Be the first to get access to new connectors. Get early access →
ConnectorBay Early access

Lexicon — connector documentation

  • MCP endpoint: https://lexicon.connectorbay.com/mcp
  • REST API: POST https://lexicon.connectorbay.com/v1/tools/{tool_name}, described by the OpenAPI 3.1 spec at https://lexicon.connectorbay.com/openapi.json
  • Transport: Streamable HTTP, stateless, MCP specification 2025-06-18 or later
  • Authentication: none required. An optional Authorization: Bearer <key> raises rate limits.
  • Health: https://lexicon.connectorbay.com/health · Tool schemas: https://lexicon.connectorbay.com/tools.json
  • Publisher: Unify Dynamics LLC · connectorbay.com/lexicon · agent@connectorbay.com

What Lexicon is for

Words, answered precisely instead of from memory: what a word means and how it is said, another word for it, what rhymes with it, what fits c?a?? with no r, s, t, l or n, what can be made from a Scrabble rack, whether it is "definitely" or "definately", where "salary" comes from, and what a butterfly is called in Hindi. Lexicon reads the Free Dictionary API, Wiktionary, Datamuse and Wikipedia's language links, and bundles a public-domain word list so the puzzle tools work offline and instantly.

What it does

Definitions with IPA, audio, meanings by part of speech, examples, synonyms and antonyms (English via the Free Dictionary API, other languages via Wiktionary). Pronunciation with ARPAbet and syllable counts. Fifteen thesaurus relations — synonyms, antonyms, related, broader/narrower, parts/wholes, adjectives for a noun, words that follow or precede, sound-alikes, homophones. Perfect and near rhymes with syllable filtering. A word finder for crosswords and Wordle (pattern, length, prefix/suffix, must-contain and excluded letters) and by meaning. Anagrams and Scrabble scores. Spelling check with corrections and a corrected passage. Etymology from Wiktionary rendered as plain text. A term's title in 100–300 languages from Wikipedia. Readability statistics (Flesch, Flesch–Kincaid, Gunning Fog, ARI, Coleman–Liau), reading time and top words, computed locally. A word of the day from a curated list of 560.

What it is not

Lexicon is an English-first dictionary and word toolkit, not a translator: term_in_languages gives the Wikipedia article title for a concept, which is a name rather than a dictionary translation. The bundled word list (ENABLE) uses US spellings and has no proper nouns, so "not in the list" does not mean "not a word". Wiktionary text is community-written and CC BY-SA.

Tools

Dictionary

define — Define a word: pronunciation (IPA + audio), meanings grouped by part of speech with example sentences, synonyms and antonyms, and the source page. English via the Free Dictionary API with Wiktionary as fallback; other languages via Wiktionary. Use for "what does X mean", "define X", "X meaning", "is X a noun or a verb". Args: word, language.

pronunciation — How to say a word: IPA transcription, ARPAbet phonemes, syllable count, audio clips (US/UK) and a plain respelling hint. Use for "how do you pronounce X", "how many syllables in X". Args: word.

etymology — Where a word comes from: the Etymology section(s) of its English Wiktionary entry as plain text (one per sense, when the word has several origins). Use for "origin of the word X", "why is it called X". Args: word.

word_of_the_day — A word of the day — the same word for everyone on a given date — from a curated list of 560 memorable words, with its definition, pronunciation and examples. Use for "word of the day", "teach me a new word". Args: day.

Thesaurus & rhymes

thesaurus — Thesaurus and word relations from Datamuse: synonyms, antonyms, semantically related words, broader/narrower terms (hypernyms/hyponyms), parts and wholes, adjectives commonly used with a noun (or nouns for an adjective), words that typically follow/precede, sound-alikes and homophones. Each result has parts of speech, frequency and a short gloss where available. Use for "another word for X", "opposite of X", "adjectives for coffee", "what's more general than X". Args: word, relation, max_results.

rhymes — Rhymes for a word — perfect rhymes or near (slant) rhymes — with syllable counts and word frequency, optionally filtered to a syllable count. Use for songwriting, poetry, "what rhymes with X". Args: word, kind, syllables, max_results.

Puzzles & spelling

word_finder — Find words by pattern and/or meaning: crossword fills ('c?a??'), Wordle candidates (pattern + must-contain + excluded letters), prefix/suffix/length searches, or "words that mean X starting with Y". Pattern-only searches run against the bundled ENABLE list (offline); meaning searches use Datamuse and include a gloss. Use for "5-letter words starting with s ending in e", "words for 'brave' that start with v", "what fits a_e". Args: pattern, means_like, starts_with, ends_with, length, must_contain, exclude, max_results.

anagrams — Words that can be made from a set of letters (each letter used once; '?' is a blank), longest and highest-scoring first, with full anagrams listed separately and Scrabble scores. Also tells you whether a single word is valid in the word list. Use for Scrabble/Words With Friends racks, anagram puzzles, "what words can I make from X". Args: letters, min_length, max_results.

spell_check — Check spelling of a word or passage: flags words not in the dictionary and proposes corrections (Wiktionary's 'misspelling of' data plus closest dictionary words). Proper nouns and rare terms may be flagged — say so. Use for "is X spelled right", "check this for typos". Args: text.

Languages & text

term_in_languages — What a term is called in other languages, from the language links of its English Wikipedia article — typically 100–300 languages for common concepts, each with the language name and native script. Best for nouns and concepts; it is a title-level translation, not a dictionary. Use for "how do you say butterfly in other languages", "what is photosynthesis called in Hindi and Japanese". Args: term, languages.

text_stats — Readability and word statistics for a passage: word/sentence/syllable counts, Flesch Reading Ease, Flesch–Kincaid grade, Gunning Fog, ARI, Coleman–Liau with a plain-English verdict, reading and speaking time, lexical diversity, top words and longest words. Computed locally; the text is not sent anywhere. Use for "how readable is this", "what grade level is this writing", "word count and reading time". Args: text.

Conventions

  • Read-only. Every tool reads public data or computes; nothing is written anywhere and nothing about the user is stored.
  • Result envelope. ok: true with data, or ok: false with a structured error (bad_input, not_found, upstream_error). degraded lists optional sources that were unreachable.
  • Rate limits. Free tier 60 tool calls/minute and 300/day per user (keyed on the user identifier supplied by the host agent, else client IP); Pro keys raise this. Over-limit calls return HTTP 429 with Retry-After. initialize and tools/list are never counted.

Support

agent@connectorbay.com · connectorbay.com/lexicon/support