Skip to main content
Glama
language-mcp

language-mcp

language-mcp

A local MCP server for Dutch, US English, and French language checks, built for AI agents (Hermes, Claude, and others) that write resumes, cover letters, blog articles, and website copy.

Currently supported: Dutch, US English, and French. Additional languages can be implemented by adding dictionaries, language-specific rules, and MCP tools; they are not supported automatically by selecting an arbitrary language.

Tools

Tool

Source

Network

Purpose

check_us_english_text

hunspell en_US + British form detection (local)

No

Check text for typos and British spelling or vocabulary, with US replacements

check_us_english_b1_text

hunspell en_US -m + rule layers (local)

No

B1 plain-language proxies: readability (Flesch Reading Ease, Flesch-Kincaid, ARI), sentence/paragraph length, passive voice, jargon, wordy phrases, hidden verbs, filler, idioms, nominalization density, "you" address

validate_us_english_word

hunspell en_US + British form detection (local)

No

Check a single English word for correct US English spelling and suggest replacements

check_dutch_text

OpenTaal/hunspell + selected spelling rules (local)

No

Check words and selected compounds, hyphens, and calendar capitalization; return suggestions, positions, rule IDs, explanations, confidence, and source links

check_dutch_b1_text

OpenTaal/hunspell -m + rule layers (local)

No

B1 simplicity proxies: readability (Flesch-Douma, ARI, LIX, Brouwer Leesindex), sentence/paragraph length, passive voice, officialese jargon, filler, idioms, rare-word flags from a Zipf frequency table with plain-synonym suggestions (Open Dutch WordNet), nominalization density, je/u voice

validate_dutch_word

OpenTaal/hunspell (local)

No

Check a single Dutch word locally for correct spelling, with suggestions

check_french_text

hunspell fr (Dicollecte, "toutes variantes") (local)

No

Spell-check French text: unknown words with suggestions and positions; elisions with straight or typographic apostrophes, hyphenated words, and non-breaking spaces handled

check_french_b1_text

hunspell fr -m + rule layers (local)

No

B1 plain-language proxies: readability (Kandel & Moles), sentence/paragraph length, passive voice (être + participle), tu/vous address form (default vous)

validate_french_word

hunspell fr (local)

No

Check a single French word for correct spelling and suggest replacements

get_dutch_word_details

woordenlijst.org (MolexServe)

Yes

Retrieve lemma details: part of speech, pronunciation, hyphenation, paradigm, and diminutive forms

The local tools use bundled hunspell dictionaries: OpenTaal for Dutch (v2.20.23) and SCOWL/LibreOffice en_US for US English. The detector for British forms catches terms that hunspell does not flag (whilst, towards, bespoke, webshop, sole trader, findability, etc.), including categories from the Straffe Sites US English guidelines, and provides a US replacement for each match.

French uses the Dicollecte/Grammalecte dictionary (v7.7, "toutes variantes": both traditional and 1990 reform spellings are accepted). Details, limits, and licenses: French checks.

get_dutch_word_details queries the internal XML service at woordenlijst.org (INT/Taalunie). This unofficial integration uses caching and rate limiting (1.2 seconds between calls); use it only for individual important words. Tool descriptions and status messages are in US English; Dutch words and upstream dictionary labels retain their original language.

Related MCP server: eyd-v

Dutch spelling rules

check_dutch_text also checks selected patterns that a word dictionary misses: btw nummer → btw-nummer, keuken tafel → keukentafel, auto ongeluk → auto-ongeluk, and 3D printer → 3D-printer. Calendar cues such as op Maandag and in Januari produce medium-confidence suggestions for lowercase spelling. Each rule finding includes its ID, explanation, original source positions, confidence, and a precise Team Taaladvies source link.

The rule layer protects code, marked headings, quotations, and other selected non-prose spans. Pass optional protected_terms for exact case-sensitive names or unmarked titles; horizontal whitespace may vary. Words inside an occurrence of a protected term are also not reported as unknown (the same contract as in check_us_english_text and check_french_text); the same words elsewhere in the text are still checked. All three spelling tools take protected_terms since v0.11.0. Accepted variants such as rode kool / rodekool, optional clarity hyphens, and meaning-dependent word groups are not automatically joined or rewritten.

This is a small, local spelling layer, not a general grammar checker. See the rule catalog, exceptions, limits, and attribution. B1 readability remains a separate check.

B1 simplicity checks

Both B1 tools report deterministic proxies with the same structure: a readability block, passive voice, rule hits with plain alternatives and positions in the source text, nominalization density, and a reader-address check. Thresholds are tool parameters because conventions differ by sector.

Dutch

check_dutch_b1_text reports deterministic B1 proxies, not a validated B1 verdict: "B1" applied to texts is an editorial convention (Rijksoverheid guideline: write new material at B1, aiming for A2), not an empirically validated text norm. What the tool measures:

  • Readability: Flesch-Douma reading ease (NL-adapted Flesch; practical B1 band ~60-70; the band label names the text: easier than B1, B1, harder than B1, much harder than B1), ARI as a second, language-neutral indication, LIX (Björnsson 1968; Swedish scale, not validated for Dutch — compounds inflate it), and Brouwer Leesindex A (1963 Dutch Flesch recalibration that weighs sentence length twice as heavily as Flesch-Douma). Formulas are suppressed below 50 words / 3 sentences (short-sample guard; the guard is intentional, see the evaluation baseline).

  • Word frequency: rare-word flags from a bundled Zipf table of the top 50,000 Dutch word forms (derived from FrequencyWords/OpenSubtitles2018 — spoken-language bias, documented in assets/frequency/README.md). Words the table knows but scores rare (default below Zipf 3, configurable via rare_word_zipf_max) are flagged with value, count, and position. Unknown words are never flagged: Dutch compounds and proper names dominate that set. When Open Dutch WordNet lists a clearly more frequent single-word synonym (at least half a Zipf point), the flag includes concrete suggestions ("staken → try: ophouden, stoppen"); suggestions are review hints, never automatic replacements.

  • Sentence and paragraph length against configurable thresholds (defaults: warn >15, flag >20 words per sentence; 150 words per paragraph, matching common editorial guidelines).

  • Passive voice: hunspell -m morphology batch plus an auxiliary window (wordt/worden/werd + past participle = high confidence; is/zijn + past participle = low-confidence zijn-passive; "door" agent noted). These are review flags: context-free morphology cannot tell a genuine passive from a copula construction, so editors judge each hit.

  • Officialese jargon with plain alternatives (betreffende → over, thans → nu, in het kader van → voor...), filler words, and idioms to avoid for NT2 readers, each with the match position in the source text.

  • Nominalization density (-ing/-tie/-heid/-iteit words per 100 words) and je/u voice consistency (default je, configurable to u).

All checks are local and offline: the same bundled OpenTaal assets and hunspell binary as the spelling tools, plus pure TypeScript rule layers in the spirit of the British-form detector.

The Dutch B1 proxies are grounded in an evaluation baseline: the bundled City of Amsterdam complex–simple corpus (1,311 sentence pairs, EUPL-1.2, evaluation-only — nothing from it runs at check time) with a harness that measures how much more often each proxy flags the complex side of a pair (tests/eval/b1-amsterdam.ts, committed baseline in tests/eval/baseline-v1.json, protocol in docs/b1-eval.md). On that set, passive voice separates +11.8 percentage points and sentence length +10.4; the rare-word signal separates +3.8; nominalization density and the long-word share barely separate, and the readability formulas have 0% coverage on single sentences because of the short-sample guard.

US English

check_us_english_b1_text applies the same approach to US English, with English formulas, thresholds, and rule sources:

  • Readability: Flesch Reading Ease (practical B1 band 60-70, "plain English" in Flesch's table), Flesch-Kincaid grade level (default target 9 or lower), and ARI. A zero-dependency syllable counter agrees with the CMU Pronouncing Dictionary on about 94% of the 10,000 most common US English words. The same short-sample guard applies.

  • Sentence and paragraph length: defaults warn above 20 and flag above 25 words per sentence (plainlanguage.gov average and the GOV.UK limit), and the longest flagged sentences are listed with positions.

  • Passive voice: hunspell -m with the bundled en_US dictionary marks regular -ed forms (affix flag D); a closed list covers irregular participles (written, built, sold). Detects be-passives, get-passives, and pronoun contractions ("it's built"), notes a "by" agent, skips "used to", and marks adjectival uses ("is located") as low confidence.

  • Formal jargon and buzzwords (utilize → use, prior to → before, robust, leverage), wordy phrases (in order to → to, due to the fact that → because), hidden verbs (make a decision → decide, provide assistance → help), filler words, and idioms, based on the Federal Plain Language Guidelines and the GOV.UK "words to avoid" list. British spellings stay in check_us_english_text.

  • Nominalization density (-tion/-sion/-ment/-ance/-ence/-ity per 100 words, everyday nouns excluded) and reader address: third-person references to the reader ("users", "the customer") are reported when the expected address is "you" (default).

French

check_french_b1_text applies the same approach to French (details and honest accuracy statements in docs/french.md):

  • Readability: Kandel & Moles (1958), the French adaptation of Flesch Reading Ease (207 - 1.015 * words/sentences - 73.6 * syllables/words), with a French syllable counter in its own module (mute final e not counted; 99.5% exact on the 10,000 most frequent spellings of Lexique 3.83). The same short-sample guard applies, and the score is an estimate because syllables are counted heuristically.

  • Sentence and paragraph length: defaults warn above 20 and flag above 25 words per sentence, 150 per paragraph; all are tool parameters.

  • Passive voice: être + past participle, precision first. Regular -é participles come from the dictionary morphology, common irregular ones from a closed list; participles of verbs that take être in compound tenses (arrivé, parti) and reflexive forms are skipped. Hits are review flags.

  • Address form: voice defaults to vous and reports tu, toi, te, t', ton, ta, tes, tien(ne)(s) (or the reverse for voice: tu). Quotations are reported separately.

  • No B1 verdict, no jargon or wordy-phrase layers.

Checking a file: path, ranges, and hashes

The six check tools (check_dutch_text, check_dutch_b1_text, check_us_english_text, check_us_english_b1_text, check_french_text, check_french_b1_text) accept either text or path. With path, the server reads the local UTF-8 file itself, so an agent never has to retype a long document into a tool call. Every report includes an Input: line with the SHA-256 of the exact text that was checked:

Input: file /abs/cv.md, range [0, 5401) of 5401 code points, 5401 code points checked, input_sha256 9f2c…, file_sha256 9f2c…

Argument

Meaning

path

Absolute path of a UTF-8 text file (max 2 MiB; binary and invalid UTF-8 are refused).

start, end

Optional half-open range [start, end) in Unicode code points of the file.

expected_sha256

Optional hex SHA-256 the checked text must have. On a mismatch nothing is checked and the tool returns an error. Works with text too.

Hashes cover the exact UTF-8 bytes without normalization, so for a whole file input_sha256 equals sha256sum <file>. With a range, finding positions are relative to the range start. To limit which folders the server may read, set LANGUAGE_MCP_ROOTS to one or more folders (separated by :, or ; on Windows); without it, any file readable by the server process is allowed. A set variable that names no folder refuses every path.

Spell checks stop after 20,000 words. When that happens the report starts with INCOMPLETE: and the tool returns an error, so a partial check never counts as full coverage: split the file into ranges instead.

This supports full-coverage review: a lead agent records the file hash or chunk hashes in its manifest, delegates the checks per chunk, and verifies that each report's input_sha256 matches.

Example: check US English copy

Call check_us_english_text with:

{
  "text": "We build custom online stores with colorful designs and clear navigation."
}

The tool reports the number of words checked, unknown words, and British forms. It provides suggestions and positions for flagged words. Review suggestions in context: proper names and technical terms may be valid even when flagged. For plain-language checks on the same copy, call check_us_english_b1_text with the same text. For Dutch copy, use check_dutch_text and check_dutch_b1_text instead; for French copy, use check_french_text and check_french_b1_text.

Installation

Requirements: Node 20+ and hunspell on PATH (pacman -S hunspell).

npm install
npm run build   # Compile TypeScript into dist/

Tests

npm test        # Run node:test through tsx

Hermes configuration (stdio)

mcp_servers:
  language:
    command: node
    args: [/absolute/path/to/language-mcp/dist/cli.js]
    connect_timeout: 60
    enabled: true
    timeout: 120

License and attribution

Code: MIT.

Dictionary assets:

  • assets/nl.dic / assets/nl.aff: © OpenTaal — Revised BSD License and/or CC BY 3.0. Full terms are in assets/LICENSE.txt; source: https://github.com/OpenTaal/opentaal-hunspell. Reusing these assets requires attribution to OpenTaal.

  • assets/en_US.dic / assets/en_US.aff: based on the SCOWL word list (Kevin Atkinson, LGPL), with an affix file from Geoff Kuenning's Ispell (BSD), distributed through LibreOffice/dictionaries. See assets/en_US-LICENSE.txt and assets/en_US-README.txt; source: https://github.com/LibreOffice/dictionaries/tree/master/en.

  • assets/fr.dic / assets/fr.aff: French dictionary from Dicollecte/Grammalecte v7.7 by Olivier R., variant "toutes variantes", © the Dicollecte contributors, licensed under the Mozilla Public License 2.0. Source: https://grammalecte.net/ (archive https://grammalecte.net/download/fr/dic/hunspell-french-dictionaries-v7.7.zip, downloaded 2026-11-10, SHA-256 and provenance cross-check in assets/fr-SOURCE.txt). The files are unmodified copies. See assets/fr-LICENSE-MPL-2.0.txt and assets/fr-README.txt. MPL 2.0 is file-level copyleft: it applies to these dictionary files, not to the MIT-licensed code, and changes to the dictionary files themselves must stay under MPL 2.0.

Data assets (each bundled with its own license and attribution file, kept separate from the MIT code):

  • assets/frequency/nl-zipf.tsv: Zipf frequencies for the top 50,000 Dutch word forms, derived from hermitdave/FrequencyWords nl_50k.txt (OpenSubtitles2018). Content CC BY-SA 4.0; see assets/frequency/README.md (includes the spoken-language bias caveat).

  • assets/synonyms/nl-synonyms.tsv: Dutch synonym table (31,199 lemmas), derived from Open Dutch WordNet release 1.4 (VU Amsterdam, CLTL). CC BY-SA 4.0; see assets/synonyms/LICENSE and assets/synonyms/README.md. When using this data, cite: Postma, Van Miltenburg, Segers, Schoen & Vossen (2016), "Open Dutch WordNet", Proceedings of the 8th Global WordNet Conference. CC BY-SA obligations apply to distributing the derived data, not to texts checked with the tool.

  • assets/eval/amsterdam-complex-simple/: City of Amsterdam complex–simple sentence pairs (EUPL-1.2) and the Hobo 2022 lexical-simplification set, bundled as evaluation-only assets for the B1 harness; never used at runtime. See the README in that directory.

Evaluation baselines (tests/eval/) are committed artifacts of the runs documented in docs/b1-eval.md.

get_dutch_word_details data: woordenlijst.org (Instituut voor de Nederlandse Taal / Taalunie), accessed through its public web service without a separate API agreement.

Available Tools

5 tools
check_dutch_textA

Spell-check Dutch text locally (OpenTaal/hunspell). Returns unknown words with suggestions and positions. Use for CVs, cover letters, blog articles, any Dutch prose.

Inputs: text (required), context.

check_us_english_textA

Check English text for US English compliance: typos (hunspell en_US) + British spellings/vocabulary (colour, whilst, towards, bespoke, webshop, sole trader...) with US replacements. Use for EN pages, blogs, US-facing copy.

Inputs: text (required).

dutch_word_detailsA

Get official Dutch word details from woordenlijst.org: lemma, woordsoort, uitspraak, syllabisering/afbreking, verkleinwoord, paradigm. Slower (network); use for individual important words, not bulk.

Inputs: word (required).

validate_dutch_wordA

Check quickly (lokaal) of één Nederlands woord correct gespeld is, met suggesties bij foute spelling.

Inputs: word (required).

validate_us_wordA

Check quickly (lokaal) of één Engels woord correct gespeld is volgens US English, met suggesties. Detecteert ook Britse spelling voor losse woorden.

Inputs: word (required).

Tool Schema Changelog

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

Loading tool schema changelog…

    TDQS

    A4/5.0

    Scored across 5 tools

    Disambiguation5/5

    Each tool has a clear, distinct purpose: full-text checking (check_us_english_text, check_dutch_text) vs single-word validation (validate_us_word, validate_dutch_word) vs dictionary lookup (dutch_word_details). The descriptions explicitly state scope (text vs one word), eliminating ambiguity. Even the English and Dutch pairs are clearly separated by language and granularity.

    Naming Consistency4/5

    Naming follows a consistent verb-based pattern: 'check_' for full-text tools and 'validate_' for single-word tools, with language identifiers. However, 'dutch_word_details' deviates from the pattern (no verb, inverted noun order) and English language identifiers vary ('us_english' vs 'us'). Overall readable, but minor inconsistencies prevent a perfect score.

    Tool Count5/5

    Five tools is a well-scoped size for a language-checking server, covering both Dutch and US English at two levels (bulk text and individual words) plus a dictionary lookup. Each tool serves a distinct need without redundancy, and the count is not excessive or trivial.

    Completeness4/5

    The surface covers the core workflows: checking full text for both languages, validating individual words, and providing Dutch word details. Minor gaps exist, such as no English dictionary details and no explicit grammar checking, but the stated purpose (spelling and US English vocabulary compliance) is fully addressed. Agents can accomplish common tasks without dead ends.

    Related MCP Connectors

    • 111 tools for AI assistants, so an answer comes from a rule instead of a guess. 84 deterministic utilities. IBAN and VAT validation, cron parsing, regex testing, hashing, JWT decoding, conversion between JSON, CSV, XML and YAML, units, number bases, timezones and date arithmetic. Eleven of them encode Dutch rules that a model tends to get wrong: AOW pension age, inheritance and gift tax, unemployment benefit duration, notice period, severance, the 30 percent ruling, holiday allowance, mileage allowance, and public and school holidays. Five more generate test data that is structurally valid and belongs to nobody: BSN, IBAN, BRP person records, UPA pension files and document numbers. 14 render tools that return a hosted file. HTML or a live URL to PDF, full page screenshots, QR codes, PDF merge and split, images to PDF, image resize, convert and compress, metadata stripping, PDF to DOCX and back. Plus read_page, which returns the readable content of a JavaScript rendered page as Markdown. 4 memory tools give an agent key-value state that survives between sessions, scoped to its own API key. 3 workflow tools list and run saved multi-step workflows on the caller's account. 6 AI tools for the jobs where a model is the right instrument rather than the wrong one: check a message for scam patterns, write a spreadsheet formula, turn a question into SQL, translate code between languages, improve a prompt, draft an email. Utilities and memory are free. Renders and AI tools have a free tier and credit packs. Workflows need an API key, because a workflow belongs to an account rather than to a key. Streamable HTTP at https://toolforte.com/api/mcp

      https://toolforte.com/api/mcp
    • Utility tools for AI agents: hashing, text stats, validation, DNS, currency, GEO audits.

      https://api.sprytools.com/mcp
    • Live web checks for AI agents: sitemaps, robots.txt, URL status, broken links, feeds, citations.

    • Real-world data for agents: air quality, geocoding, quakes, holidays, web search

    Related MCP Servers

    • A
      license
      Not graded
      quality
      B
      maintenance
      Enables AI agents to look up official EYD Edisi Kelima spelling rules and check or correct Indonesian text for common errors such as nonstandard prepositions, particles, affixed forms, and punctuation through tool calls.
      43 npm
      10
      MIT
    • A
      license
      Not graded
      quality
      D
      maintenance
      Enables AI assistants and applications to access Dutch weather information, including current conditions, forecasts, alerts, historical data, and automatic resolution of Dutch location names to grid identifiers.
      Apache 2.0