Text & Number Toolkit
Server Details
Amounts in words (Arabic cheque grammar), number formatting, Arabic text tools, date parsing.
- Status
- Healthy
- Uptime
- 100.0% over the last 24 hours
- Last Tested
- Transport
- Streamable HTTP · MCP 2025-11-25
- URL
- ChatGPT
- –
- Claude
- –
TDQS
Scored across 10 tools
Most tools target a distinct operation: parse_number vs format_number vs number_to_words vs amount_to_words are separable by input/output direction and currency scope. A couple of boundaries are soft — convert_digits also rewrites digits to Western form, which normalize_arabic does as one of its rules, and amount_to_words/number_to_words could be confused at a glance. Descriptions do enough work to resolve these.
All snake_case and predominantly verb-first (convert_digits, detect_script, format_number, parse_date, normalize_arabic), which makes the set predictable. Minor deviations: amount_to_words and number_to_words use noun_to_noun form, and transliterate is a bare verb. Still readable and non-chaotic.
Ten tools is well within the sweet spot for a multilingual text/number utility server. Each tool maps to a distinct primitive (parse, format, verbalize, normalize, convert, detect) with no filler entries.
Core numeric lifecycle is covered: parse_number, format_number, number_to_words, amount_to_words, plus digit/script/normalization/transliteration and date parsing. Gaps: no reverse direction for words-to-number or words-to-amount, and dates can be parsed but not rendered back into a locale format. These are workable around but real.
Available Tools
10 toolsamount_to_wordsWrite a money amount in wordsARead-onlyIdempotentInspect
Convert an amount in a currency to words for cheques, invoices and contracts, in 56 languages. Arabic output applies number–noun agreement (درهم واحد / درهمان / ثلاثة دراهم / أحد عشر درهماً) and the correct minor unit (فلس، هللة، قرش…); English uses CLDR currency names. style='cheque' adds the customary wrapper. Example: amount 1250.50, currency 'AED', language 'ar', style 'cheque'. Response: result plus data_confidence, estimated_items[], sources[], data_version, warnings[]; deterministic (no AI inside), nothing logged.
Inputs: amount (required), currency (required), style, language. Returns: object
convert_digitsConvert digit systemsARead-onlyIdempotentInspect
Rewrite digits between Western (0-9), Arabic-Indic (٠-٩) and Persian/Urdu (۰-۹) anywhere in a text, leaving everything else untouched. Response: result plus data_confidence, estimated_items[], sources[], data_version, warnings[]; deterministic (no AI inside), nothing logged.
Inputs: to (required), text (required). Returns: object
detect_scriptDetect scripts, direction and digit systemsARead-onlyIdempotentInspect
Proportions of writing systems in a text (latin, arabic, cyrillic, han…), dominant script, RTL/LTR direction, mixed-script flag, which digit systems appear, and hints such as Persian/Urdu-specific letters. Free. Response: result plus data_confidence, estimated_items[], sources[], data_version, warnings[]; deterministic (no AI inside), nothing logged.
Inputs: text (required). Returns: object
format_numberFormat a number for a localeARead-onlyIdempotentInspect
Locale-correct display of a decimal, currency amount or percentage using CLDR rules: grouping (1,234,567 / 12,34,567 / 1.234.567 / 1 234 567), decimal mark, currency symbol placement, Arabic-Indic digits for ar_* locales. Example: number 1234567.891, locale 'en_IN', style 'currency', currency 'INR'. Response: result plus data_confidence, estimated_items[], sources[], data_version, warnings[]; deterministic (no AI inside), nothing logged.
Inputs: locale (required), number (required), style, currency, +2 more. Returns: object
list_languagesSupported languages and localesBRead-onlyIdempotentInspect
Languages available for words, the curated Arabic-grammar currencies, and notes on locales. Free. Response: result plus data_confidence, estimated_items[], sources[], data_version, warnings[]; deterministic (no AI inside), nothing logged.
Inputs: no named parameters. Returns: object
normalize_arabicNormalise Arabic textARead-onlyIdempotentInspect
Clean Arabic text for matching, search and storage: strip diacritics and tatweel, unify alef forms, optional ة→ه and ى→ي, Western digits, Latin punctuation, whitespace. Reports exactly which rules changed the text. Response: result plus data_confidence, estimated_items[], sources[], data_version, warnings[]; deterministic (no AI inside), nothing logged.
Inputs: text (required), unify_alef, strip_tatweel, strip_tashkeel, +5 more. Returns: object
number_to_wordsWrite a number in wordsARead-onlyIdempotentInspect
Cardinal, ordinal or year wording of a number in 56 languages (en, ar, fr, de, es, pt, it, nl, tr, ru, hi, ur, id, ja, ko…). Example: number 2026, language 'en', to 'year' → 'twenty twenty-six'. Response: result plus data_confidence, estimated_items[], sources[], data_version, warnings[]; deterministic (no AI inside), nothing logged.
Inputs: number (required), to, language. Returns: object
parse_dateParse a human-written date (200 locales + Hijri)ARead-onlyIdempotentInspect
Turn a date written in natural language or local numeric formats into an ISO date/datetime: '3 mars 2026', '12.11.2026', 'next month', 'غداً', 'in 3 weeks', and Hijri dates such as '15 رمضان 1447' or '1 Muharram 1448' (converted by Umm al-Qura). Returns precision (day/month/year/time), the detected language and the relative base used. Pass languages and date_order when known. Example: text '١٥ رمضان ١٤٤٧'. Response: result plus data_confidence, estimated_items[], sources[], data_version, warnings[]; deterministic (no AI inside), nothing logged.
Inputs: text (required), timezone, languages, date_order, +2 more. Returns: object
parse_numberRead a human-written numberARead-onlyIdempotentInspect
Turn '1.234,56', '١٬٢٣٤٫٥٦', '12 345,6' or '1,234.56' into an exact decimal, using the locale's separators first and a clearly flagged heuristic when they do not match. Example: text '1.234,56', locale 'de'. Response: result plus data_confidence, estimated_items[], sources[], data_version, warnings[]; deterministic (no AI inside), nothing logged.
Inputs: text (required), locale. Returns: object
transliterateRomanise any script to ASCIIARead-onlyIdempotentInspect
Deterministic romanisation of any script to plain ASCII (Cyrillic, Greek, CJK, Devanagari, Thai, Arabic…) for slugs, sorting, matching and systems that reject non-ASCII. Not an official spelling: for Arabic names the result is a consonant skeleton and is flagged low confidence. Response: result plus data_confidence, estimated_items[], sources[], data_version, warnings[]; deterministic (no AI inside), nothing logged.
Inputs: text (required). Returns: object
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Related MCP Connectors
Arabic PDF tables to JSON, domain availability (RDAP), CWV verdicts, free OpenAI shutdown scanner.
OCR, editable Word, tables, translation and data extraction for Arabic-script documents
Persian and Iranian utilities for agents plus text tooling. Paid via x402 or MPP.
Arabic-first OCR, translation and document extraction. First call mints a free trial key.
Related MCP Servers
- AlicenseAqualityCmaintenanceMCP server for correct Arabic formatting — currency, Hijri dates, number-to-words, RTL fixes and validation across all 22 Arab countries. Zero-dependency.17141 npm3MIT
- AlicenseAqualityDmaintenanceMCP server exposing Arabic text utilities: normalisation, tashkeel stripping, transliteration, heuristic dialect detection, and token counting.5MIT
- AlicenseAqualityBmaintenanceEnables Claude to deterministically normalize Pakistani phone numbers, convert between Latin and Urdu digit scripts, compute Hijri dates, and format rupee amounts in lakh/crore notation with Urdu word forms. All helpers run locally with no network access or stored data.5MIT
- AlicenseBqualityCmaintenanceEnables dependable Arabic text normalization and search preparation for RAG and deduplication, with typed outputs, stable fingerprints, and experimental dialect, sentiment, and diacritization tools.2MIT
Glama MCP Gateway
Add one secure layer between your agents and this server.