# jpcite MCP Tools Index This file lists every publicly published MCP tool exposed by jpcite. Protocol: MCP 2025-06-18. Transport: stdio. Package: autonomath-mcp. HTTP-only clients should use the REST/OpenAPI surface instead. Canonical MCP entry: https://jpcite.com/mcp-server.json Full MCP manifest: https://jpcite.com/mcp-server.full.json Total tools: 261 ## Tools - [search_programs](https://jpcite.com/docs/mcp-tools/#search_programs): INGREDIENT: returns ingredient (foundation data), client agent applies finishing. Usage model: foundation data; client agent finishes ~500 token (¥5-¥15) before showing to end user. Do not surface... - [get_program](https://jpcite.com/docs/mcp-tools/#get_program): INGREDIENT: returns ingredient (foundation data for 1 program), client agent applies finishing. Usage model: foundation data; client agent finishes ~500 token (¥5-¥15) before showing to end user. D... - [batch_get_programs](https://jpcite.com/docs/mcp-tools/#batch_get_programs): INGREDIENT: returns ingredient (foundation data for ≤50 programs), client agent applies finishing. Usage model: foundation data; client agent finishes ~500 token (¥5-¥15) before showing to end user... - [list_exclusion_rules](https://jpcite.com/docs/mcp-tools/#list_exclusion_rules): COMPLIANCE: 補助金の併給禁止 / 前提要件ルールを列挙する (list 181 subsidy exclusion + prerequisite rules across public-program domains). Use this when the user wants to browse combination restrictions, prerequisite ce... - [check_exclusions](https://jpcite.com/docs/mcp-tools/#check_exclusions): COMPLIANCE: 併給可否を機械的に判定する — 候補制度セットに対して 181 本の併給禁止 / 前提要件ルールを走らせ、違反するものだけ返す (given a candidate set of program IDs, run all 181 補助金 exclusion / prerequisite rules and return only the violations). Th... - [get_meta](https://jpcite.com/docs/mcp-tools/#get_meta): UTILITY: データの鮮度・網羅件数を確認する (verify dataset freshness and scope). Returns public-searchable program count, canonical vs external-source split, 採択事例 / 融資 / 行政処分 / rule counts, tier distribution (S/A/B... - [get_usage_status](https://jpcite.com/docs/mcp-tools/#get_usage_status): META: 現在のクォータ残量を確認する (probe current API quota state without consuming a slot). - [enum_values](https://jpcite.com/docs/mcp-tools/#enum_values): INGREDIENT: returns ingredient (valid enum vocabulary), client agent applies finishing by selecting + relaying canonical value. Do not surface raw JSON. UTILITY: 他ツールのフィルタ値を先に検証する (probe which filt... - [search_enforcement_cases](https://jpcite.com/docs/mcp-tools/#search_enforcement_cases): INGREDIENT: returns ingredient (foundation data for compliance audit), client agent applies finishing. Usage model: foundation data; client agent finishes ~500 token (¥5-¥15), translates to risk br... - [get_enforcement_case](https://jpcite.com/docs/mcp-tools/#get_enforcement_case): DETAIL: 会計検査院 不正・不当請求事例 1 件の詳細を取得する (fetch one enforcement case). Returns full record: event_type, ministry, recipient (name + 法人番号 + kind), bureau, prefecture, occurred_fiscal_years, all amount_*... - [search_case_studies](https://jpcite.com/docs/mcp-tools/#search_case_studies): INGREDIENT: returns ingredient (recipient evidence foundation data), client agent applies finishing. Usage model: foundation data; client agent finishes ~500 token (¥5-¥15), translates to recipient... - [get_case_study](https://jpcite.com/docs/mcp-tools/#get_case_study): DETAIL: 採択事例 1 件の収録済みフィールドの詳細を取得する (fetch one case study). Returns recipient profile (company_name, 法人番号, prefecture, industry_jsic, employees, founded_year, capital_yen), case_title / case_summary... - [search_loan_programs](https://jpcite.com/docs/mcp-tools/#search_loan_programs): INGREDIENT: returns ingredient (foundation data for loan decomposition), client agent applies finishing. Usage model: foundation data; client agent finishes ~500 token (¥5-¥15), translates to lendi... - [get_loan_program](https://jpcite.com/docs/mcp-tools/#get_loan_program): DETAIL: 融資プログラム 1 件の詳細を取得する (fetch one 融資 program by numeric id). Returns full record including three-axis lending-condition (担保 / 個人保証人 / 第三者保証人), interest rates (base + special), loan period, gra... - [prescreen_programs](https://jpcite.com/docs/mcp-tools/#prescreen_programs): DISCOVER-JUDGE: profile → ranked eligible programs (fit-based discovery, NOT keyword search). - [smb_starter_pack](https://jpcite.com/docs/mcp-tools/#smb_starter_pack): ONE-SHOT DISCOVERY: 1 call で SMB 経営者が「今日何できる?」を返す。 - [upcoming_deadlines](https://jpcite.com/docs/mcp-tools/#upcoming_deadlines): DISCOVER-CALENDAR: list 補助金 / 助成金 / 融資 / 税制 programs whose application deadline (application_window.end_date) falls within the next N days. - [deadline_calendar](https://jpcite.com/docs/mcp-tools/#deadline_calendar): ONE-SHOT CALENDAR: 今後 N ヶ月 (1..6) の締切を月別グルーピングで 1 call。 - [subsidy_combo_finder](https://jpcite.com/docs/mcp-tools/#subsidy_combo_finder): ONE-SHOT COMBO: 補助金+融資+税制 の 非衝突組合せ TOP N を 1 call で。 - [dd_profile_am](https://jpcite.com/docs/mcp-tools/#dd_profile_am): ONE-SHOT DD: 法人番号 → 公表コンプライアンス + 採択実績 + インボイス登録 を 1 call. - [similar_cases](https://jpcite.com/docs/mcp-tools/#similar_cases): CASE-STUDY-LED DISCOVERY: 採択事例 を seed に「似た事例 + その制度」を返す。 - [subsidy_roadmap_3yr](https://jpcite.com/docs/mcp-tools/#subsidy_roadmap_3yr): ONE-SHOT 3-YEAR ROADMAP: industry × prefecture × size × purpose で - [search_laws](https://jpcite.com/docs/mcp-tools/#search_laws): INGREDIENT: returns ingredient (foundation legal corpus data), client agent applies finishing. Usage model: foundation data; client agent finishes ~500 token (¥5-¥15), translates to legal brief, ci... - [get_law](https://jpcite.com/docs/mcp-tools/#get_law): INGREDIENT: returns ingredient (foundation legal record), client agent applies finishing. Usage model: foundation data; client agent finishes ~500 token (¥5-¥15) before showing to end user. Do not... - [list_law_revisions](https://jpcite.com/docs/mcp-tools/#list_law_revisions): LINEAGE-LAW: trace the revision chain for a 法令 — walks `superseded_by_law_id` forward and backward to reconstruct (predecessors → this → successors → current). Essential for diachronic legal analys... - [search_court_decisions](https://jpcite.com/docs/mcp-tools/#search_court_decisions): INGREDIENT: returns ingredient (foundation court-decision data), client agent applies finishing. Usage model: foundation data; client agent finishes ~500 token (¥5-¥15), translates to case-law brie... - [get_court_decision](https://jpcite.com/docs/mcp-tools/#get_court_decision): DETAIL-CASE: fetch a single 判例 with full source lineage (courts.go.jp primary). Returns case_name, court, decision_date, key_ruling, impact_on_business, related_law_ids, precedent_weight, source_ur... - [find_precedents_by_statute](https://jpcite.com/docs/mcp-tools/#find_precedents_by_statute): TRACE-STATUTE: given a LAW-<10 hex> unified_id, return 判例 citing that statute via related_law_ids_json. Ordered by precedent_weight → court_level → decision_date. When `article_citation` is set, we... - [search_bids](https://jpcite.com/docs/mcp-tools/#search_bids): INGREDIENT: returns ingredient (foundation procurement-notice data), client agent applies finishing. Usage model: foundation data; client agent finishes ~500 token (¥5-¥15), translates to bid-brief... - [get_bid](https://jpcite.com/docs/mcp-tools/#get_bid): DETAIL-BID: fetch a single 入札案件 (procurement notice / 落札結果). Returns bid_title, bid_kind, procuring_entity + houjin_bangou, ministry, prefecture, program_id_hint, all deadline + amount + winner fie... - [bid_eligible_for_profile](https://jpcite.com/docs/mcp-tools/#bid_eligible_for_profile): SCREEN-BID: compare a business profile against bid.eligibility_conditions. Honest substring scan — not a structured eligibility engine. Returns `possibly_eligible` (bool, True unless a hard mismatc... - [search_tax_rules](https://jpcite.com/docs/mcp-tools/#search_tax_rules): DISCOVER-TAX: search 税務判定ルールセット (国税庁 タックスアンサー + 電帳法一問一答 + インボイス Q&A). Each row pairs narrative `eligibility_conditions` with a machine-readable predicate tree for `evaluate_tax_applicability`. - [get_tax_rule](https://jpcite.com/docs/mcp-tools/#get_tax_rule): DETAIL-TAX: fetch a single 税務判定ルールセット by TAX-<10 hex>. Returns ruleset_name, tax_category, ruleset_kind, effective_from / effective_until (watch cliff dates), related_law_ids, narrative eligibility... - [evaluate_tax_applicability](https://jpcite.com/docs/mcp-tools/#evaluate_tax_applicability): JUDGE-TAX: evaluate eligibility predicates for tax rulesets against a caller business_profile. Walks `eligibility_conditions_json` per row and returns per-ruleset `applicable` + reasons + matched /... - [compose_audit_workpaper](https://jpcite.com/docs/mcp-tools/#compose_audit_workpaper): [KAIKEI] 監査ワークペーパー (PDF/CSV/MD/DOCX) を 1 件の client + ruleset セットに対して生成する。corpus_snapshot_id + sha256 + §47条の2 wording を全 surface に埋め込む。WeasyPrint レンダ → published artifact/ に stored result、再 pull は無... - [audit_batch_evaluate](https://jpcite.com/docs/mcp-tools/#audit_batch_evaluate): [KAIKEI] Batch evaluation across an audit firm's client population. ¥3 × N profiles billing (K=10 fan-out → 5,000×100=50,000 units / ¥150,000). Returns per-profile results + anomalies (population-d... - [resolve_citation_chain](https://jpcite.com/docs/mcp-tools/#resolve_citation_chain): [KAIKEI] tax_ruleset → 法令 article → 通達 → 質疑応答 → 文書回答 の citation chain を auto-resolve する。国税庁・法令・判例の公表情報をつなぎ、監査調書の索引に貼りやすい tree を返す。¥3/billable unit。§47条の2 + §52 sensitive — 税務助言ではなく出典確認用。 - [search_invoice_registrants](https://jpcite.com/docs/mcp-tools/#search_invoice_registrants): INGREDIENT: returns ingredient (foundation invoice-registrant data), client agent applies finishing. Usage model: foundation data; client agent finishes ~500 token (¥5-¥15), translates to registran... - [trace_program_to_law](https://jpcite.com/docs/mcp-tools/#trace_program_to_law): TRACE-PROGRAM-LAW: given a program unified_id, return its 根拠法 / 関連法 chain — joins `source-derived dataset` → `laws`. Each entry reports ref_kind (authority / eligibility / exclusion / reference / p... - [find_cases_by_law](https://jpcite.com/docs/mcp-tools/#find_cases_by_law): TRACE-LAW-CASES: given a LAW-<10 hex>, return (court_decisions citing it) + optionally (source-derived dataset linked to those decisions via enforcement_decision_refs). Essential for "which rulings... - [combined_compliance_check](https://jpcite.com/docs/mcp-tools/#combined_compliance_check): OMNIBUS-COMPLIANCE: one-shot compliance report combining (a) source-derived dataset check for the named program, (b) tax_rulesets evaluation against business_profile, (c) top-N relevant bids (filte... - [regulatory_prep_pack](https://jpcite.com/docs/mcp-tools/#regulatory_prep_pack): ONE-SHOT DISCOVERY: 業種 + 都道府県 (+ 規模) で「コンプラ pack」を 1 call で。 - [list_active_disaster_programs](https://jpcite.com/docs/mcp-tools/#list_active_disaster_programs): DISASTER: 過去 12 ヶ月の災害復興・特例制度を 1 コールで surface する (list disaster-recovery programs surfaced in the rolling N-month window). Use as the 発災後 immediate-surface entry point — a 都道府県 LP team can call it w... - [match_disaster_programs](https://jpcite.com/docs/mcp-tools/#match_disaster_programs): DISASTER: 発災後 prefecture+災害種別+日付 から該当制度を一括返却 (match every applicable subsidy / loan / tax特例 for a given disaster instance). Returns buckets keyed on program_kind, tier-sorted (S→A→B→C). Use this wh... - [disaster_catalog](https://jpcite.com/docs/mcp-tools/#disaster_catalog): DISASTER: 過去 N 年の災害指定 history を programs.primary_name から再構成 (walk programs.primary_name for 「令和N年…豪雨」 / 「令和N年…地震」 patterns and surface one event row per detected disaster). Useful for retrospective... - [search_tax_incentives](https://jpcite.com/docs/mcp-tools/#search_tax_incentives): DISCOVER (Tax): Search 50 Japanese tax rulesets — corporate deductions (減価償却/試験研究費), tax credits (雇用/エネルギー/DX), special measures (租税特別措置). - [search_certifications](https://jpcite.com/docs/mcp-tools/#search_certifications): DISCOVER (Certifications): Search 66 Japanese certification programs (経営革新等支援機関認定 / 経営力向上計画 / 中小企業等経営強化法 etc.). - [list_open_programs](https://jpcite.com/docs/mcp-tools/#list_open_programs): [TIMELINE] Returns programs whose application window covers the given date (default=今日 JST), sorted by days-until-close ascending. Output is search-derived; verify primary source (source_url) for t... - [enum_values_am](https://jpcite.com/docs/mcp-tools/#enum_values_am): [UTILITY] Returns the canonical enum values + source coverage for filter arguments used by other tools (target_type / authority_level / funding_purpose / prefecture / program_kind 等), so callers ca... - [search_by_law](https://jpcite.com/docs/mcp-tools/#search_by_law): [DISCOVER-LAW] Returns programs / tax_measures / certifications / law rows linked to a given law name (canonical or colloquial). Uses source-derived dataset + source-derived dataset.short_name` for... - [active_programs_at](https://jpcite.com/docs/mcp-tools/#active_programs_at): [TIMELINE] 任意の ISO 日付 pivot で **effective window (施行〜廃止) が及ぶ** 制度 + 税制を列挙する — `list_open_programs` が 募集窓口 を、本 tool は 制度の **存在期間** を見る (歴史的 "XX年時点で有効だった制度" の効力期間 lookup 用途). - [search_acceptance_stats_am](https://jpcite.com/docs/mcp-tools/#search_acceptance_stats_am): [EVIDENCE] Returns adoption statistics (応募件数 / 採択件数 / 採択率 / 予算額) per (program × fiscal_year × round). Aggregated from METI / MAFF published sources. Output is search-derived; verify primary source... - [related_programs](https://jpcite.com/docs/mcp-tools/#related_programs): [DISCOVER-GRAPH] Returns related programs along 6 relation axes (prerequisite / compatible / incompatible / successor / predecessor / similar), 1-2 hops from a seed program / tax / cert. Walks sour... - [get_annotations](https://jpcite.com/docs/mcp-tools/#get_annotations): [ANNOTATION] Return public annotation rows for a given entity_id. - [check_answer_freshness](https://jpcite.com/docs/mcp-tools/#check_answer_freshness): [P4 FRESHNESS] Verify whether a precomputed answer is still fresh against the latest law / 税制 / 制度 amendment sweep. Pure metadata lookup. NO LLM. Returns freshness_state ('fresh' / 'stale' / 'expir... - [compose_audit_workpaper_v2](https://jpcite.com/docs/mcp-tools/#compose_audit_workpaper_v2): Roll up intel_houjin_full + apply_eligibility_chain + cross_check_jurisdiction + amendment_alert for one 法人 in one FY into a 税理士/会計士 audit workpaper. ¥15 / call (5 units). NO LLM, deterministic ret... - [search_gx_programs_am](https://jpcite.com/docs/mcp-tools/#search_gx_programs_am): DISCOVER (GX/Green): Search Green Transformation subsidies — emissions reduction, renewable energy, EV adoption, ZEB/ZEH (net-zero buildings), carbon credits. Returns curated programs with eligibil... - [search_loans_am](https://jpcite.com/docs/mcp-tools/#search_loans_am): [DISCOVER-LOAN] Returns matching loan products from source-derived dataset, filtered by 3 independent axes (担保 / 個人保証 / 第三者保証). Spans 公庫 / 自治体制度融資 / 商工中金. Output is search-derived; verify primary s... - [check_enforcement_am](https://jpcite.com/docs/mcp-tools/#check_enforcement_am): [ENFORCEMENT] Returns 行政処分 records from source-derived dataset for a 法人番号 or 企業名, including currently_excluded flag (active 排除期間 at as_of_date) and 5-year history. Coverage is the 22,258-row source... - [search_mutual_plans_am](https://jpcite.com/docs/mcp-tools/#search_mutual_plans_am): [DISCOVER-MUTUAL] Returns matching 共済 / 年金 / 労災 records (小規模企業共済 / 倒産防止共済 / iDeCo+ / public index / DC / 労災特別加入 等) from source-derived dataset, filtered by plan_kind × premium range × tax_deduction... - [get_law_article_am](https://jpcite.com/docs/mcp-tools/#get_law_article_am): [LAW-ARTICLE] Returns the article text from source-derived dataset for a (law name, article number) pair. Accepts natural notation like '租税特別措置法 第41条の19' and normalizes to canonical form. Includes... - [benchmark_cohort_average_am](https://jpcite.com/docs/mcp-tools/#benchmark_cohort_average_am): [BENCHMARK] 業種 (JSIC) × 規模 × 地域 平均採択額 / 採択件数 / hit数 (制度数) / outlier 法人 (top 10%) over source-derived dataset + source-derived dataset. Single ¥3/billable unit. NO LLM. §52 / §47条の2 / §1 sensitive —... - [predictive_subscriber_fanout_chain](https://jpcite.com/docs/mcp-tools/#predictive_subscriber_fanout_chain): [AUDIT, SENSITIVE — §52/§47条の2/§72/§1] release chain B — predictive_subscriber_fanout (dim K). Registers the supplied Subscription, enqueues the supplied PredictionEvent, then runs due_events_for_s... - [session_multi_step_eligibility_chain](https://jpcite.com/docs/mcp-tools/#session_multi_step_eligibility_chain): [AUDIT, SENSITIVE — §52/§47条の2/§72/§1] release chain B — session_multi_step_eligibility (dim L). Opens a fresh 24h session, persists each supplied step in order, then closes the session and returns... - [rule_tree_batch_eval_chain](https://jpcite.com/docs/mcp-tools/#rule_tree_batch_eval_chain): [AUDIT, SENSITIVE — §52/§47条の2/§72/§1] release chain B — rule_tree_batch_eval (dim M). Evaluates N RuleTrees over a single context dict in 1 call and returns every verdict + rationale_path + source... - [anonymized_cohort_query_with_redact_chain](https://jpcite.com/docs/mcp-tools/#anonymized_cohort_query_with_redact_chain): [AUDIT, SENSITIVE — §52/§47条の2/§72/§1] release chain B — anonymized_cohort_query_with_redact (dim N). Fuses the three dim N primitives (redact_pii_fields over the sample row, check_k_anonymity over... - [time_machine_snapshot_walk_chain](https://jpcite.com/docs/mcp-tools/#time_machine_snapshot_walk_chain): [AUDIT, SENSITIVE — §52/§47条の2/§72/§1] release chain B — time_machine_snapshot_walk (dim Q). Walks one snapshot per month between start_as_of_date and end_as_of_date (capped at month_count_cap) and... - [verify_citations](https://jpcite.com/docs/mcp-tools/#verify_citations): [CITATION-VERIFY] Substantiate verification_status="verified" by deterministic substring + Japanese numeric-form match against the cited primary source. Pure no-LLM. Per-citation verdict ∈ {verifie... - [case_cohort_match_am](https://jpcite.com/docs/mcp-tools/#case_cohort_match_am): [PEER-MATCH] 同業 (JSIC) × 同規模 (employees + revenue) × 同地域 (prefecture) peer-group matcher: pulls source-derived dataset (public corpus, 2,286) + source-derived dataset (public corpus, 201,845) + per... - [match_cohort_5d_am](https://jpcite.com/docs/mcp-tools/#match_cohort_5d_am): [PEER-5D] いつ使うか: 法人 × 業種 × 規模 × 地域 × 制度の 5 軸で「私と同じカテゴリの企業が通った制度」を即座に返す。入力: jsic_major (A-T)、employee_band (4 段階)、prefecture_code (47 都道府県 + null)、limit (1-100)。出力: eligible_program_ids[]、peer_group... - [program_risk_score_am](https://jpcite.com/docs/mcp-tools/#program_risk_score_am): [PROGRAM-REVIEW-4D] いつ使うか: 制度 × 業法 × 行政処分 × 取消理由の 4 軸 review score (0-100) を返す。weighted: 業法 0.5 / 行政処分 0.3 / 取消理由 0.2。入力: program_id (unified_id)。出力: top_review_signal + all_axes[]、weights、_disclai... - [supplier_chain_am](https://jpcite.com/docs/mcp-tools/#supplier_chain_am): [SUPPLIER-CHAIN] いつ使うか: anchor houjin を起点に bipartite chain (invoice_registrant_active/revoked, adoption_partner, enforcement_subject の 4 link_type) を最大 5 hop まで traverse。入力: houjin_bangou (13 桁) +... - [portfolio_optimize_am](https://jpcite.com/docs/mcp-tools/#portfolio_optimize_am): [R8-COMPAT] source-derived dataset 43,966 row full surface — portfolio optimizer (greedy max-IS) + duplicate / mutually-exclusive review pairs + top-3 recommended_mix ranked by axis-weighted score... - [program_compatibility_pair_am](https://jpcite.com/docs/mcp-tools/#program_compatibility_pair_am): [R8-COMPAT] 2 制度間の互換性 — 4-bucket verdict {compatible, mutually_exclusive, unknown, sequential} resolved over source-derived dataset + source-derived dataset + source-derived dataset + source-derive... - [apply_eligibility_chain_am](https://jpcite.com/docs/mcp-tools/#apply_eligibility_chain_am): Multi-step eligibility orchestration over prerequisite_chain → rule_engine_check → source-derived dataset → source-derived dataset per program. Returns per-program verdict (eligible / partial / ine... - [find_complementary_programs_am](https://jpcite.com/docs/mcp-tools/#find_complementary_programs_am): Seed program → source-derived dataset compatible edges → portfolio with combined_ceiling_yen + conflicts. authoritative_share_pct surfaced. inferred_only=true edges are heuristic. §52 sensitive — v... - [simulate_application_am](https://jpcite.com/docs/mcp-tools/#simulate_application_am): Pure-SQL mock walkthrough: source-derived dataset + source-derived dataset + source-derived dataset + source-derived dataset. Returns document_checklist + certifications + est_review_days + complet... - [track_amendment_lineage_am](https://jpcite.com/docs/mcp-tools/#track_amendment_lineage_am): source-derived dataset time-series for a target (14,596 rows; only 140 carry effective_from). Returns timeline + strict_count (with effective_from) + hash_only_count + warnings. eligibility change... - [program_active_periods_am](https://jpcite.com/docs/mcp-tools/#program_active_periods_am): source-derived dataset (1,256 rows) per-program rounds + days_to_close + sunset_warning. Returns open_count / upcoming_count / closed_count + soonest_close_date. sunset_warning fires when only clos... - [programs_by_corporate_form_am](https://jpcite.com/docs/mcp-tools/#programs_by_corporate_form_am): [CORPORATE-FORM-AM] 法人格 × 制度 適用 matcher。NO LLM, ¥3/billable unit metered. `_disclaimer` 必須。 - [program_eligibility_by_form_am](https://jpcite.com/docs/mcp-tools/#program_eligibility_by_form_am): [CORPORATE-FORM-AM] 制度別 法人格 適用表 (15 axes)。NO LLM, ¥3/billable unit metered. `_disclaimer` 必須。 - [get_houjin_360_am](https://jpcite.com/docs/mcp-tools/#get_houjin_360_am): [CORPORATE-LAYER] 法人 360° view by 法人番号 — joins source-derived dataset + source-derived dataset + source-derived dataset + source-derived dataset into a single envelope. Surfaces master_info + invoi... - [list_edinet_disclosures](https://jpcite.com/docs/mcp-tools/#list_edinet_disclosures): [CORPORATE-LAYER] EDINET (金融庁 電子開示) disclosure pointer — returns canonical search URL + API v2 query hint for 有価証券報告書 / 大量保有報告書 etc. Pointer-only (NO live HTTP inside tool). License public_domain.... - [search_invoice_by_houjin_partial](https://jpcite.com/docs/mcp-tools/#search_invoice_by_houjin_partial): [CORPORATE-LAYER] Partial 法人名 search across NTA 適格請求書発行事業者 (PDL v1.0 bulk). Substring LIKE on normalized_name with 出典明記 + 編集・加工注記 attribution included in covered responses. Returns top-N matches wi... - [program_full_context](https://jpcite.com/docs/mcp-tools/#program_full_context): [CROSS-REF R8] Bundle the full primary-source context of a 制度 in 1 call: program metadata + 法令根拠 + 改正履歴 + 関連判例 + 同業 採択事例 + 関連 行政処分 + 排他ルール. deterministic retrieval over public corpus + best-effort... - [law_related_programs_cross](https://jpcite.com/docs/mcp-tools/#law_related_programs_cross): [CROSS-REF R8] Reverse program lookup for a 法令: walks supersession chain (both directions) and surfaces every program citing the law (or a predecessor) with a ref_kind histogram. deterministic retr... - [cases_by_industry_size_pref](https://jpcite.com/docs/mcp-tools/#cases_by_industry_size_pref): [CROSS-REF R8] 採択事例 narrowed by 業種 (JSIC) × 規模 (employees / capital) × 都道府県 in 1 call. deterministic retrieval over source-derived dataset. ¥3/billable unit. NOT sensitive (1次資料の検索). - [find_municipality_subsidies](https://jpcite.com/docs/mcp-tools/#find_municipality_subsidies): [DD2 GEO] Dedicated municipality-OCR subsidy lookup over source-derived dataset. This dataset can be empty on the current public corpus; use `search_programs` for sellable broad 支援制度 discovery unle... - [discover_related](https://jpcite.com/docs/mcp-tools/#discover_related): [DISCOVER-RELATED] Returns up to 5 axes × 5 rows of related entities for the given entity in one call. deterministic retrieval + structured public index-vec, NO LLM. 1 ¥3 unit per call. SAME compos... - [dynamic_eligibility_check_am](https://jpcite.com/docs/mcp-tools/#dynamic_eligibility_check_am): [ELIGIBILITY-DYNAMIC-AM] Joins one houjin's 行政処分 history (source-derived dataset) with source-derived dataset to triage every program in public corpus into blocked / borderline / eligible verdicts.... - [program_eligibility_for_houjin_am](https://jpcite.com/docs/mcp-tools/#program_eligibility_for_houjin_am): [ELIGIBILITY-PAIR-AM] Resolves eligibility for one (program, 法人) pair by joining source-derived dataset with source-derived dataset. NO LLM. Returns `_disclaimer`. Verify primary source. - [get_evidence_packet](https://jpcite.com/docs/mcp-tools/#get_evidence_packet): [EVIDENCE-PACKET] Returns a single Evidence Packet envelope: primary metadata + per-fact provenance + compat-matrix rule verdicts (program only). NO LLM. 1 ¥3 unit per call. SAME composer as REST /... - [fact_signature_verify_am](https://jpcite.com/docs/mcp-tools/#fact_signature_verify_am): [FACT-SIGNATURE] content-hash traceability check + rule-based 'why' explanation for one extracted_fact row in a single MCP call. Returns verify={status: valid|tampered|no_signature|key_unconfigured... - [foreign_fdi_list_am](https://jpcite.com/docs/mcp-tools/#foreign_fdi_list_am): いつ使う: 海外法人 (FDI) 日本進出 entry condition を 80 か国 peer group から filter — region / G7 / OECD / ASEAN / EU / DTA flag の任意組み合わせ. 入力: region (optional enum), is_g7/is_oecd/is_asean/is_eu/has_dta (optional... - [foreign_fdi_country_am](https://jpcite.com/docs/mcp-tools/#foreign_fdi_country_am): いつ使う: 1 か国の FDI 進出 entry condition 詳細 — visa keiei-kanri / 最低資本金 / 業種制限 / DTA+BIT presence / MOFA+JETRO 一次資料 source_url. 入力: country_iso (ISO 3166-1 alpha-2, 2-letter uppercase). 出力: country_name_j... - [check_funding_stack_am](https://jpcite.com/docs/mcp-tools/#check_funding_stack_am): [FUNDING-STACK-AM] Returns a deterministic 制度併用可否 verdict (compatible / incompatible / requires_review / unknown) per pair + aggregate, by joining source-derived dataset with source-derived dataset... - [match_programs_by_funding_stage_am](https://jpcite.com/docs/mcp-tools/#match_programs_by_funding_stage_am): [FUNDING-STAGE-AM] 資金調達ステージ別 (シード/アーリー/グロース/IPO/事業承継) program マッチャー。NO LLM, ¥3/billable unit metered. `_disclaimer` 必須。 - [graph_traverse](https://jpcite.com/docs/mcp-tools/#graph_traverse): [KG] O7 — Returns paths from a 1-3 hop heterogeneous BFS over source-derived dataset (24,004 edges / 15 relation types). deterministic retrieval traversal (no LLM). Output is graph-derived; edges w... - [extract_kg_from_text](https://jpcite.com/docs/mcp-tools/#extract_kg_from_text): [AUDIT, SENSITIVE — §52/§47条の2/§72/§1] Moat M1 KG extraction. Extract canonical - [get_entity_relations](https://jpcite.com/docs/mcp-tools/#get_entity_relations): [AUDIT] Moat M1 KG edge lookup. Returns outgoing + incoming relations for - [search_case_facts](https://jpcite.com/docs/mcp-tools/#search_case_facts): [AUDIT, SENSITIVE — §52/§72] Moat M2 case-fact search over the unified - [get_case_extraction](https://jpcite.com/docs/mcp-tools/#get_case_extraction): [AUDIT, SENSITIVE — §52/§72] Moat M2 fetch the canonical extraction - [search_figures_by_topic](https://jpcite.com/docs/mcp-tools/#search_figures_by_topic): [AUDIT] Moat M3 figure search over the jpcite figure corpus (captions + OCR - [get_figure_caption](https://jpcite.com/docs/mcp-tools/#get_figure_caption): [AUDIT] Moat M3 fetch caption + provenance for a single figure_id. - [semantic_search_law_articles](https://jpcite.com/docs/mcp-tools/#semantic_search_law_articles): [AUDIT, SENSITIVE — §52/§47条の2/§72/§1] Moat M4 law-embedding semantic - [jpcite_bert_v1_encode](https://jpcite.com/docs/mcp-tools/#jpcite_bert_v1_encode): [AUDIT] Moat M5 jpcite-BERT-v1 encode. Returns the SimCSE embedding vector - [rerank_results](https://jpcite.com/docs/mcp-tools/#rerank_results): [AUDIT] Moat M6 cross-encoder reranker. Pairs (query, candidate) are scored - [predict_related_entities](https://jpcite.com/docs/mcp-tools/#predict_related_entities): [AUDIT] Moat M7 KG completion. Returns up to limit related entities for - [find_cases_citing_law](https://jpcite.com/docs/mcp-tools/#find_cases_citing_law): [AUDIT, SENSITIVE — §72/§52] Moat M8 citation lookup — return cases citing the - [find_laws_cited_by_case](https://jpcite.com/docs/mcp-tools/#find_laws_cited_by_case): [AUDIT, SENSITIVE — §72/§52] Moat M8 citation lookup — return laws cited by the - [search_chunks](https://jpcite.com/docs/mcp-tools/#search_chunks): [AUDIT] Moat M9 document chunk search over the unified jpcite chunk store - [multitask_predict](https://jpcite.com/docs/mcp-tools/#multitask_predict): [AUDIT] Moat M11 multi-task inference — runs the requested NLP heads in a - [query_houjin_kg_facts](https://jpcite.com/docs/mcp-tools/#query_houjin_kg_facts): [AUDIT, SENSITIVE — §52/§47条の2/§72/§1/§3] M1 KG facts lookup. - [search_outcome_corpus](https://jpcite.com/docs/mcp-tools/#search_outcome_corpus): [AUDIT, SENSITIVE — §52/§47条の2/§72/§1/§3] M2 採択事例 corpus search. - [search_figures](https://jpcite.com/docs/mcp-tools/#search_figures): [AUDIT] M3 figure CLIP top-k search. - [semantic_law_search](https://jpcite.com/docs/mcp-tools/#semantic_law_search): [AUDIT, SENSITIVE — §52/§47条の2/§72/§1/§3] M4 法令逐条 semantic search. - [find_similar_text](https://jpcite.com/docs/mcp-tools/#find_similar_text): [AUDIT] M5 jpcite-BERT SimCSE cosine similarity search. - [rerank_documents_ce](https://jpcite.com/docs/mcp-tools/#rerank_documents_ce): [AUDIT, PENDING] M6 cross-encoder reranking with ``docs`` parameter. - [predict_relation](https://jpcite.com/docs/mcp-tools/#predict_relation): [AUDIT] M7 KG completion — 4-model ensemble relation prediction. - [classify_citation](https://jpcite.com/docs/mcp-tools/#classify_citation): [AUDIT, SENSITIVE — §72/§52] M8 citation classifier. - [chunk_retrieval](https://jpcite.com/docs/mcp-tools/#chunk_retrieval): [AUDIT] M9 jpcite-text chunk retrieval over 708K-row corpus. - [opensearch_search](https://jpcite.com/docs/mcp-tools/#opensearch_search): [AUDIT] M10 OpenSearch hybrid (BM25 + k-NN) search — U1 M-side R1 format. - [multitask_predict_input](https://jpcite.com/docs/mcp-tools/#multitask_predict_input): [AUDIT] M11 multitask AL iter — single-input multihead inference. - [get_artifact_template](https://jpcite.com/docs/mcp-tools/#get_artifact_template): [AUDIT, SENSITIVE — §52/§47条の2/§72/§1/§3] Moat N1 fetch a single - [list_artifact_templates](https://jpcite.com/docs/mcp-tools/#list_artifact_templates): [AUDIT, SENSITIVE — §52/§47条の2/§72/§1/§3] Moat N1 enumerate artifact - [get_houjin_portfolio](https://jpcite.com/docs/mcp-tools/#get_houjin_portfolio): [AUDIT, SENSITIVE - §52/§47条の2/§72/§1] Moat N2 fetch the program portfolio - [find_gap_programs](https://jpcite.com/docs/mcp-tools/#find_gap_programs): [AUDIT, SENSITIVE - §52/§47条の2/§72/§1] Moat N2 surface gap programs - programs - [get_reasoning_chain](https://jpcite.com/docs/mcp-tools/#get_reasoning_chain): [AUDIT, SENSITIVE — §52/§47条の2/§72/§1/§3] Moat N3 fetch deterministic - [walk_reasoning_chain](https://jpcite.com/docs/mcp-tools/#walk_reasoning_chain): [AUDIT, SENSITIVE — §52/§47条の2/§72/§1/§3] Moat N3 walk the reasoning - [find_filing_window](https://jpcite.com/docs/mcp-tools/#find_filing_window): [AUDIT] Moat N4 - Resolve filing window for (program, houjin). - [list_windows](https://jpcite.com/docs/mcp-tools/#list_windows): [AUDIT] Moat N4 - Enumerate windows by jurisdiction_kind. - [resolve_alias](https://jpcite.com/docs/mcp-tools/#resolve_alias): [AUDIT] Moat N5 - Resolve surface text to canonical_id[]. - [amendment_alert](https://jpcite.com/docs/mcp-tools/#amendment_alert): [AUDIT] Moat N6 - amendment alert + impact score (internal depth label B (metered as billable units)). - [get_recipe](https://jpcite.com/docs/mcp-tools/#get_recipe): [AUDIT, SENSITIVE - SS52/SS47-2/SS72/SS1/SS3] Moat N8 fetch a single - [list_recipes](https://jpcite.com/docs/mcp-tools/#list_recipes): [AUDIT, SENSITIVE - SS52/SS47-2/SS72/SS1/SS3] Moat N8 enumerate recipe - [resolve_placeholder](https://jpcite.com/docs/mcp-tools/#resolve_placeholder): [AUDIT, SENSITIVE - SS52/SS47-2/SS72/SS1/SS3] Moat N9 resolve one - [agent_full_context](https://jpcite.com/docs/mcp-tools/#agent_full_context): [AUDIT, SENSITIVE - §52/§47条の2/§72/§1/§3] Moat HE-1 - 1-call - [prepare_implementation_workpaper](https://jpcite.com/docs/mcp-tools/#prepare_implementation_workpaper): [AUDIT, SENSITIVE — §52/§47条の2/§72/§1/§3] HE-2 Heavy-Output endpoint. - [agent_briefing_pack](https://jpcite.com/docs/mcp-tools/#agent_briefing_pack): [AUDIT, SENSITIVE — §52/§47条の2/§72/§1/§3] Moat HE-3 agent briefing pack. - [multi_tool_orchestrate](https://jpcite.com/docs/mcp-tools/#multi_tool_orchestrate): [AUDIT, SENSITIVE - SS52/SS47-2/SS72/SS1/SS3] HE-4 server-side bundler: - [cohort_lora_resolve](https://jpcite.com/docs/mcp-tools/#cohort_lora_resolve): [AUDIT] Moat BB4 peer group LoRA adapter router. Resolves a segment - [agent_cohort_deep_chusho_keieisha](https://jpcite.com/docs/mcp-tools/#agent_cohort_deep_chusho_keieisha): [AUDIT, SENSITIVE — §52/§47条の2/§72/§1/§3] Moat HE-5 peer group deep — 中小経営者. - [agent_cohort_deep_gyouseishoshi](https://jpcite.com/docs/mcp-tools/#agent_cohort_deep_gyouseishoshi): [AUDIT, SENSITIVE — §52/§47条の2/§72/§1/§3] Moat HE-5 peer group deep — 行政書士. - [agent_cohort_deep_kaikeishi](https://jpcite.com/docs/mcp-tools/#agent_cohort_deep_kaikeishi): [AUDIT, SENSITIVE — §52/§47条の2/§72/§1/§3] Moat HE-5 peer group deep — 会計士. - [agent_cohort_deep_shihoshoshi](https://jpcite.com/docs/mcp-tools/#agent_cohort_deep_shihoshoshi): [AUDIT, SENSITIVE — §52/§47条の2/§72/§1/§3] Moat HE-5 peer group deep — 司法書士. - [agent_cohort_deep_zeirishi](https://jpcite.com/docs/mcp-tools/#agent_cohort_deep_zeirishi): [AUDIT, SENSITIVE — §52/§47条の2/§72/§1/§3] Moat HE-5 peer group deep — 税理士. - [agent_cohort_ultra_chusho_keieisha](https://jpcite.com/docs/mcp-tools/#agent_cohort_ultra_chusho_keieisha): [AUDIT, SENSITIVE — §52/§47条の2/§72/§1/§3] Moat HE-6 peer group ultra — 中小経営者. - [agent_cohort_ultra_gyouseishoshi](https://jpcite.com/docs/mcp-tools/#agent_cohort_ultra_gyouseishoshi): [AUDIT, SENSITIVE — §52/§47条の2/§72/§1/§3] Moat HE-6 peer group ultra — 行政書士. - [agent_cohort_ultra_kaikeishi](https://jpcite.com/docs/mcp-tools/#agent_cohort_ultra_kaikeishi): [AUDIT, SENSITIVE — §52/§47条の2/§72/§1/§3] Moat HE-6 peer group ultra — 会計士. - [agent_cohort_ultra_shihoshoshi](https://jpcite.com/docs/mcp-tools/#agent_cohort_ultra_shihoshoshi): [AUDIT, SENSITIVE — §52/§47条の2/§72/§1/§3] Moat HE-6 peer group ultra — 司法書士. - [agent_cohort_ultra_zeirishi](https://jpcite.com/docs/mcp-tools/#agent_cohort_ultra_zeirishi): [AUDIT, SENSITIVE — §52/§47条の2/§72/§1/§3] Moat HE-6 peer group ultra — 税理士. - [predictive_houjin_outlook](https://jpcite.com/docs/mcp-tools/#predictive_houjin_outlook): [AUDIT, SENSITIVE - §52/§47条の2/§72/§1/§3] HE-5 predictive_houjin_outlook. - [session_context_lookback](https://jpcite.com/docs/mcp-tools/#session_context_lookback): [AUDIT, SENSITIVE - §52/§47条の2/§72/§1/§3] HE-6 session_context_lookback. - [rule_tree_application](https://jpcite.com/docs/mcp-tools/#rule_tree_application): [AUDIT, SENSITIVE - §52/§47条の2/§72/§1/§3] HE-7 rule_tree_application. - [anonymized_cohort_query](https://jpcite.com/docs/mcp-tools/#anonymized_cohort_query): [AUDIT, SENSITIVE - §52/§47条の2/§72/§1/§3] HE-8 anonymized_cohort_query. - [explainable_evidence_chain](https://jpcite.com/docs/mcp-tools/#explainable_evidence_chain): [AUDIT, SENSITIVE - §52/§47条の2/§72/§1/§3] HE-9 explainable_evidence_chain. - [composable_subsidy_audit](https://jpcite.com/docs/mcp-tools/#composable_subsidy_audit): [AUDIT, SENSITIVE - §52/§47条の2/§72/§1/§3] HE-10 composable_subsidy_audit. - [time_machine_program_status](https://jpcite.com/docs/mcp-tools/#time_machine_program_status): [AUDIT, SENSITIVE - §52/§47条の2/§72/§1/§3] HE-11 time_machine_program_status. - [federated_partner_query](https://jpcite.com/docs/mcp-tools/#federated_partner_query): [AUDIT, SENSITIVE - §52/§47条の2/§72/§1/§3] HE-12 federated_partner_query. - [copilot_scaffold_workpaper](https://jpcite.com/docs/mcp-tools/#copilot_scaffold_workpaper): [AUDIT, SENSITIVE - §52/§47条の2/§72/§1/§3] HE-13 copilot_scaffold_workpaper. - [ma_lifecycle_compose](https://jpcite.com/docs/mcp-tools/#ma_lifecycle_compose): [AUDIT, SENSITIVE - §52/§47条の2/§72/§1/§3] HE-14 ma_lifecycle_compose. - [deep_health_am](https://jpcite.com/docs/mcp-tools/#deep_health_am): jpcite サービス全体の health check (api / mcp / billing / data freshness / dashboard 5 component の集約)。本番監視・SLA breach 検知・on-call rollover 直前確認に使う。引数なし。返却: status ("ok"/"degraded"/"unhealthy") / latency_ms... - [pack_construction](https://jpcite.com/docs/mcp-tools/#pack_construction): [INDUSTRY-PACK] 建設業 (JSIC D) peer group pack: top 10 programs (建設・住宅・耐震・改修 fence) + up to 5 国税不服審判所 裁決事例 (法人税・消費税) + up to 3 通達 references (法基通・消基通). Single ¥3/billable unit. NO LLM. §52/§47条の2 sen... - [pack_manufacturing](https://jpcite.com/docs/mcp-tools/#pack_manufacturing): [INDUSTRY-PACK] 製造業 (JSIC E) peer group pack: top 10 programs (ものづくり・設備投資・省エネ・GX・事業再構築 fence) + up to 5 国税不服審判所 裁決事例 (法人税・所得税) + up to 3 通達 references (法基通). Single ¥3/billable unit. NO LLM. §52/§4... - [pack_real_estate](https://jpcite.com/docs/mcp-tools/#pack_real_estate): [INDUSTRY-PACK] 不動産業 (JSIC K) peer group pack: top 10 programs (不動産・空き家・住宅・賃貸 fence) + up to 5 国税不服審判所 裁決事例 (所得税・相続税・法人税) + up to 3 通達 references (所基通・相基通). Single ¥3/billable unit. NO LLM. §52/§47... - [industry_scale_region_view](https://jpcite.com/docs/mcp-tools/#industry_scale_region_view): [N7 peer group VIEW] Resolve a 業界(JSIC) × 規模(scale_class) × 地域(prefcode/citycode) peer group over source-derived dataset (~4,935 rows). Returns peer group statistics: program_ids/program_count, jud... - [invoice_risk_lookup](https://jpcite.com/docs/mcp-tools/#invoice_risk_lookup): [R8-INVOICE-REVIEW] T-number 単発 review lookup. invoice_registrants × houjin_master を機械的照合し、0-100 score + tax_credit_eligible boolean + 6 ヶ月 / 1 年経過 heuristic で review_band (clear / caution / verify... - [invoice_risk_batch](https://jpcite.com/docs/mcp-tools/#invoice_risk_batch): [R8-INVOICE-REVIEW] T-number 一括 review lookup (最大 100 件 / 1 metered call)。各 item は invoice_review_lookup と同じ envelope shape (review={…} or error="…")。経理 fan-out で取引先一覧を 1 call で scoring する用途。NO LLM... - [houjin_invoice_status](https://jpcite.com/docs/mcp-tools/#houjin_invoice_status): [R8-INVOICE-REVIEW] 法人番号 → 適格事業者番号 resolve + review envelope。invoice_registrants 側で houjin_bangou が見つからない場合は invoice_registration_number=null + registered=False + score=100 (block) を返す。NO LLM。§52 f... - [jpcite_route](https://jpcite.com/docs/mcp-tools/#jpcite_route): Route a user request to the smallest sufficient P0 jpcite action. Free, deterministic, no external calls. - [jpcite_preview_cost](https://jpcite.com/docs/mcp-tools/#jpcite_preview_cost): Preview units, known gaps, consent needs, and no-hit caveat. Free. - [jpcite_execute_packet](https://jpcite.com/docs/mcp-tools/#jpcite_execute_packet): Fail-closed execute entrypoint. It is currently non-billable. - [jpcite_get_packet](https://jpcite.com/docs/mcp-tools/#jpcite_get_packet): Retrieve a P0 packet if materialized. Free and deterministic; no absence claim is made. - [search_kokkai_utterance](https://jpcite.com/docs/mcp-tools/#search_kokkai_utterance): [KOKKAI] public dataset 国会会議録 keyword + date filter. Returns top rows with 3-axis citation (source_url + retrieved_at + sha256). Sensitive (§52 / §47条の2 / §72 / §3) — disclaimer envelope mandatory.... - [search_shingikai_minutes](https://jpcite.com/docs/mcp-tools/#search_shingikai_minutes): [SHINGIKAI] public dataset 審議会 議事録 keyword filter. Returns top rows with 3-axis citation. Sensitive (§52 / §47条の2 / §72) — disclaimer envelope mandatory. NO LLM, single ¥3/billable unit billing. - [unified_lifecycle_calendar](https://jpcite.com/docs/mcp-tools/#unified_lifecycle_calendar): Returns merged calendar of tax sunset + program sunset + application close + law cliff events. Output is search-derived from public-source data; verify primary source (source_url) for business deci... - [program_lifecycle](https://jpcite.com/docs/mcp-tools/#program_lifecycle): [LIFECYCLE] Returns source-linked snapshot of program status (abolished / superseded / sunset_imminent / sunset_scheduled / amended / active / not_yet / unknown). Most rows lack historical diffs (e... - [program_abstract_structured](https://jpcite.com/docs/mcp-tools/#program_abstract_structured): I18N — Returns audience-targeted, closed-vocab Japanese abstract for a single program. Translation is the customer LLM's job; we does not call Anthropic API. official_name_ja + legal_id must stay v... - [find_municipal_program_pdf](https://jpcite.com/docs/mcp-tools/#find_municipal_program_pdf): [M1 MUNICIPAL PDF] 自治体補助金 PDF metadata + Textract OCR 抜粋を 1-call で返す scaffold tool。W1 AWS-A wet-run ($4,939, Textract 1,718 PDF, 24-48h) 着地前は seed manifest (150 自治体) + content-hash placeholder。着地後は... - [search_municipality_subsidies](https://jpcite.com/docs/mcp-tools/#search_municipality_subsidies): [MUNICIPALITY] 自治体補助金 page-diff listing over the dedicated municipality table. This dataset can be empty on the current public corpus; use `search_programs` for sellable broad 支援制度 discovery unless... - [find_saiketsu](https://jpcite.com/docs/mcp-tools/#find_saiketsu): [DISCOVER-CASE-LAW] 国税不服審判所 (KFS) 公表裁決事例 を全文検索 (FTS5 trigram on nta_saiketsu)。出力は citation のみで税務助言 (税理士法 §52) ではない。出典 source_url で原典確認必須。 - [cite_tsutatsu](https://jpcite.com/docs/mcp-tools/#cite_tsutatsu): [CITE-TSUTATSU] Lookup a 通達 article by code. Returns title + body excerpt + source_url. 出力は citation のみで税務助言 (税理士法 §52) ではない。 - [find_shitsugi](https://jpcite.com/docs/mcp-tools/#find_shitsugi): [DISCOVER-QA] 国税庁 質疑応答事例 を全文検索 (FTS5 trigram on nta_shitsugi)。出力は citation のみで税務助言 (税理士法 §52) ではない。出典 source_url で原典確認必須。 - [find_bunsho_kaitou](https://jpcite.com/docs/mcp-tools/#find_bunsho_kaitou): [DISCOVER-RULING] 国税庁 文書回答事例 (事前照会回答) を全文検索。出力は citation のみで税務助言 (税理士法 §52) ではない。出典 source_url で原典確認必須。 - [opensearch_hybrid_search](https://jpcite.com/docs/mcp-tools/#opensearch_hybrid_search): [PREVIEW — pending_upstream_lane] OpenSearch BM25 + kuromoji hybrid search contract. Returns a zero-billing preview envelope unless an operator-configured live endpoint is available. NOT an 採択 fore... - [outcome_houjin_360](https://jpcite.com/docs/mcp-tools/#outcome_houjin_360): [AUDIT, SENSITIVE — §52/§47条の2/§72/§1] release outcome — 法人 due diligence 360. estimated 3 billable unit(s). NO LLM. Returns JPCIR envelope (Evidence + OutcomeContract + citations + known_gaps) fro... - [outcome_program_lineage](https://jpcite.com/docs/mcp-tools/#outcome_program_lineage): [AUDIT, SENSITIVE — §52/§47条の2/§72/§1] release outcome — 制度系譜 (amendment lineage). estimated 2 billable unit(s). NO LLM. Returns JPCIR envelope with predecessor/successor chain from source-derived... - [outcome_adoption_observation](https://jpcite.com/docs/mcp-tools/#outcome_acceptance_probability): [AUDIT, SENSITIVE — §52/§47条の2/§72/§1] release outcome — 採択事例 peer group observation. estimated 2 billable unit(s). NO LLM. Returns JPCIR envelope with source-linked observed peer group counts from... - [outcome_tax_ruleset_phase_change](https://jpcite.com/docs/mcp-tools/#outcome_tax_ruleset_phase_change): [AUDIT, SENSITIVE — §52/§47条の2/§72/§1] release outcome — 税制段階変更. estimated 2 billable unit(s). NO LLM. Returns JPCIR envelope with tax-rule + 通達 + 改正履歴 chain. - [outcome_regulatory_q_over_q_diff](https://jpcite.com/docs/mcp-tools/#outcome_regulatory_q_over_q_diff): [AUDIT, SENSITIVE — §52/§47条の2/§72/§1] release outcome — 法令改正 Q-over-Q diff. estimated 3 billable unit(s). NO LLM. Returns JPCIR envelope with quarterly law diff. - [outcome_enforcement_seasonal_trend](https://jpcite.com/docs/mcp-tools/#outcome_enforcement_seasonal_trend): [AUDIT, SENSITIVE — §52/§47条の2/§72/§1] release outcome — 行政処分季節性. estimated 1 billable unit(s). NO LLM. Returns JPCIR envelope with monthly enforcement-action seasonality. - [outcome_bid_announcement_seasonality](https://jpcite.com/docs/mcp-tools/#outcome_bid_announcement_seasonality): [AUDIT, SENSITIVE — §52/§47条の2/§72/§1] release outcome — 入札季節性. estimated 1 billable unit(s). NO LLM. Returns JPCIR envelope with monthly bid-announcement seasonality. - [outcome_succession_event_pulse](https://jpcite.com/docs/mcp-tools/#outcome_succession_event_pulse): [AUDIT, SENSITIVE — §52/§47条の2/§72/§1] release outcome — 事業承継 event pulse. estimated 2 billable unit(s). NO LLM. Returns JPCIR envelope with succession-event signal + program matcher. - [outcome_prefecture_program_heatmap](https://jpcite.com/docs/mcp-tools/#outcome_prefecture_program_heatmap): [AUDIT, SENSITIVE — §52/§47条の2/§72/§1] release outcome — 47 都道府県 × 制度 heatmap. estimated 2 billable unit(s). NO LLM. Returns JPCIR envelope with prefecture × program heatmap rollup. - [outcome_cross_prefecture_arbitrage](https://jpcite.com/docs/mcp-tools/#outcome_cross_prefecture_arbitrage): [AUDIT, SENSITIVE — §52/§47条の2/§72/§1/§3] release outcome — 都道府県間アービトラージ. estimated 3 billable unit(s). NO LLM. Returns JPCIR envelope with cross-prefecture program gap + 移転メリット rollup. - [policy_upstream_watch](https://jpcite.com/docs/mcp-tools/#policy_upstream_watch): [POLICY_UPSTREAM] public dataset cross-axis upstream signal rollup. Per keyword: kokkai count + shingikai count + ongoing-pubcomment count + most-recent evidence URL on each axis. Drives "what shou... - [policy_upstream_timeline](https://jpcite.com/docs/mcp-tools/#policy_upstream_timeline): [POLICY_UPSTREAM] public dataset single-topic timeline across 5 stages (kokkai → shingikai → pubcomment → law_amendment → program_launch). Each event carries 3-axis citation (source_url + retrieved... - [portfolio_optimize_precomputed_am](https://jpcite.com/docs/mcp-tools/#portfolio_optimize_precomputed_am): Top 8 program ranked recommendations for a 法人 (precomputed daily). Reads source-derived dataset (data update, regular source refresh) — distinct from compatibility_tools.portfolio_optimize_am which... - [houjin_risk_score_am](https://jpcite.com/docs/mcp-tools/#houjin_risk_score_am): 0-100 composite review score for a 法人 (daily refresh). 40 enforcement + 30 invoice + 15 adoption + 15 credit_age. Pure SELECT against source-derived dataset. NO LLM, 1 ¥3 billable unit. §52 envelope. - [program_forecast_30yr_am](https://jpcite.com/docs/mcp-tools/#program_forecast_30yr_am): 30-year x 12-month Markov chain forecast for a program (monthly refresh). Returns per-(year, month) state distribution over {active, paused, sunset, renewed} + expected_call_count cumulative. Pure... - [alliance_opportunities_am](https://jpcite.com/docs/mcp-tools/#alliance_opportunities_am): Top 10 partner 法人 候補 for a source 法人 (weekly refresh). Composes co-adoption + JSIC chain + size balance + region proximity into a 0-100 score. Pure SELECT against source-derived dataset. NO LLM, 1... - [graph_vec_search_am](https://jpcite.com/docs/mcp-tools/#graph_vec_search_am): Top-k semantic similar entity via structured public index-vec k-NN over source-derived dataset (503,930 rows x 12 record_kinds). deterministic retrieval k-NN on precomputed embeddings. NO LLM at re... - [prerequisite_chain](https://jpcite.com/docs/mcp-tools/#prerequisite_chain): [R5-PREREQUISITE-CHAIN] Returns curated prerequisite chain for a program (認定 / 計画 / 登録) with preparation_time_days + preparation_cost_yen. Coverage is partial (135/8,203 programs = 1.6%); empty cha... - [get_provenance](https://jpcite.com/docs/mcp-tools/#get_provenance): [PROVENANCE] Returns source attribution for the entity at point-in-time of last fetch — all rows from source-derived dataset × source-derived dataset JOIN with license_summary. include_facts=True a... - [get_provenance_for_fact](https://jpcite.com/docs/mcp-tools/#get_provenance_for_fact): [PROVENANCE-FACT] Returns source attribution for a single fact_id at point-in-time of last fetch. Resolves source-derived dataset.source_id → source-derived dataset. When source_id is NULL (legacy... - [get_pubcomment_status](https://jpcite.com/docs/mcp-tools/#get_pubcomment_status): [PUBCOMMENT] public dataset e-Gov パブコメ 公示 follow. Returns 公示中 + 直近 90 日終了 案件 with 3-axis citation (full_text_url + retrieved_at + sha256) + peer_group_impact rollup. Lead time 30-60 日, sensitive (§... - [realestate_recent_deals](https://jpcite.com/docs/mcp-tools/#realestate_recent_deals): [REAL-ESTATE / Q8 Q15 / internal depth label C (metered as billable units)] 近隣取引事例の集約 (国土交通省 取引価格情報 API ベース)。area_code (5桁 MLIT 市区町村コード) を起点に radius_m / days_back / limit でフィルタした取引事例 (TradePrice /... - [koushi_kakaku_lookup](https://jpcite.com/docs/mcp-tools/#koushi_kakaku_lookup): [REAL-ESTATE / Q8 Q15 / internal depth label A (metered as billable units)] 公示価格 + 都道府県地価調査の標準地点をルックアップ。address を渡すと都道府県プレフィックス match → 該当年の標準地番号・公示価格 (円/m²) ・用途・形状・建ぺい率・容積率・前年比 etc. を返却。MLIT XCT00... - [realestate_touki_kankatsu](https://jpcite.com/docs/mcp-tools/#realestate_touki_kankatsu): [REAL-ESTATE / Q8 Q13 / internal depth label A (metered as billable units)] 不動産登記の管轄法務局ルーティング。address → 都道府県解決 → 9 区分の地方法務局管区 (札幌/仙台/東京/名古屋/大阪/広島/高松/福岡/那覇) → 該当する地方法務局・支局リストを返却。登記簿謄本 bulk fetch (¥3... - [recommend_similar_program](https://jpcite.com/docs/mcp-tools/#recommend_similar_program): Vector k-NN over source-derived datasetS (programs). Re-ranked by cosine + verification_count + source-derived dataset (W22-9). NOT an 採択 forecast — 行政書士法 §1 / 税理士法 §52 fence; the LLM must surface... - [recommend_similar_case](https://jpcite.com/docs/mcp-tools/#recommend_similar_case): Vector k-NN over source-derived datasetC (source-derived dataset). Cosine distance with optional density boost. NOT an 採択 forecast — 行政書士法 §1 / 税理士法 §52 fence; the LLM must surface the disclaimer e... - [recommend_similar_court_decision](https://jpcite.com/docs/mcp-tools/#recommend_similar_court_decision): Vector k-NN over source-derived datasetJ (court_decisions). Cosine distance with optional density boost. NOT a legal opinion — 弁護士法 §72 / 行政書士法 §1 fence; the LLM must surface the disclaimer envelope. - [programs_by_region_am](https://jpcite.com/docs/mcp-tools/#programs_by_region_am): Programs hit-map for a 5-digit region code. - [region_coverage_am](https://jpcite.com/docs/mcp-tools/#region_coverage_am): Per-level program hit count + coverage_gap flag for a region. - [search_regions_am](https://jpcite.com/docs/mcp-tools/#search_regions_am): Free-text search over source-derived dataset (1,966 rows). Exact > prefix > substring rank. - [rule_engine_check](https://jpcite.com/docs/mcp-tools/#rule_engine_check): [R9-UNIFIED-RULE-ENGINE] Returns rule evaluation result + applicable law citations across 6 corpora (49,247 rows): exclusion + compat_matrix (48,815 rows, of which 4,849 are 'unknown' status) + com... - [semantic_search_legacy_am](https://jpcite.com/docs/mcp-tools/#semantic_search_legacy_am): いつ使う: 1024-dim e5-large embedding を持つ agent が canonical 1-row-per-canonical_id corpus で cosine top-k を 1 call で取りたい時。 入力: embedding (1024d L2-normalised float list), corpus (default 'program'), top... - [semantic_search_v2_am](https://jpcite.com/docs/mcp-tools/#semantic_search_v2_am): いつ使う: plain-text query から source-derived dataset 503k+ corpus を hybrid 検索 (BM25 + 384d e5-small + cross-encoder) — semantic_search_am の v2-suffix alias、Anthropic registry 互換維持 + dim 19 audit MCP-gl... - [semantic_search_am](https://jpcite.com/docs/mcp-tools/#semantic_search_am): いつ使う: plain-text 検索 query から hybrid 検索結果 (BM25 + 384d e5-small + cross-encoder) を返す。入力: query (string 2-512), top_k (1-50, default 10), rerank (bool, default True), record_kinds (optional list). 出力... - [match_due_diligence_questions](https://jpcite.com/docs/mcp-tools/#match_due_diligence_questions): DD question checklist (30-60 items) tailored to industry × program portfolio × 与信 review by joining dd_question_templates (60 rows, data update) with houjin / adoption / enforcement / invoice corpo... - [prepare_kessan_briefing](https://jpcite.com/docs/mcp-tools/#prepare_kessan_briefing): 月次 / 四半期 summary of program-eligibility changes since last 決算 by joining source-derived dataset + source-derived dataset within the FY window. Compounds saved_searches digest cadence. §52 sensitive... - [forecast_program_renewal](https://jpcite.com/docs/mcp-tools/#forecast_program_renewal): Probability + window of program renewal in next FY based on historical source-derived dataset cadence + source-derived dataset density. 4-signal weighted average (frequency / recency / pipeline / s... - [cross_check_jurisdiction](https://jpcite.com/docs/mcp-tools/#cross_check_jurisdiction): Registered (法務局) vs invoice (NTA) vs operational (交付) jurisdiction breakdown. Detects 不一致 for 税理士 onboarding — flags prefecture mismatches between houjin_master / invoice_registrants / adoption_rec... - [bundle_application_kit](https://jpcite.com/docs/mcp-tools/#bundle_application_kit): Complete downloadable kit assembly: program metadata + cover letter scaffold + 必要書類 checklist + similar 採択例 list. Pure file assembly, NO LLM, NO DOCX generation. §1 sensitive — 申請書面作成は行政書士の独占業務、当社は... - [shihoshoshi_dd_pack_am](https://jpcite.com/docs/mcp-tools/#shihoshoshi_dd_pack_am): [public dataset 司法書士] 司法書士 peer group dedicated DD pack — 1-call で 商業登記前 360° (source-derived dataset + corp.* facts) + 不動産登記前 cross_check_jurisdiction + 反社相当 enforcement (fine/grant_refund/subsidy... - [get_source_manifest](https://jpcite.com/docs/mcp-tools/#get_source_manifest): [EVIDENCE-GRAPH] Returns the full source manifest for one program: per-fact provenance (where source_id is populated) + entity-level rollup (source-derived dataset) + license set + publisher count... - [list_static_resources_am](https://jpcite.com/docs/mcp-tools/#list_static_resources_am): Manifest of curated jpcite taxonomies (制度 / 用語 / 助成区分 / 義務 etc.). - [get_static_resource_am](https://jpcite.com/docs/mcp-tools/#get_static_resource_am): Load one curated taxonomy / lookup file. Returns full JSON + license. - [list_example_profiles_am](https://jpcite.com/docs/mcp-tools/#list_example_profiles_am): Manifest of canonical client-intake example payloads (PII-clean). - [get_example_profile_am](https://jpcite.com/docs/mcp-tools/#get_example_profile_am): Return one canonical client profile JSON as a complete-payload example. - [match_succession_am](https://jpcite.com/docs/mcp-tools/#match_succession_am): [SUCCESSION-MATCH] M&A / 事業承継 制度 matcher: scenario (親族内 / 第三者M&A / 役員従業員) と 売上 / 従業員数 / 代表者年齢 から、適用候補となる 補助金・税制 (事業承継税制 / 相続税精算課税)・法令支援 (経営承継円滑化法) を返す。deterministic retrieval, NO LLM. 1 unit = 1 ca... - [succession_playbook_am](https://jpcite.com/docs/mcp-tools/#succession_playbook_am): [SUCCESSION-PLAYBOOK] 標準 事業承継 playbook (7 step) + advisor chain (税理士 + M&A仲介 + 認定支援機関 + 司法書士 + 弁護士) + cliff dates (特例承継計画 提出期限 / 特例措置 適用期限). NO LLM. 1 unit. §52 envelope. - [list_tax_sunset_alerts](https://jpcite.com/docs/mcp-tools/#list_tax_sunset_alerts): [TIMELINE-TAX] Returns tax measures whose effective_until falls within the next N days, plus 大綱 cliff date buckets. Output is search-derived from source-derived dataset (57 rows with effective_unti... - [tax_rule_full_chain](https://jpcite.com/docs/mcp-tools/#tax_rule_full_chain): [TAX-CHAIN] 税制 (TAX-*) を巡る解釈一式を 1 call で取得: 規定本文 + 根拠条文 (laws) + 通達 (nta_tsutatsu_index) + 裁決事例 (nta_saiketsu) + 判例 (court_decisions) + 改正履歴 (sibling tax_rulesets). 出力は citation のみで税務助言 (税理士法 §52)... - [get_am_tax_rule](https://jpcite.com/docs/mcp-tools/#get_am_tax_rule): [DISCOVER-TAX-RULE] Returns structured tax rule rows for a 税制措置 (rate / cap / 根拠条文 / 適用期限) from source-derived dataset. One measure can return multiple rows when both 特別償却 and 税額控除 exist. Output is... - [query_at_snapshot_v2](https://jpcite.com/docs/mcp-tools/#query_at_snapshot_v2): [AUDIT, SENSITIVE — §52 / §47条の2] Time Machine. Returns the program's eligibility / amount / deadline frozen at as_of, with 3-axis citation (source_url + source_fetched_at + source_sha256). Pivots... - [query_program_evolution](https://jpcite.com/docs/mcp-tools/#query_program_evolution): [AUDIT, SENSITIVE — §52 / §47条の2] Time Machine — 12-month evolution grid. Runs query_at_snapshot at every month-end of `year` in one call (single ¥3 metered event, 11 stored resultd reads). Surface... - [program_timeline_am](https://jpcite.com/docs/mcp-tools/#program_timeline_am): [TIMELINE] Per-program annual adoption rollup + next_round (closest open / upcoming source-derived dataset) + competition_proxy (adoption_per_round). Reads source-derived dataset (201,845) + source... - [cases_timeline_trend_am](https://jpcite.com/docs/mcp-tools/#cases_timeline_trend_am): [TIMELINE-TREND] 業種 (JSIC prefix) × 地域 (prefecture) × 時間 (year) trend over source-derived dataset: yearly adoption_count / distinct_houjin / distinct_program_count / total_amount_yen + trend_flag (... - [upcoming_rounds_for_my_profile_am](https://jpcite.com/docs/mcp-tools/#upcoming_rounds_for_my_profile_am): [UPCOMING-ROUNDS] Match every source-derived dataset closing in the next horizon_days against the calling key's client_profiles via JSIC × prefecture × target_types × last_active_program overlap. A... - [search_trademark_published](https://jpcite.com/docs/mcp-tools/#search_trademark_published): [TRADEMARK-PUBLISHED] 商標公報 + 意匠公報 + 国際商標公報 search (INPIT + 特許庁 gazette OCR moat). NO LLM, ¥3/billable unit metered. `_disclaimer` 必須。 - [validate](https://jpcite.com/docs/mcp-tools/#validate): [VALIDATE] applicant_data を source-derived dataset の active 述語で評価し、 - [evidence_with_provenance_chain](https://jpcite.com/docs/mcp-tools/#evidence_with_provenance_chain): [AUDIT, SENSITIVE — §52/§47条の2/§72/§1] release chain — evidence_with_provenance (dim P + Q + O + N). Locks a fact to a monthly snapshot, builds an content-hash canonical payload, and gates the resp... - [session_aware_eligibility_check_chain](https://jpcite.com/docs/mcp-tools/#session_aware_eligibility_check_chain): [AUDIT, SENSITIVE — §52/§47条の2/§72/§1] release chain — session_aware_eligibility_check (dim L + M + K). Opens a 24h session_context, evaluates rule_tree, enqueues a predictive_service event so the... - [federated_handoff_with_audit_chain](https://jpcite.com/docs/mcp-tools/#federated_handoff_with_audit_chain): [AUDIT, SENSITIVE — §52/§47条の2/§72/§1] release chain — federated_handoff_with_audit (dim P + R + N). When jpcite cannot answer, asks the curated 6-partner federation (freee/mf/notion/slack/github/l... - [temporal_compliance_audit_chain](https://jpcite.com/docs/mcp-tools/#temporal_compliance_audit_chain): [AUDIT, SENSITIVE — §52/§47条の2/§72/§1] release chain — temporal_compliance_audit (dim Q + M + O). Resolves two monthly snapshots, runs counterfactual_diff (added/removed/changed/unchanged + content... - [anonymized_aggregate_query](https://jpcite.com/docs/mcp-tools/#anonymized_aggregate_query): [ANONYMIZED, SENSITIVE — §52/§47条の2/§72/§1] release dim N k-anonymity + PII-redact gate. Returns aggregates only when cohort_size >= K_ANONYMITY_MIN (5); otherwise returns absent envelope. PII fiel... - [sign_fact](https://jpcite.com/docs/mcp-tools/#sign_fact): [AUDIT, SENSITIVE — §52/§47条の2/§72/§1] release dim O sign_fact. Builds the canonical UTF-8 payload bytes for (fact_id, FactMetadata 4-axis). Returns canonical_payload_hex deterministically (single... - [verify_fact](https://jpcite.com/docs/mcp-tools/#verify_fact): [AUDIT, SENSITIVE — §52/§47条の2/§72/§1] release dim O verify_fact. Resolves the operator public key from AUTONOMATH_FACT_SIGN_PUBLIC_KEY env (32-byte hex), then verifies the operator-key signature o... - [eligibility_audit_workpaper_composed](https://jpcite.com/docs/mcp-tools/#eligibility_audit_workpaper_composed): [AUDIT, SENSITIVE — §52/§47条の2/§72/§1] release dim P composed — 税理士 monthly eligibility audit workpaper. Compresses 4 atomic tools (apply_eligibility_chain_am + track_amendment_lineage_am + program... - [subsidy_eligibility_full_composed](https://jpcite.com/docs/mcp-tools/#subsidy_eligibility_full_composed): [AUDIT, SENSITIVE — §52/§47条の2/§72/§1] release dim P composed — 補助金 7-step full eligibility check. Compresses 5 atomic tools (search_programs_am + apply_eligibility_chain_am + check_enforcement_am... - [ma_due_diligence_pack_composed](https://jpcite.com/docs/mcp-tools/#ma_due_diligence_pack_composed): [AUDIT, SENSITIVE — §52/§47条の2/§72/§1/§3] release dim P composed — M&A 12-axis due-diligence pack. Compresses 4 atomic tools (match_due_diligence_questions + cross_check_jurisdiction + check_enforc... - [invoice_compatibility_check_composed](https://jpcite.com/docs/mcp-tools/#invoice_compatibility_check_composed): [AUDIT, SENSITIVE — §52/§47条の2/§72/§1] release dim P composed — 適格事業者照合 + 取引先 enrichment. Compresses 3 atomic tools (check_invoice_registrant + corporate_layer_lookup + check_enforcement_am) into 1... - [query_snapshot_as_of_v2](https://jpcite.com/docs/mcp-tools/#query_snapshot_as_of_v2): [AUDIT, SENSITIVE — §52/§47条の2/§72/§1] release dim Q v2. Returns the file-backed monthly snapshot whose as_of_date is the largest <= the requested date. Reads published artifact//... - [counterfactual_diff_v2](https://jpcite.com/docs/mcp-tools/#counterfactual_diff_v2): [AUDIT, SENSITIVE — §52/§47条の2/§72/§1] release dim Q v2 counterfactual. Resolves the file-backed monthly snapshots at as_of_a and as_of_b for the dataset, then returns the top-level JSON-key diff (... - [recommend_partner_for_gap](https://jpcite.com/docs/mcp-tools/#recommend_partner_for_gap): [AUDIT, SENSITIVE — §52/§47条の2/§72/§1] release dim R federated MCP recommendation. Deterministic substring + alias matcher over the curated 6-partner federation (freee/mf/notion/slack/github/linear... - [product_tax_monthly_closing_pack](https://jpcite.com/docs/mcp-tools/#product_tax_monthly_closing_pack): [AUDIT, SENSITIVE — §52/監査基準] A1 Product — 税理士月次決算 Pack. - [product_audit_workpaper_pack](https://jpcite.com/docs/mcp-tools/#product_audit_workpaper_pack): [AUDIT, SENSITIVE — §47条の2/監査基準] A2 Product — 会計士監査調書 Pack. - [product_subsidy_roadmap_12month](https://jpcite.com/docs/mcp-tools/#product_subsidy_roadmap_12month): [AUDIT, SENSITIVE - §52/§47条の2/§72/§1/§3] A3 - 補助金活用ロードマップ Pack. - [product_shuugyou_kisoku_pack](https://jpcite.com/docs/mcp-tools/#product_shuugyou_kisoku_pack): [AUDIT, SENSITIVE - §52/§47条の2/§72/§1/§3/社労士法 §27] A4 - 就業規則生成 Pack. - [product_kaisha_setsuritsu_pack](https://jpcite.com/docs/mcp-tools/#product_kaisha_setsuritsu_pack): [AUDIT, SENSITIVE - §52/§47条の2/§72/§1/§3/社労士法/会社法/商業登記法]