Shirabe Japan Data Hub
Japan data tools for AI agents: calendar (rokuyo), address, name splitting, corporate number lookup
使うべきか
品質と安全性
ツール定義とプロトコルへの準拠に関する自動分析に基づいています。
コンテキストコスト
これは、サーバーのツールがモデルのコンテキストに読み込まれるたびに消費されるおおよそのトークン数です。数が多いほど、ほかのタスクに使える注意が減ります。
インストール
ワンクリックインストール
これを `claude_desktop_config.json` ファイルに追加してください:
{
"mcpServers": {
"hub": {
"url": "https://shirabe.dev/mcp"
}
}
}リモートエンドポイント
https://shirabe.dev/mcpstreamable-httpできること
ツール一覧
ツール(5)
🟢lookup_calendar(date, categories)
Look up Japanese calendar information for a given date: Rokuyo (six-day cycle such as Taian/Butsumetsu), Rekichu (almanac notes), Eto (sexagenary cycle), 24 solar terms, and purpose-based auspiciousness scores. Useful when an AI agent needs canonical Japanese calendar facts (e.g. choosing an auspicious date for a wedding or ceremony). Source: Shirabe Calendar API (shirabe.dev).
入力スキーマ
{
"type": "object",
"properties": {
"date": {
"type": "string",
"description": "Target date in YYYY-MM-DD (between 1873-01-01 and 2100-12-31)."
},
"categories": {
"type": "array",
"items": {
"type": "string"
},
"description": "Optional purpose categories to score (e.g. marriage, funeral, groundbreaking). Omit to return all available categories."
}
},
"required": [
"date"
],
"additionalProperties": false
}🟢normalize_japanese_address(address)
Normalize a free-form Japanese address against the official Address Base Registry (ABR, all 47 prefectures). Returns the canonical form, structured components (prefecture/city/town/block/building), postal code, WGS84 coordinates, match level (0-4) and confidence, plus mandatory CC BY 4.0 attribution. Useful when an AI agent must clean or de-duplicate Japanese B2B/customer records. Source: Shirabe Address API.
入力スキーマ
{
"type": "object",
"properties": {
"address": {
"type": "string",
"description": "A raw Japanese address string (may include postal code, building, floor)."
}
},
"required": [
"address"
],
"additionalProperties": false
}🟢split_japanese_name(name)
Split a Japanese personal name into family and given parts using IPAdic person-name POS tags (with whitespace/length heuristics as fallback). Returns family, given, and a confidence score (0-1; warning when low). Useful for normalizing name fields in HR, CRM, or form data. Source: Shirabe Text API.
入力スキーマ
{
"type": "object",
"properties": {
"name": {
"type": "string",
"description": "A Japanese personal name, e.g. 山田良介."
}
},
"required": [
"name"
],
"additionalProperties": false
}🟢corporation_lookup(law_id)
Look up a Japanese company by its 13-digit corporate number (法人番号) against the National Tax Agency (NTA) corporate-number registry. Returns the registered trade name, head-office address, change history and other public fields as JSON, plus mandatory NTA attribution. Useful when an AI agent already has a corporate number and needs canonical company facts (e.g. validating or enriching a B2B record). To go the other way (company name → number), use corporation_search. Source: Shirabe Corporation API.
入力スキーマ
{
"type": "object",
"properties": {
"law_id": {
"type": "string",
"description": "A 13-digit Japanese corporate number (法人番号), e.g. 1234567890123."
}
},
"required": [
"law_id"
],
"additionalProperties": false
}🟢corporation_search(name)
Search the Japanese corporate-number registry (National Tax Agency) by company name and return matching companies, each with its 13-digit corporate number (法人番号), registered name and address, plus mandatory NTA attribution. Handles trade-name variants (㈱ / (株) / 株式会社) via normalization. Useful when an AI agent has a company name and needs to resolve its corporate number / canonical record. To go the other way (number → company), use corporation_lookup. Source: Shirabe Corporation API.
入力スキーマ
{
"type": "object",
"properties": {
"name": {
"type": "string",
"description": "A Japanese company name, e.g. 株式会社テックウェル (variants like ㈱テックウェル are accepted)."
}
},
"required": [
"name"
],
"additionalProperties": false
}コミュニティ
エビデンス