estonian-mcp

smithery/silly-geese/estonian-mcp

Estonian NLP tools so AI agents stop hallucinating Estonian. 28 read-only tools wrapping EstNLTK, EKI Reeglid, and Riigi Teataja: spell-check, morphological analysis, lemmatization, full inflection paradigms, WordNet synonyms, fastText related words, named-entity recognition, orthography/grammar checks (capitalization, compounds, commas, numbers, abbreviation hyphenation, object case, register, style, redundancy, calque risk), compound attestation and an organisation’s own domain glossary, editorial checks that catch kantseliit in reports and academic prose, flag a document that names one thing three ways and spot Estonian that keeps English sentence structure, plus legal-Estonian tools (legalese simplification that protects terms of art, defined-term + cross-reference tracking, and canonical legal-usage collocations from public-domain legislation). Paradigms cover ordinals, comparatives, superlatives and proper nouns, include the short illative (majja beside majasse), and lead every slot with the form built on that paradigm’s own stem, so raamatutele comes before the literary raamatuile. A word with two inflection types (kott inflects as either koti or kota, two different words sharing a nominative) returns one consistent table per type instead of a merged one. Results are lean: one compact block per call, no echoed input, about half the tokens of earlier versions. Offline and PII-free: no third-party calls and nothing stored, and self-hosted, confidential text never leaves the machine. Works in Claude, ChatGPT and Codex, and is listed in Anthropic’s official Connectors Directory. Scores 99.1% on TalTech’s inflection_et and 100% once the 13 gold rows that contradict EKI are adjudicated, plus 99.3% first-form over all fourteen cases on 11,011 rows of real Estonian text. Use it as ground truth so the model stops inventing Estonian spelling and case forms and stops guessing whether a word fits its register or its domain.