# Text & Number Toolkit (remote · textkit.noahsarch.tech)

Amounts in words (Arabic cheque grammar), number formatting, Arabic text tools, date parsing.

- Trust score: 69/100 (medium)
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-11-04

## Components

- remote · `textkit.noahsarch.tech`: 69/100 (this document), [markdown](https://verifymcp.io/servers/tech-noahsarch-text-number-toolkit/textkit.md), [page](https://verifymcp.io/servers/tech-noahsarch-text-number-toolkit/textkit)

## Channel facts

- Endpoint: `https://textkit.noahsarch.tech/mcp`
- Transports: `streamable-http`
- Auth: `none`
- Version: `0.1.1`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically against the live server, and we only credit what we can confirm. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-11-04.

- **Endpoint Security**: 63/100
  - The endpoint's TLS certificate is valid, in date, and uses a strong key.
  - No authorisation is required to call this server. Every tool declares its destructiveHint and none is destructive, so open access doesn't expose one.
  - HTTPS enforcement could not be verified: the plaintext port answered with HTTP 406, which proves neither a plaintext path nor enforcement.
  - HSTS check failed: the Strict-Transport-Security header is absent.
  - DNSSEC check failed: this domain isn't protected by DNSSEC.
- **Transport & Reachability**: 100/100
  - Verified streamable-http transport via a live MCP handshake.
- **Schema Quality & AI Usability**: 77/100
  - 100% of prompts and resources have a non-trivial description (not blank, and not just the item's name).
  - AI-judged instruction clarity (good).
  - Context-footprint check failed: tool/resource definitions use about 2010 tokens (~167/item across 12 items; 10 tools + 2 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 13/100
  - Stability observed for 4 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 96/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 85% of tool parameters carry a description.
  - Structured output schemas are declared (100% of tools); any adoption earns full credit.
- **Tool Safety**: 100/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - We read all 10 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 12 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 100/100
  - Implements a current MCP spec version (2026-07-28).

## Install

### How do I install the Text & Number Toolkit MCP server?

Text & Number Toolkit is a hosted endpoint at https://textkit.noahsarch.tech/mcp, so there is nothing to install locally. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

### Claude

```bash
claude mcp add --transport http tech-noahsarch-text-number-toolkit 'https://textkit.noahsarch.tech/mcp'
```

### Cursor

```json
{
  "mcpServers": {
    "tech-noahsarch-text-number-toolkit": {
      "url": "https://textkit.noahsarch.tech/mcp"
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "tech-noahsarch-text-number-toolkit": {
      "type": "http",
      "url": "https://textkit.noahsarch.tech/mcp"
    }
  }
}
```

### Codex

```toml
[mcp_servers.tech-noahsarch-text-number-toolkit]
url = "https://textkit.noahsarch.tech/mcp"
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "tech-noahsarch-text-number-toolkit": {
      "type": "remote",
      "url": "https://textkit.noahsarch.tech/mcp",
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add tech-noahsarch-text-number-toolkit --url 'https://textkit.noahsarch.tech/mcp' --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  tech-noahsarch-text-number-toolkit:
    url: "https://textkit.noahsarch.tech/mcp"
```

### Netclaw

```json
{
  "McpServers": {
    "tech-noahsarch-text-number-toolkit": {
      "Transport": "http",
      "Url": "https://textkit.noahsarch.tech/mcp"
    }
  }
}
```

### Vellum

```bash
assistant mcp add tech-noahsarch-text-number-toolkit -t streamable-http -u 'https://textkit.noahsarch.tech/mcp'
```

### Other

```json
{
  "mcpServers": {
    "tech-noahsarch-text-number-toolkit": {
      "type": "http",
      "url": "https://textkit.noahsarch.tech/mcp"
    }
  }
}
```

The mcpServers block is a cross-client convention. Remote transports vary, so check your client's docs.

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-11-04 (score 69, +1)

No change was recorded against any check on this day. Stability & Change Management went from 10 to 13. That category is still filling its 30-day observation window: 3 days of observed history at the previous scan, 4 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-11-02 (score 68, +1)

No change was recorded against any check on this day. Stability & Change Management went from 3 to 7. That category is still filling its 30-day observation window: 1 days of observed history at the previous scan, 2 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-11-01 (score 67, 0)

- [functional improvement] Stability: unverified → 0.03

### 2026-10-31 (score 67)

First indexed and scored.

## MCP tools (10)

### `amount_to_words` (~258 tokens)

Write a money amount in words

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.

Input parameters:

- `amount` (required): Amount as number or numeric string, e.g. 1234567.89 or '١٢٣٤٫٥٠'.
- `currency` (string, required): ISO 4217 code: AED, SAR, USD, EUR…
- `language` (string): Language of the words: 'en', 'ar', 'fr', 'de', 'es', 'hi', 'ur'… (56 languages; list_languages).
- `style` (string): cheque wraps the phrase the way cheques/contracts do ('… only' / 'فقط … لا غير').

### `number_to_words` (~160 tokens)

Write a number in words

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.

Input parameters:

- `language` (string): Target language code (56 supported).
- `number` (required): Number (integers or decimals; Arabic-Indic digits accepted).
- `to` (string): cardinal (default) | ordinal (1st, الأول) | year (nineteen ninety-nine).

### `format_number` (~244 tokens)

Format a number for a locale

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.

Input parameters:

- `currency`: ISO 4217 code when style=currency.
- `decimals`: Force a number of decimal places; default = locale/currency rule.
- `locale` (string, required): CLDR locale: 'en', 'en_IN' (lakh grouping), 'ar_AE' (Arabic-Indic digits), 'de_DE', 'fr_CH'…
- `number` (required): Number to format.
- `numbering` (string): Digit system: locale default (ar_EG → Arabic-Indic, ar_AE → Western), or force latn / arab.
- `style` (string)

### `parse_number` (~172 tokens)

Read a human-written number

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.

Input parameters:

- `locale` (string): Locale whose separators to assume first; a heuristic fallback handles mismatches and says so.
- `text` (string, required): Number as written by a human: '1.234,56', '١٬٢٣٤٫٥٦', '12 345,6', '1,234.56'.

### `convert_digits` (~108 tokens)

Convert digit systems

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.

Input parameters:

- `text` (string, required)
- `to` (string, required): western 0-9 | arabic_indic ٠-٩ | persian ۰-۹.

### `normalize_arabic` (~265 tokens)

Normalise Arabic text

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.

Input parameters:

- `alef_maqsura_to_yaa` (boolean): ى → ي (search normalisation; changes spelling).
- `collapse_whitespace` (boolean)
- `digits_to_western` (boolean): ٠-٩/۰-۹ → 0-9.
- `punctuation_to_latin` (boolean): ، ؛ ؟ ٪ ٫ ٬ → , ; ? % . ,
- `strip_tashkeel` (boolean): Remove diacritics (fatha, damma, shadda…).
- `strip_tatweel` (boolean): Remove kashida/tatweel elongation.
- `taa_marbuta_to_haa` (boolean): ة → ه (search normalisation; changes spelling).
- `text` (string, required)
- `unify_alef` (boolean): آ أ إ ٱ → ا.

### `transliterate` (~132 tokens)

Romanise any script to ASCII

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.

Input parameters:

- `text` (string, required): Text in any script (Cyrillic, Greek, CJK, Arabic, Devanagari…).

### `detect_script` (~95 tokens)

Detect scripts, direction and digit systems

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.

Input parameters:

- `text` (string, required)

### `parse_date` (~323 tokens)

Parse a human-written date (200 locales + Hijri)

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.

Input parameters:

- `date_order`: Order for ambiguous numeric dates. Pass it whenever you know the source country.
- `languages`: Language codes to try, e.g. ['en','ar','fr']. Strongly recommended for speed and accuracy.
- `prefer_future` (boolean): Resolve ambiguous relative dates forward (deadlines) rather than backward.
- `relative_base`: ISO datetime that relative phrases ('tomorrow', 'in 3 days') count from. Default: now.
- `text` (string, required): A date as humans write it: '3 mars 2026', '12/11/2026', 'غداً', 'in 3 weeks', '15 رمضان 1447', '2026-11-12T10:00'.
- `timezone`: IANA zone for the result, e.g. 'Asia/Dubai'.

### `list_languages` (~55 tokens)

Supported languages and locales

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.

## Diagnostics

Captured diagnostic sections: TLS, DNSSEC, Authorisation, Transports. The full working is on the page: https://verifymcp.io/servers/tech-noahsarch-text-number-toolkit/textkit#diagnostics

## Score history

- 2026-11-04: 69
- 2026-11-03: 68
- 2026-11-02: 68
- 2026-11-01: 67
- 2026-10-31: 67

## Common questions

### What is the Text & Number Toolkit MCP server?

Text & Number Toolkit is an MCP server listed in the public MCP registry as tech.noahsarch/text-number-toolkit. Amounts in words (Arabic cheque grammar), number formatting, Arabic text tools, date parsing. This page covers its hosted endpoint (https://textkit.noahsarch.tech/mcp).

### Is the Text & Number Toolkit MCP server safe to use?

Text & Number Toolkit scores 69 out of 100 on VerifyMCP. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

### What tools does the Text & Number Toolkit MCP server expose?

Text & Number Toolkit exposes 10 tools: amount_to_words, number_to_words, format_number, parse_number, convert_digits, and 5 more. Their descriptions and schemas cost roughly 1,812 tokens of context every time the server is loaded.

### Does the Text & Number Toolkit MCP server require authentication?

No. We connected to Text & Number Toolkit without credentials and it answered, so anything it exposes is reachable by anyone who knows the address.

### Is the Text & Number Toolkit MCP server still maintained?

Text & Number Toolkit is still listed as active in the MCP registry. We last reached this channel on 4 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

## Links

- Remote endpoint: https://textkit.noahsarch.tech/mcp
- Website: https://agents.noahsarch.tech/
- Changelog RSS feed: https://verifymcp.io/servers/tech-noahsarch-text-number-toolkit/textkit.xml
- Changelog JSON feed: https://verifymcp.io/servers/tech-noahsarch-text-number-toolkit/textkit.json
- HTML version of this page: https://verifymcp.io/servers/tech-noahsarch-text-number-toolkit/textkit