行政書士 許認可 eligibility pack (A3)

建設業・産廃・宅建・運送・古物・飲食 等の許認可 eligibility を業種 × 都道府県 × 市町村 × 法人格 fence + 排他/併用ルール 1 packet。申請書面作成は scaffold + 一次 URL only。

誰のためか

行政書士 (Administrative-Scrivener) コホート. 月次 200 req 想定 (¥3/req)。

1 query で返るもの (package_kind)

evidence_packet, watch_digest

呼び出される heavy / composed endpoint

• POST /v1/programs/full_context
• GET /v1/laws/{law_id}/related_programs
• POST /v1/exclusions/check
• POST /v1/jpcite/route
• POST /v1/evidence/packets/query

SDK example — Python (jpcite-mcp / autonomath-mcp PyPI)

# A3 Administrative-Scrivener Licensing Eligibility Pack — Python (jpcite-mcp)
import os
import httpx

JPCITE_API = "https://api.jpcite.com"
API_KEY = os.environ["JPCITE_API_KEY"]  # see https://jpcite.com/dashboard

def fetch_gyoseishoshi_packet(houjin_bangou: str) -> dict:
    # 1. Free preflight — no charge until accepted_artifact delivery.
    preview = httpx.post(
        f"{JPCITE_API}/v1/jpcite/preview_cost",
        headers={"X-API-Key": API_KEY, "X-Client-Tag": "gyoseishoshi-001"},
        json={"outcome_contract_id": "A3_gyosei_licensing_eligibility_pack",
               "input": {"houjin_bangou": houjin_bangou}}
    ).raise_for_status().json()
    assert preview["cap_passed"], "outcome exceeds cap — adjust max_price_jpy"

    # 2. Execute packet — charges 60 billable units (=¥60).
    packet = httpx.post(
        f"{JPCITE_API}/v1/jpcite/execute_packet",
        headers={"X-API-Key": API_KEY,
                  "X-Client-Tag": "gyoseishoshi-001",
                  "X-Jpcite-Scoped-Cap-Token": preview["scoped_cap_token"],
                  "Idempotency-Key": f"gyoseishoshi-{houjin_bangou}-2026-05"},
        json={"outcome_contract_id": "A3_gyosei_licensing_eligibility_pack",
               "input": {"houjin_bangou": houjin_bangou},
               "max_price_jpy": 2000}
    ).raise_for_status().json()
    return packet  # contains source_url[], fetched_at, known_gaps[], evidence[]

SDK example — TypeScript (Bedrock MCP / OpenAI tool-use)

// A3 Administrative-Scrivener Licensing Eligibility Pack — TypeScript (Bedrock / OpenAI tool-use)
import { JpciteClient } from "@jpcite/sdk";  // wraps OpenAPI 219 paths

const client = new JpciteClient({
  baseUrl: "https://api.jpcite.com",
  apiKey: process.env.JPCITE_API_KEY!,
  clientTag: "gyoseishoshi-001",  // 顧問先 fan-out attribution
});

export async function fetchAdministrativeScrivenerPacket(houjinBangou: string) {
  const preview = await client.previewCost({
    outcome_contract_id: "A3_gyosei_licensing_eligibility_pack",
    input: { houjin_bangou: houjinBangou },
  });
  if (!preview.cap_passed) throw new Error("over cap");

  const packet = await client.executePacket({
    outcome_contract_id: "A3_gyosei_licensing_eligibility_pack",
    input: { houjin_bangou: houjinBangou },
    max_price_jpy: 2000,
    scopedCapToken: preview.scoped_cap_token,
    idempotencyKey: `gyoseishoshi-${houjinBangou}-2026-05`,
  });
  return packet;  // { source_url[], fetched_at, known_gaps[], evidence[] }
}

Claude Code .mcp.json snippet

{
  "mcpServers": {
    "jpcite": {
      "command": "npx",
      "args": [
        "-y",
        "autonomath-mcp"
      ],
      "env": {
        "JPCITE_API_KEY": "${env:JPCITE_API_KEY}",
        "JPCITE_DEFAULT_OUTCOME": "A3_gyosei_licensing_eligibility_pack",
        "JPCITE_CLIENT_TAG": "gyoseishoshi-001"
      }
    }
  }
}

jpcite ¥600 / 月 vs LLM API replacement

cheapest LLM tier (Haiku 4.5) でも jpcite の 0.5x コスト。 さらに LLM 単独は出典 URL を hallucinate するため、 一次資料 URL + fetched_at + known_gaps は jpcite でしか得られない。

コホート 別コスト比較表を見る →

1 call ≈ 人手 ¥2,000 相当

30-90 分の一次資料調査 + 名寄せ + 出典確認を 1 query で代替。 代替時給 ¥3,000 換算で 1 packet ≒ ¥2,000。 jpcite ¥3 / packet との差分が ROI。

使い始める

1. /dashboard で API キー発行 (匿名 3 req/日無料)
2. Python: pip install autonomath-mcp
3. Claude Code: .mcp.json 上記 snippet を貼り付け
4. getting-started 経由で 1 packet を取得

関連リソース

• API reference (219 path)
• MCP tools (146 default-gate)
• cookbook (15 recipes)
• 行政書士 向け コホート landing
• outcome catalog (450 outcome)