@pipeworx/wiktionary

Connect: https://pipeworx.io/mcp — every tool in the catalog, including @pipeworx/wiktionary’s. Install: one-click buttons

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: 5

Wiktionary MCP — multilingual dictionary content via the MediaWiki REST API. ~6M entries across hundreds of languages. No auth.

Tools

• definition(word, lang?) — parsed definitions grouped by language section (uses Wikimedia’s rest_v1/page/definition)
• summary(word, lang?) — page summary
• search(query, lang?, limit?) — title-prefix + fulltext search
• etymology(word, lang?) — extracts the Etymology section
• pronunciations(word, lang?) — extracts IPA pronunciation rows

Languages

lang is the Wiktionary subdomain code: en (default), fr, de, ja, zh, es, …

Data source

• https://<lang>.wiktionary.org/api/rest_v1/
• https://<lang>.wiktionary.org/w/api.php (for search + wikitext extraction)

Tools

• definition — Parsed definitions grouped by part-of-speech sections.
• summary — Fetch the Wiktionary REST page summary (title, extract, thumbnail) for a word on the specified language subdomain (default en).
• search — Wiktionary title + fulltext search.
• etymology — Etymology section extracted from wikitext.
• pronunciations — IPA / phonetic transcriptions extracted from wikitext.