosystem, so you can either connect directly to the Tatoeba endpoint or access it through their unified gateway alongside 670+ other data sources. Supports the ask_pipeworx interface for natural language queries instead of direct tool calls.
Tatoeba MCP — multilingual sentence corpus.
Part of Pipeworx — an MCP gateway connecting AI agents to 673+ live data sources.
| Tool | Description |
|---|---|
search | Search sentences. Use ISO 639-3 codes ("eng","fra","spa","jpn","cmn",…) for from/to. |
sentence | Single sentence by id. |
translations | Translations of a sentence. |
languages | Supported languages. |
Add to your MCP client (Claude Desktop, Cursor, Windsurf, etc.):
{
"mcpServers": {
"tatoeba": {
"url": "https://gateway.pipeworx.io/tatoeba/mcp"
}
}
}
Or connect to the full Pipeworx gateway for access to all 673+ data sources:
{
"mcpServers": {
"pipeworx": {
"url": "https://gateway.pipeworx.io/mcp"
}
}
}
Instead of calling tools directly, you can ask questions in plain English:
ask_pipeworx({ question: "your question about Tatoeba data" })
The gateway picks the right tool and fills the arguments automatically.
MIT