Skip to main content
Glama

Server Details

Language assistant for Slovenian, Croatian and Serbian languages. Checking phrase correctness, ortography check (Slovenian only), text simplification, word forms, similar words, ...

Ownership verified
Status
Healthy
Uptime
100.0% over the last 24 hours
Last Tested
Transport
Streamable HTTP · MCP 2025-11-25
URL
ChatGPT
–
Claude
–

TDQS

A3.9/5.0

Scored across 9 tools

Disambiguation4/5

Most tools target clearly distinct linguistic operations: orthography checking, text evidence, pairing, rule explanation, expressions, forms, lookup, normalization, and replacement suggestions. The main possible overlap is between check_text and check_orthography/normalize_text, and check_text can optionally surface unnatural verb+noun pairs also related to check_pairing, but descriptions sufficiently distinguish scope.

Naming Consistency5/5

All tool names use consistent snake_case and follow a predictable verb_noun pattern: check_*, explain_rule, find_expression, get_forms, lookup_word, normalize_text, suggest_replacements. There are no mixed naming conventions or vague tool names.

Tool Count5/5

Nine tools is well scoped for a language proofreading and lexical resource server. Each tool covers a meaningful operation, and the set avoids both thin coverage and excessive fragmentation.

Completeness4/5

The surface covers orthography, proofreading evidence, corpus pairing, rule lookup, idioms, inflection, word lookup, normalization, and replacements, which supports core proofreading workflows. Some gaps remain, notably grammar/agreement checking is explicitly not covered and there is no general corpus search tool, but these are understandable scope limits rather than dead ends.

Publisher details

Operator
Marko Plahuta, Virostatik s.p. · Publisher source
Vendor relationship
Not applicable
Privacy policy
Not provided
Trust center
Not applicable
Restrictions
Not applicable

Available Tools

9 tools
check_orthographyCheck OrthographyA
Read-onlyIdempotent
Inspect

Slovenian, Croatian and Serbian. Orthography findings, each with the rule's place in the rulebook (Slovenian: § number of Slovenski pravopis 2001; Croatian: chapter, section and page of Hrvatski pravopis, IHJJ 2013; Serbian: point and page of Pravopis srpskoga jezika, Matica srpska 2010), a paraphrase of the rule, the text, a suggested replacement and character offsets. Slovenian: commas before subordinate and adversative clauses, ne + verb, together or apart, s/z and k/h, capitals, spacing, dashes, dates, abbreviations. Croatian: no comma before a dependent clause after its main clause, comma before ali/nego, ne + verb (ne mogu), je li, ni za što, together or apart (nažalost, sa mnom, dvadeset pet), č/ć, ije/je, voicing, sljedeći, HDZ-a, 80-ih, capitals, spacing (50 %, 15 – 17), dates, abbreviations. Serbian (Latin or Cyrillic; findings in the input's script): the future radiću (not radit ću), ne + verb, da li, ni za šta, together or apart (nažalost, u stvari, na primer, sa mnom), Serbian forms (ko, uopšte, opšti, zadaci, tužilac), no mixing of ekavian and ijekavian, no comma before declarative da or nego što, 55%, 1941–1945, XX vek, dr without a full stop, NATO-a, capitals. kind says how sure a finding is: mechanical (the rule decides), heuristic (usually right), lexical (decided from the lexicon and corpus counts). Not checked: the comma after a leading or embedded clause (Serbian: opt-in rule comma_leading_clause), grammar, loanword spelling.

Inputs: text (required), lang, rules. Returns: object

check_pairingCheck PairingA
Read-onlyIdempotent
Inspect

Is a word pairing natural? For a two-word phrase: whether the corpus pairs them, how strongly, and the words that usually take each one's place (napraviti odluku -> donijeti). For one word: its usual partners. Catches word-for-word translations.

Inputs: lang (required), word, limit, phrase, +1 more. Returns: object

check_textCheck TextA
Read-onlyIdempotent
Inspect

Proofreading evidence for a text: words found in neither the corpus nor the lexicon (misspelled or invented), known misspellings, missing diacritics, rare words, a word repeated three or more times within 60 words, and optionally unnatural verb + noun pairs. Returns findings with character offsets, not a corrected text. Grammar (agreement, case after prepositions) is not checked.

Inputs: lang (required), text (required), pairings. Returns: object

explain_ruleExplain RuleA
Read-onlyIdempotent
Inspect

The orthography rules check_orthography applies and the parts of the rulebook that match a query (Slovenski pravopis 2001 for sl, Hrvatski pravopis IHJJ 2013 for hr, Pravopis srpskoga jezika, Matica srpska 2010 for sr): rule, where it stands in the book, a paraphrase, and how reliable the check is. Use it to justify a correction to the user. The rulebooks are paraphrased, not quoted.

Inputs: query (required), lang. Returns: object

find_expressionFind ExpressionA
Read-onlyIdempotent
Inspect

Fixed expressions and idioms with their meaning, register and whether they are figurative: find one for an idea, or explain one. Covers the expressions kontekst has explained (about 870 Slovenian, 3,000 Croatian, 1,500 Serbian).

Inputs: lang (required), limit, concept, expression. Returns: object

get_formsGet FormsA
Read-onlyIdempotent
Inspect

Inflected forms from the lexicon: one form (with features or like) or the whole table. Each form says whether it occurs in the corpus (attested); prefer attested forms.

Inputs: lang (required), word (required), like, features. Returns: object

lookup_wordLookup WordB
Read-onlyIdempotent
Inspect

What kontekst knows about each word: lemma and grammatical readings, corpus count and frequency band (1 rarest .. 5 commonest), standard spelling if it is a variant, loanword flag, and the parts asked for in include.

Inputs: lang (required), words (required), include. Returns: object

normalize_textNormalize TextA
Read-onlyIdempotent
Inspect

Cleaned text plus a list of every change. For text typed without diacritics, from speech recognition or OCR, or for analytics. Changes a word only when the evidence is clear (the winning spelling at least 5x commoner); the rest are listed in undecided with their options. Words the lexicon knows are never respelled except to add diacritics or fix broken encoding.

Inputs: lang (required), text (required), steps. Returns: object

suggest_replacementsSuggest ReplacementsA
Read-onlyIdempotent
Inspect

Alternatives for a word, each already inflected to the same case, number, gender and person as the input (konzistentnoj -> dosljednoj), so it can be dropped into the sentence. Candidates come from kontekst's similar-word lists: they can be related or opposite words rather than synonyms, so choose by meaning. When the input form is ambiguous (several readings), other_readings gives each candidate's form per reading; pick the one the sentence needs.

Inputs: lang (required), word (required), goal, safe, +2 more. Returns: object

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    Related MCP Servers

    • A
      license
      Not graded
      quality
      C
      maintenance
      Remote MCP server that lets AI assistants read tracked competitive intelligence — competitor news, reviews, website changes, social posts and ads — and act on it by managing projects, competitors, battle cards, reports and canvases. Every answer carries a source and a date, and write actions only publish when explicitly shared.
      MIT
    • A
      license
      A
      quality
      D
      maintenance
      Enables brand visibility monitoring across major AI platforms like ChatGPT, Claude, Gemini, and Perplexity. It allows users to track visibility scores, analyze competitor data, and receive actionable insights to improve AI-generated brand recommendations.
      16
      11 npm
      1
      MIT
    • A
      license
      Not graded
      quality
      C
      maintenance
      Browse IndustryLens's published competitive-intelligence reports and head-to-head competitor comparisons from any AI agent — real, source-backed data.
      MIT
    Try in Browser

    Glama MCP Gateway

    Add one secure layer between your agents and this server.

    Resources