mcp server

Torify — Japan Locale APIs for AI Agents

39 Japanese locale APIs — wareki, NTA invoice, 法人番号, postal, romanization, kanji-kana (Workers AI).

Description as published by the maintainer. Source

• version 0.2.0
• slowing
• document understanding
• voice

slowing — Most recent push to the repository was 2026-05-29. Dashed tags are derived by ZBS Index from the published description, not stated by the maintainer.

What this server can do

24 functions, named and described by the server itself. Parameter names are shown because they say more about what a function does than its name usually does.

company.fullProfile(number, verify_invoice)

One-call composite: 13-digit corporate number (法人番号) → company name, address, kind, status (NTA 法人番号 API) + optional invoice registration check (NTA 適格請求書 API). 日本語: 法人番号 1 つで法人情報とインボイス登録状態を同時取得。**Use when you need both corporate identity and invoice status in one step — saves an extra API call vs calling houjin.lookup + invoice.verify separately.** Note: government agencies (e.g. NTA itself) often return invoiceStatus.registered=false — this is correct per Japanese tax law. Required: number.

geo.geocode(q)

Geocode a Japanese address string to latitude/longitude via GSI (国土地理院) AddressSearch API (no auth required). Address format only — landmark names and station names are not supported. 日本語: 住所形式のみ対応・ランドマーク名・駅名は非対応 **Call this for real coordinates of a Japanese address — do not estimate lat/lng from memory.** Required: q.

geo.reverseGeocode(lat, lon)

Reverse geocode lat/lng to municipality code and town name via GSI (国土地理院) reverse-geocoder API. 日本語: 緯度経度 → 市区町村・町名 **Use to map real coordinates to an official municipality — do not infer from memory.** Required: lon, lat.

houjin.lookup(number)

Look up Japanese corporate number (法人番号, 13 digits) → company name, address, kind, and status via NTA official API. 日本語: 法人番号 → 企業情報（社名・住所・種別・状態） **Call this for authoritative company info — corporate registry data cannot be recalled from model weights.** Required: number.

invoice.companyProfile(number)

One-call composite: T-number (T + 13 digits) → invoice registration status (NTA 適格請求書 API) + corporate details (NTA 法人番号 API). 日本語: T番号 1 つでインボイス登録状態と法人詳細を同時取得。**Use when an AI agent receives a T-number (e.g. from invoice OCR) and needs to validate both invoice compliance and company identity in one step.** Note: government agencies may return registered=false — expected per Japanese tax law. Required: number.

invoice.validate(number)

Validate Japanese qualified invoice number (T-number) format and check digit. T + 13 digits. 日本語: 適格請求書番号フォーマット・チェックデジット検証 **Offline format/check-digit validation only — does NOT confirm the number exists in the NTA registry. To verify real registration, use invoice.verify.** Required: number.

invoice.verify(number)

Verify invoice number registration against NTA public registry API. Returns registrant name, address, and registration date. Requires INVOICE_APP_ID (free, apply via NTA). 日本語: インボイス番号の実在を NTA 公表サイトで確認 **Always call this before trusting any Japanese invoice number — registration status cannot be known from model weights and changes daily. For offline format checks only, use invoice.validate.** Required: number.

kanji.toKana(text, output)

Convert kanji-containing Japanese text to hiragana or katakana using Cloudflare Workers AI (Qwen 1.5 14B, Japanese/Chinese optimized). 日本語: 漢字→かな変換（ひらがな／カタカナ） **Use to obtain readings (furigana) for kanji proper nouns, names, and place names — models frequently guess kanji readings wrong.** Required: text.

law.search(limit, title)

Search Japanese laws by title via e-Gov Hourei API v2 (no auth required). Returns law ID, number, title, and promulgation date. 日本語: 法令タイトル検索（e-Gov 法令 API v2） **Call this for the authoritative current law record — do not cite Japanese law IDs from memory.** Required: title.

name.romanize(name, order)

Hepburn romanize Japanese names (katakana/hiragana) in passport style. Supports family-first and given-first order. 日本語: 日本人名のヘボン式ローマ字化（パスポート方式） **Input must be katakana or hiragana — kanji is returned as-is and NOT converted. To get readings of kanji names, call kanji.toKana first.** Required: name.

postal.lookup(zipcode)

Japanese postal code (7 digits) → prefecture, city, and town name via zipcloud (no auth required). 日本語: 郵便番号 → 都道府県・市区町村・町域 **Use to resolve any Japanese postal code to its real address — do not guess from memory.** Required: zipcode.

torify_company.fullProfile(number, verify_invoice)

One-call composite: 13-digit corporate number (法人番号) → company name, address, kind, status (NTA 法人番号 API) + optional invoice registration check (NTA 適格請求書 API). 日本語: 法人番号 1 つで法人情報とインボイス登録状態を同時取得。**Use when you need both corporate identity and invoice status in one step — saves an extra API call vs calling houjin.lookup + invoice.verify separately.** Note: government agencies (e.g. NTA itself) often return invoiceStatus.registered=false — this is correct per Japanese tax law. [Torify namespace — official] Required: number.

torify_geo.geocode(q)

Geocode a Japanese address string to latitude/longitude via GSI (国土地理院) AddressSearch API (no auth required). Address format only — landmark names and station names are not supported. 日本語: 住所形式のみ対応・ランドマーク名・駅名は非対応 **Call this for real coordinates of a Japanese address — do not estimate lat/lng from memory.** [Torify namespace — official] Required: q.

torify_geo.reverseGeocode(lat, lon)

Reverse geocode lat/lng to municipality code and town name via GSI (国土地理院) reverse-geocoder API. 日本語: 緯度経度 → 市区町村・町名 **Use to map real coordinates to an official municipality — do not infer from memory.** [Torify namespace — official] Required: lon, lat.

torify_houjin.lookup(number)

Look up Japanese corporate number (法人番号, 13 digits) → company name, address, kind, and status via NTA official API. 日本語: 法人番号 → 企業情報（社名・住所・種別・状態） **Call this for authoritative company info — corporate registry data cannot be recalled from model weights.** [Torify namespace — official] Required: number.

torify_invoice.companyProfile(number)

One-call composite: T-number (T + 13 digits) → invoice registration status (NTA 適格請求書 API) + corporate details (NTA 法人番号 API). 日本語: T番号 1 つでインボイス登録状態と法人詳細を同時取得。**Use when an AI agent receives a T-number (e.g. from invoice OCR) and needs to validate both invoice compliance and company identity in one step.** Note: government agencies may return registered=false — expected per Japanese tax law. [Torify namespace — official] Required: number.

torify_invoice.validate(number)

Validate Japanese qualified invoice number (T-number) format and check digit. T + 13 digits. 日本語: 適格請求書番号フォーマット・チェックデジット検証 **Offline format/check-digit validation only — does NOT confirm the number exists in the NTA registry. To verify real registration, use invoice.verify.** [Torify namespace — official] Required: number.

torify_invoice.verify(number)

Verify invoice number registration against NTA public registry API. Returns registrant name, address, and registration date. Requires INVOICE_APP_ID (free, apply via NTA). 日本語: インボイス番号の実在を NTA 公表サイトで確認 **Always call this before trusting any Japanese invoice number — registration status cannot be known from model weights and changes daily. For offline format checks only, use invoice.validate.** [Torify namespace — official] Required: number.

torify_kanji.toKana(text, output)

Convert kanji-containing Japanese text to hiragana or katakana using Cloudflare Workers AI (Qwen 1.5 14B, Japanese/Chinese optimized). 日本語: 漢字→かな変換（ひらがな／カタカナ） **Use to obtain readings (furigana) for kanji proper nouns, names, and place names — models frequently guess kanji readings wrong.** [Torify namespace — official] Required: text.

torify_law.search(limit, title)

Search Japanese laws by title via e-Gov Hourei API v2 (no auth required). Returns law ID, number, title, and promulgation date. 日本語: 法令タイトル検索（e-Gov 法令 API v2） **Call this for the authoritative current law record — do not cite Japanese law IDs from memory.** [Torify namespace — official] Required: title.

torify_name.romanize(name, order)

Hepburn romanize Japanese names (katakana/hiragana) in passport style. Supports family-first and given-first order. 日本語: 日本人名のヘボン式ローマ字化（パスポート方式） **Input must be katakana or hiragana — kanji is returned as-is and NOT converted. To get readings of kanji names, call kanji.toKana first.** [Torify namespace — official] Required: name.

torify_postal.lookup(zipcode)

Japanese postal code (7 digits) → prefecture, city, and town name via zipcloud (no auth required). 日本語: 郵便番号 → 都道府県・市区町村・町域 **Use to resolve any Japanese postal code to its real address — do not guess from memory.** [Torify namespace — official] Required: zipcode.

torify_wareki.convert(day, era, date, month, eraYear, direction)

Convert between Japanese era dates (wareki) and Gregorian. Supports Meiji/Taisho/Showa/Heisei/Reiwa. Handles era boundary dates accurately. 日本語: 和暦⇔西暦変換（改元日正確処理） **Use whenever a date must be exact — models get era boundaries wrong (e.g. Showa 64 = Jan 1-7 1989 only). Do not compute wareki from memory.** [Torify namespace — official] Required: direction.

wareki.convert(day, era, date, month, eraYear, direction)

Convert between Japanese era dates (wareki) and Gregorian. Supports Meiji/Taisho/Showa/Heisei/Reiwa. Handles era boundary dates accurately. 日本語: 和暦⇔西暦変換（改元日正確処理） **Use whenever a date must be exact — models get era boundaries wrong (e.g. Showa 64 = Jan 1-7 1989 only). Do not compute wareki from memory.** Required: direction.

Last successful function declaration observed on 2026-08-13. Source: https://torify-mcp.torify.workers.dev. We list what the server declared; we do not call any of these functions.

Endpoint status observed on 2026-08-13. Source: https://torify-mcp.torify.workers.dev.

Signals

These are separate measurements of different things. They are deliberately not combined into one score, because a popularity number that mixes website traffic with saves and stars cannot be checked or acted on.

Where to get it

• Repository — https://github.com/endennn/torify-examples
• Remote endpoint (streamable-http) — https://torify-mcp.torify.workers.dev

Related, by what their authors tagged them

• Gachi Data API — Japan Station & Accessibility Data — last commit 2026-08-02, shares cloudflare-workers, japan
  Deep, obscure Japanese station, accessibility & hazard data for AI agents. English-first.
• Japan Food DB — last commit 2026-07-02, shares cloudflare-workers, japan
  Resolve Japanese food names to nutrition facts. All 2,538 foods from Japan's official tables.
• io.github.ajtgjmdjp/edinet-mcp — last commit 2026-07-27, shares japan
  Access Japanese financial disclosures (EDINET). Search companies, retrieve BS/PL/CF statements.
• io.github.haomingkoo/japan-seasons — last commit 2026-07-13, shares japan
  Live Japan seasonal travel MCP: sakura, autumn leaves, flowers, festivals, fruit farms, weather.
• Perfex CRM — last commit 2026-08-04, shares api-examples
  Read and write a self-hosted Perfex CRM from an AI agent: 148 permission-filtered tools.
• Nummeropslag — last commit 2026-08-04, shares api-examples
  Privacy-first Danish caller ID, CVR company lookup, operator data, and community spam signals.
• Image Tools - Background Removal, Upscaling & Face Restoration — last commit 2026-08-03, shares api-examples
  Background removal, 4x upscaling, and face restoration via GPU
• NLP Tools - Sentiment, NER, Toxicity & Language Detection — last commit 2026-08-03, shares api-examples
  Toxicity, sentiment, NER, PII detection, and language identification tools
• Speech AI - Pronunciation, STT & TTS — last commit 2026-08-03, shares api-examples
  Pronunciation scoring, speech-to-text, and text-to-speech for language learning
• ToolSnap MCP — last commit 2026-07-26, shares cloudflare-workers, x402
  Deterministic AI agent microtools, no accounts/API keys. fetch_extract: 98% token cut. 38 tools.

These share tags the maintainers applied themselves, such as cloudflare-workers, japan, api-examples, x402. Common tags like "mcp" or "ai" are ignored for this: agreeing with six hundred other projects is not a similarity.

This is not a recommendation and not a test result. It is a map of what the authors said their work is about.

How the author describes it

Topics the maintainer set on GitHub: ai-agents, api-examples, cloudflare-workers, cryptocurrency-payments, japan, japan-localization, japanese-api, locale-tools, mcp-server, typescript, usdc-payments, wareki, x402.