@pipeworx/tatoeba
Connect: https://pipeworx.io/mcp — every tool in the catalog, including @pipeworx/tatoeba’s. Install: one-click buttons
Connect to just the @pipeworx/tatoeba pack
https://gateway.pipeworx.io/tatoeba/mcp — only @pipeworx/tatoeba’s own tools, nothing else in the catalog.
No MCP client? Skip the connection: POST https://gateway.pipeworx.io/v1/tools/search_packs {"query":"..."} to find a tool below, GET /v1/tools/<name> for its schema, POST the same URL with arguments for the data — see For AI agents.
Tools: 4
Tatoeba MCP — collaborative multilingual sentence database (~13M sentences in 400+ languages). Keyless.
Tools
search(query, from?, to?, limit?, page?)— sentence searchsentence(id)— single sentence by idtranslations(id)— translations of a sentencelanguages()— list of supported languages
Data source
https://tatoeba.org/eng/api_v0/
Tools
- search — Search sentences. Use ISO 639-3 codes (“eng”,“fra”,“spa”,“jpn”,“cmn”,…) for from/to.
- sentence — Fetch a single Tatoeba sentence record by numeric ID; returns the sentence text, language code, author, and linked audio/translation metadata.
- translations — Translations of a sentence.
- languages — List all languages supported by Tatoeba with their ISO 639-3 codes and sentence counts; use codes as
from/tovalues insearch.
Tools
languages— List all languages supported by Tatoeba with their ISO 639-3 codes and sentence counts; use codes as `from`/`to` values in `search`.search— Search sentences. Use ISO 639-3 codes ( eng , fra , spa , jpn , cmn ,…) for from/to.sentence— Fetch a single Tatoeba sentence record by numeric ID; returns the sentence text, language code, author, and linked audio/translation metadata.translations— Translations of a sentence.