MCP.Market

Autonomath MCP server

by shigetosidumeda-cyber·io.github.shigetosidumeda-cyber/autonomath-mcp·v0.5.0

Japanese public-program MCP — subsidies, loans, tax, law, invoice. 261 tools, ¥3/billable unit

C57/100grade C
What users say
No reviews yet
Be the first
Safety scan
C57/100

full report

Adoption
New

25 downloads/wk

Reviews

Write one

Nobody has reviewed Autonomath yet.

If you have run it, two minutes of your experience saves the next person an afternoon.

Autonomath tools (100, 1 write)

write = sends, deletes, buys or posts

Read from the package source without running it. The installed server may list more.

  • _pack_construction_impl
  • anonymized_cohort_query

    [AUDIT, SENSITIVE - §52/§47条の2/§72/§1/§3] HE-8 anonymized_cohort_query.

  • anonymized_cohort_query_with_redact_chain

    [AUDIT, SENSITIVE — §52/§47条の2/§72/§1] Wave 51 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 the cohort_size, write_audit_entry for the APPI-grade audit row) into one composed call. Returns ComposedEnvelope with composed_steps (anonymized_query.redact_pii_fields + check_k_anonymity + write_audi

  • apply_eligibility_chain_am

    Multi-step eligibility orchestration over prerequisite_chain → rule_engine_check → exclusion_rules → am_compat_matrix per program. Returns per-program verdict (eligible / partial / ineligible) + reasoning_steps + cite chain. Heuristic; verify primary source. §52 sensitive.

  • 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 case_studies + jpi_adoption_records. Single ¥3/req. NO LLM. §52 / §47条の2 / §1 sensitive — directional benchmark, not 採択保証 / 経営助言.

  • case_cohort_match_am

    [COHORT-MATCH] 同業 (JSIC) × 同規模 (employees + revenue) × 同地域 (prefecture) cohort matcher: pulls case_studies (jpintel.db, 2,286) + jpi_adoption_records (autonomath.db, 201,845) + per-program rollup (appearance_count / avg_amount / cohort_share). Single ¥3/req. NO LLM. §52 / §47条の2 / §1 sensitive — information retrieval, not 申請代理.

  • case_law_search

    [CASE-LAW] 判例検索 (Q10 弁護士 cohort) — Tier B ¥6 placeholder scaffold (W4 AWS-K 後 LIVE)。

  • case_law_summary

    [CASE-LAW] 判例単体 summary — Tier A ¥3 placeholder scaffold (W4 AWS-K 後 LIVE)。

  • case_law_to_law_refs

    [CASE-LAW] 判例 → 引用法令 (KG cites_law edge walk) — Tier B ¥6 placeholder。

  • 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. Pure SQLite over case_studies. ¥3/req. NOT sensitive (1次資料の検索).

  • 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' / 'expired' / 'unknown') + last_validated_at + invalidation_reason + amendment_diff_ids lineage.

  • check_enforcement_am

    [ENFORCEMENT] Returns 行政処分 records from am_enforcement_detail 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 1,185-row corpus only — absence of records does NOT prove a clean record. Verify primary source (source_url) for due-diligence decisions.

  • check_foreign_capital_eligibility

    [ENGLISH-WEDGE] Per-program foreign-capital eligibility flag lookup over am_subsidy_rule.foreign_capital_eligibility (migration 092). Returns most-restrictive of {eligible / eligible_with_caveat / case_by_case / excluded / silent}. NO LLM, single ¥3/req. 行政書士法 §1 / FDI 規制 fence — disclaimer envelope mandatory.

  • check_funding_stack_am
  • composable_subsidy_audit

    [AUDIT, SENSITIVE - §52/§47条の2/§72/§1/§3] HE-10 composable_subsidy_audit.

  • compose_audit_workpaper

    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, pure SQL. §52 / §47条の2 / §72 / §1 sensitive.

  • copilot_scaffold_workpaper

    [AUDIT, SENSITIVE - §52/§47条の2/§72/§1/§3] HE-13 copilot_scaffold_workpaper.

  • cross_source_score_am

    [CROSS-SOURCE] fact_id ごとの cross-source agreement score (0.0..1.0) を 1 call で返す。複数の一次資料 (e-Gov / NTA / METI / other) が同じ値を支持している割合 (agreement_ratio) + canonical_value + 各 source の値 (per_source_values) + 派生 confidence_band ('high'/'medium'/'low'/'unknown') を含む。NO LLM、純粋 SQLite。1 unit billing。出力 agreement_ratio が高くても上流ドラフトの孫引き集中の可能性があるため、最終判断は各 source_url の原典確認が必須。

  • 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 / components dict / overall。エラー時 503 + retry_after を返し、内部例外は raise せず envelope 化。

  • discover_related

    [DISCOVER-RELATED] Returns up to 5 axes × 5 rows of related entities for the given entity in one call. Pure SQL + sqlite-vec, NO LLM. 1 ¥3 unit per call. SAME composer as REST GET /v1/discover/related/{entity_id}.

  • dynamic_eligibility_check_am
  • explainable_evidence_chain
  • fact_signature_verify_am

    [FACT-SIGNATURE] Ed25519 signature verify + rule-based 'why' explanation for one extracted_fact row in a single MCP call. Returns verify={status: valid|tampered|no_signature|key_unconfigured, signed_at, key_id, payload_sha256} + why={explanation paragraph, rule_based, llm_used=false}. Detects byte-level tamper since signing (查察/audit retention proof) and surfaces the deterministic 'why this fact w

  • federated_partner_query

    [AUDIT, SENSITIVE - §52/§47条の2/§72/§1/§3] HE-12 federated_partner_query.

  • find_complementary_programs_am

    Seed program → am_compat_matrix compatible edges → portfolio with combined_ceiling_yen + conflicts. authoritative_share_pct surfaced. inferred_only=true edges are heuristic. §52 sensitive — verify 経費重複 + 適正化法 17 条 before stacking.

  • find_fdi_friendly_subsidies

    [ENGLISH-WEDGE] Find Japanese subsidy programs filtered by industry JSIC + foreign_capital_eligibility != 'excluded'. Ranks eligible > eligible_with_caveat > case_by_case > silent. NO LLM, single ¥3/req. 行政書士法 §1 / FDI 規制 fence — disclaimer envelope mandatory.

  • find_municipality_subsidies

    [DD2 GEO] 1,714 市町村 補助金 4-axis cohort lookup. Returns rows with 5-axis citation (subsidy_url + S3 PDF URI + OCR S3 URI + ocr_job_id + sha256). 政府著作物 §13 license — source_attribution envelope per row. NO LLM. Single ¥3/req.

  • 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_ja+en, region, OECD/G7/G20/ASEAN/EU 旗, visa_keiei_kanri, min_capital_yen, restricted_sectors, promotion_program, mofa_source_url, jetro_source_url, license, _billing_unit=1, _disclaimer (§72/§1/出入国管理). エラ

  • foreign_fdi_list_am

    いつ使う: 海外法人 (FDI) 日本進出 entry condition を 80 か国 cohort 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 0|1), limit (1-200). 出力: items (FDI 国情報 list w/ visa_keiei_kanri / min_capital_yen / restricted_sectors / promotion_program / mofa+jetro source_url), total, filters, _billing_unit=1, _disclaimer (§72/§1/出入国管

  • get_annotations

    [ANNOTATION] Return public annotation rows for a given entity_id.

  • get_evidence_packet
  • get_evidence_packet_batch

    [EVIDENCE-PACKET-BATCH] Bulk Evidence Packet composer — up to 100 {kind, id} lookups in one call. Returns {results[], total, successful, failed, errors[], _billing_unit, _next_calls, _disclaimer, corpus_snapshot_id, audit_seal}. SAME composer as get_evidence_packet. NO LLM. ¥3 × successful only.

  • get_houjin_360_am

    [CORPORATE-LAYER] 法人 360° view by 法人番号 — joins jpi_houjin_master + jpi_invoice_registrants + am_enforcement_detail + jpi_adoption_records into a single envelope. Surfaces master_info + invoice_status + enforcement_count + adoption_count + related_programs_count. NO LLM. §52 sensitive — 与信判断 / 税務助言 territory.

  • get_law_article_am

    [LAW-ARTICLE] Returns the article text from am_law_article 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 last_amended + source_url. Output is search-derived; verify primary source (e-Gov) for legal interpretation.

  • get_law_article_en

    [ENGLISH-WEDGE] Exact (law_id, article_no) lookup returning the e-Gov 英訳 EN body. Falls back to JP body with a warning when no EN translation exists. JP version remains the only legally authoritative text. Foreign-investor cohort. NO LLM, single ¥3/req. 弁護士法 §72 fence — disclaimer envelope mandatory.

  • get_program_eligibility_predicate

    [ELIGIBILITY] Returns a structured eligibility predicate for one program so the customer LLM can evaluate fit (industry/prefecture/capital/employees/age/crop/cert) with boolean logic instead of re-reading 公募要領. Predicate is search-derived from jpi_programs corpus snapshot (migration 164); a missing axis means "unknown", NOT "no constraint" — verify primary source (source_url) before final eligibil

  • get_tax_treaty

    [ENGLISH-WEDGE] Bilateral tax-treaty lookup over am_tax_treaty (33 rows live, schema seeds ~80). Returns WHT rates (dividend / interest / royalty / parent-sub), PE threshold, info-exchange status, MoAA arbitration flag, MoF source URL. NO LLM, single ¥3/req. 税理士法 §52 / 国際課税 fence — disclaimer envelope mandatory.

  • graph_traverse
  • houjin_360

    [R8] Unified houjin 360 in 1 call: master + adoption_records + enforcement_cases + bids_won + invoice_registrant_status + recent_news + watch_alerts + 3-axis scores (risk_score / credit_score / compliance_score). Joins houjin_master + jpi_adoption_records + am_enforcement_detail + bids + jpi_invoice_registrants + am_amendment_diff + customer_watches. Pure SQL, NO LLM. ¥3/billable unit. §52/§72/§1

  • houjin_invoice_status

    [R8-INVOICE-RISK] 法人番号 → 適格事業者番号 resolve + risk 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 fence。

  • industry_scale_region_view

    [N7 COHORT VIEW] Resolve a 業界(JSIC) × 規模(scale_class) × 地域(prefcode/citycode) cohort over am_segment_view (~4,935 rows). Returns cohort statistics: program_ids/program_count, judgment_ids/judgment_count, tsutatsu_ids/tsutatsu_count, adoption_count, popularity_rank within the JSIC major, plus the matched jsic_name_ja + resolved prefecture. Tier B (¥6). NO LLM, NO HTTP, deterministic SQLite lookup.

  • intel_audit_chain

    Composite Merkle proof + sources + 5-step verify chain in 1 call. Replaces 3-call audit fan-out (/v1/audit/proof + /v1/audit/seals + /v1/am/provenance). Auditor pastes booleans directly into 監査調書. ¥3/billable unit. §47条の2 / §52 fence — cryptographic provenance only, NOT 監査意見.

  • intel_bundle_optimal

    Houjin → 最適 program bundle in 1 call: greedy weighted optimizer over am_recommended_programs + am_compat_matrix + jpi_exclusion_rules. Returns bundle + total_expected_amount + conflict graph + alternative bundles + decision_support.{why_this_matters,decision_insights,next_actions}. ¥3/billable unit. §52/§1 fence.

  • intel_citation_pack

    Citation pack — every primary-source citation surface (法令+通達+裁決+判例+行政処分+採択) bundled as markdown (default) or JSON in 1 call. ¥3/billable unit. §52/§47条の2/§1/§72 fence — citation pack can be re-quoted into 申請書面/提案書 territory.

  • intel_competitor_landscape

    Competitor landscape wrapper. Delegates lazily to the REST pure helper or endpoint module when present. Pure in-process call; no HTTP roundtrip.

  • intel_conflict

    Combo conflict detector: pairwise check across am_compat_matrix + jpi_exclusion_rules + 適正化法 17 conditions, returns conflict_pairs + alternative_bundles. ¥3/billable unit. §52/§1 fence — flagging compatibility, NOT 申請可否判定.

  • intel_cross_jurisdiction

    Cross-jurisdiction wrapper. Delegates lazily to the REST pure helper or endpoint module when present. Pure in-process call; no HTTP roundtrip.

  • intel_diff

    Composite entity diff (M&A DD): shared_attrs + unique_to_a + unique_to_b + conflict_points across primary table + am_5hop_graph + am_program_eligibility_predicate + am_id_bridge. Pure SQLite + Python set arithmetic, NO LLM. ¥3/billable unit. §52/§72/§1/§3/§47条の2 fence — descriptive, NOT prescriptive.

  • intel_houjin_full

    Composite houjin 360-degree bundle in 1 call: meta + adoption_history + enforcement + invoice_status + peer_summary + jurisdiction + watch_status + decision_support.{risk_summary,decision_insights,next_actions,known_gaps}. Replaces 5+ legacy fan-out reads. ¥3/billable unit. §52/§72/§1 fence.

  • intel_match

    Smart matchmaking: top-N programs with documents, similar adopters, laws, tsutatsu, audit proof, plus next_questions, eligibility_gaps, and document_readiness to plan follow-up and application prep. Pure SQLite ranking. §52/§1 fence.

  • intel_news_brief

    News brief wrapper. Delegates lazily to the REST pure helper or endpoint module when present. Pure in-process call; no HTTP roundtrip.

  • intel_onboarding_brief

    Onboarding brief wrapper. Delegates lazily to the REST pure helper or endpoint module when present. Pure in-process call; no HTTP roundtrip.

  • intel_path

    5-hop bidirectional BFS reasoning chain between 2 entities in 1 call. Returns shortest_path + up to 3 alternates so customer LLM can visualise the citation chain. Walks am_5hop_graph + am_citation_network + am_id_bridge. ¥3/billable unit. §52/§72/§1 fence.

  • intel_peer_group

    同業他社 N peers in 1 call: Jaccard similarity on (jsic × prefecture × capital × employee bucket) + per-axis comparison envelope. NO LLM. §52/§72 fence — peer benchmarking, NOT 信用調査.

  • intel_portfolio_heatmap

    Portfolio heatmap wrapper. Delegates lazily to the REST pure helper or endpoint module when present. Pure in-process call; no HTTP roundtrip.

  • intel_probability_radar

    probability_estimate (NOT forecast) + same-industry adoption rate + mean award + ROI for (program × houjin) in 1 call. Pure SQLite, NO LLM. §52/§1 行政書士法 fence — output is statistical estimate, NOT 採択保証. Replaces 5+ legacy fan-out calls.

  • intel_program_full

    Composite per-program bundle in 1 call: program_meta + eligibility_predicate + amendments_recent + adoptions_top + similar_programs + citations + audit_proof. Replaces 8+ naive single-program calls. ¥3/billable unit. §52/§1/§72 fence.

  • intel_refund_riskwrite action

    Refund risk wrapper. Delegates lazily to the REST pure helper or endpoint module when present. Pure in-process call; no HTTP roundtrip.

  • intel_regulatory_context

    Full regulatory bundle for 1 program in 1 call: 法令 + 通達 + 裁決 + 判例 + 行政処分. Replaces 5+ axis-specific fan-out calls. ¥3/billable unit. §72/§52/§1 fence — primary-source pointers, NOT 法解釈.

  • intel_risk_score

    Multi-axis houjin risk score: enforcement + refund + invoice + adoption revocation + jurisdiction drift in 1 call. Rules-based public-data score, NO LLM. ¥3/billable unit. NOT a credit rating; §72/§52/§1 fence.

  • intel_scenario_simulate

    Scenario simulation wrapper. Delegates lazily to the REST pure helper or endpoint module when present. Pure in-process call; no HTTP roundtrip.

  • intel_timeline

    Annual cross-substrate event timeline for 1 program in 1 call. Cross-joins am_amendment_diff + am_adoption_trend_monthly + am_enforcement_anomaly + am_adopted_company_features + am_program_narrative_full. NO LLM. §52/§1/§72 fence.

  • intel_why_excluded

    Eligibility-failure reasoning: returns predicate_violations + remediation_steps + suggested_alternative_programs in 1 call. Walks am_program_eligibility_predicate + am_relation. NO LLM. §52/§1 fence — heuristic remediation, NOT 申請代理.

  • invoice_risk_batch

    [R8-INVOICE-RISK] T-number 一括 risk lookup (最大 100 件 / 1 metered call)。各 item は invoice_risk_lookup と同じ envelope shape (risk={…} or error="…")。経理 fan-out で取引先一覧を 1 call で scoring する用途。NO LLM。§52 fence。

  • invoice_risk_lookup

    [R8-INVOICE-RISK] T-number 単発 risk 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 risk_band (clear / caution / verify / block) を返す。NO LLM。§52 fence on 仕入税額控除 territory。

  • jpcite_route

    Route a user request to the cheapest sufficient P0 jpcite action. Free, deterministic, no external calls.

  • 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. Pure SQLite over laws + program_law_refs. ¥3/req. §72/§52/§1 fence.

  • 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. NOT sensitive — pure pointer, no advice; customer LLM fetches body itself.

  • ma_lifecycle_compose

    [AUDIT, SENSITIVE - §52/§47条の2/§72/§1/§3] HE-14 ma_lifecycle_compose.

  • match_cohort_5d_am

    [COHORT-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[]、cohort_meta (last_refreshed_at, eligible_count)。エラー: missing jsic/band → invalid_enum、autonomath.db 不在 → db_unavailable。1 ¥3/req。NO LLM。§52 / §47条の2 / §1 sensitive。

  • match_programs_by_funding_stage_am
  • pack_construction

    [INDUSTRY-PACK] 建設業 (JSIC D) cohort 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/req. NO LLM. §52/§47条の2 sensitive — information retrieval, not 税務助言. Compounds via _next_calls.

  • pack_manufacturing

    [INDUSTRY-PACK] 製造業 (JSIC E) cohort 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/req. NO LLM. §52/§47条の2 sensitive — information retrieval, not 税務助言.

  • pack_real_estate

    [INDUSTRY-PACK] 不動産業 (JSIC K) cohort 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/req. NO LLM. §52/§47条の2 sensitive — information retrieval, not 税務助言.

  • portfolio_optimize_am

    [R8-COMPAT] am_compat_matrix 43,966 row full surface — portfolio optimizer (greedy max-IS) + duplicate / mutually-exclusive risk pairs + top-3 recommended_mix ranked by axis-weighted score (coverage / amount / risk). Cross-joins am_compat_matrix + am_funding_stack_empirical + am_program_eligibility_predicate + am_relation. Pure SQLite + Python. NO LLM. §52 / §1 / §72 sensitive — verify 経費重複 + 適正化法

  • predictive_houjin_outlook

    [AUDIT, SENSITIVE - §52/§47条の2/§72/§1/§3] HE-5 predictive_houjin_outlook.

  • predictive_subscriber_fanout_chain
  • program_active_periods_am

    am_application_round (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 closed rounds exist OR close < 14 days away.

  • program_compatibility_pair_am

    [R8-COMPAT] 2 制度間の互換性 — 4-bucket verdict {compatible, mutually_exclusive, unknown, sequential} resolved over am_compat_matrix + am_funding_stack_empirical + am_program_eligibility_predicate + am_relation. 'sequential' fires on temporal-precedence edges (requires_before / precedes / follows / superseded_by). NO LLM. §52 / §1 / §72 sensitive.

  • program_eligibility_by_form_am

    [CORPORATE-FORM-AM] 制度別 法人格 適用表 (15 axes)。NO LLM, ¥3/req metered. `_disclaimer` 必須。

  • program_eligibility_for_houjin_am

    [ELIGIBILITY-PAIR-AM] Resolves eligibility for one (program, 法人) pair by joining am_enforcement_detail with exclusion_rules. NO LLM. Returns `_disclaimer`. Verify primary source.

  • 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. Pure SQLite over jpintel + best-effort autonomath am_amendment_diff. ¥3/req. §72/§52/§1/§27 fence.

  • program_risk_score_am

    [PROGRAM-RISK-4D] いつ使うか: 制度 × 業法 × 行政処分 × 取消理由の 4 軸 risk 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_risk + all_axes[]、weights、_disclaimer。エラー: program_id 未指定 → invalid_enum、precompute 不在 → axis_count=0 で返却 (200 OK)。1 ¥3/req。NO LLM。§52 / §47条の2 / §1 sensitive — 行政書士法 §1 / 税理士法 §52 の boundary を crossed 制度を識別する用途。

  • programs_by_corporate_form_am

    [CORPORATE-FORM-AM] 法人格 × 制度 適用 matcher。NO LLM, ¥3/req metered. `_disclaimer` 必須。

  • rest_pack_construction

    [INDUSTRY-PACK] 建設業 (JSIC D) cohort: top 10 programs + 5 saiketsu + 3 通達.

  • rule_tree_application

    [AUDIT, SENSITIVE - §52/§47条の2/§72/§1/§3] HE-7 rule_tree_application.

  • rule_tree_batch_eval_chain

    [AUDIT, SENSITIVE — §52/§47条の2/§72/§1] Wave 51 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_doc_ids in parallel index order. Replaces N atomic rule_engine_check round-trips with one composed call. Returns ComposedEnvelope with composed_steps (rule_tree.evaluate_tree:batch). NO LLM, 3 ¥3 units

  • 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 eligibility summaries.

  • 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 baked into every response. Returns top-N matches with houjin_bangou + status + last_update. §52 sensitive — 仕入税額控除 確定判断 territory.

  • search_laws_en

    [ENGLISH-WEDGE] Keyword search restricted to am_law_article rows where body_en (e-Gov 日本法令外国語訳, CC-BY 4.0) is present. Returns EN excerpt + source_url. Foreign-investor cohort entry point. NO LLM, single ¥3/req. 弁護士法 §72 / 国際課税 fence — disclaimer envelope mandatory.

  • search_loans_am

    [DISCOVER-LOAN] Returns matching loan products from am_loan_product, 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 source (source_url) for the actual lending terms.

  • 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+ / DB / DC / 労災特別加入 等) from am_insurance_mutual, filtered by plan_kind × premium range × tax_deduction_type × provider. Output is search-derived; verify primary source (source_url) for actual contract terms.

  • session_context_lookback

    [AUDIT, SENSITIVE - §52/§47条の2/§72/§1/§3] HE-6 session_context_lookback.

  • session_multi_step_eligibility_chain

    [AUDIT, SENSITIVE — §52/§47条の2/§72/§1] Wave 51 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 the terminal SavedContext snapshot. Surfaces per-step status (persisted / failed / skipped) so the agent can audit which actions landed. Returns ComposedEnvelope with composed_steps (session_context.ope

  • simulate_application_am

    Pure-SQL mock walkthrough: am_application_steps + am_prerequisite_bundle + am_application_round + am_law_article. Returns document_checklist + certifications + est_review_days + completeness_score. NO LLM. §52 sensitive — not a substitute for 行政書士 §1 申請代理.

  • 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) + max_hops (1-5)。出力: edges[]、by_link_type breakdown、edge_count。エラー: houjin_bangou が 13 桁でない → invalid_enum、precompute 不在 → edges=[] で返却 (200 OK)。2 ¥3/req (heavy)。NO LLM。§52 / §47条の2 / §1 sensitive — 取引先デュー

  • time_machine_program_status

    [AUDIT, SENSITIVE - §52/§47条の2/§72/§1/§3] HE-11 time_machine_program_status.

  • time_machine_snapshot_walk_chain

    [AUDIT, SENSITIVE — §52/§47条の2/§72/§1] Wave 51 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 emits pairwise counterfactual_diff results so the agent can trace how the dataset evolved over the window. Returns ComposedEnvelope with composed_steps (time_machine.query_as_of:walk + counterfactual_di

  • track_amendment_lineage_am

    am_amendment_snapshot 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_hash is uniform sha256-of-empty on 82.3% — time-series fence surfaced.

  • 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 ∈ {verified, inferred, unknown}; SHA256 checksum returned for re-checks. Up to 10 citations / 30s wall clock.

Public scan report

scanner v0.1.9 · 2026-09-27 · same rubric, same numbers if you re-run it

1 medium
  • Code scan754 source files scanned20/25
  • –Live reliabilityno gateway calls yet and no remote to proben/a
  • –Tool poisoningtools not inspected (local package is not executed); not countedn/a
  • Auth qualitylocal package, no credentials required12/15
  • Maintenancerepository not readable: repo not found3/15
  • Maintainer identityno repository or website to verify2/10

Findings (1)

  • mediumeval / new Function usedexec.eval
    autonomath_mcp-0.5.0/src/jpintel_mcp/api/main.py: …uate. # Deterministic decision-tree eval (AND/OR/XOR + LEAF predicates), # 1 c…
Overall 57/100. Components that don't apply are left out of the denominator. Any critical finding is an F.RubricAppeal a findingJSON

How Autonomath compares

Against every graded Finance MCP server, from our own scans and uptime checks. Updated after each scan run.

Safety score
57/100
higher than 15% of 1,761 Finance servers
Tools
100
the typical Finance server has 8
Tools that change things
1%
typical: 0%. Fewer write tools means less an agent can break
Downloads a week
25
more than 12% of 421 Finance servers with a package

What its tools let an agent do: 98 read · 1 change · 1 run or deploy

Install Autonomath in Claude Code, Cursor or VS Code

claude mcp add autonomath-mcp -- uvx autonomath-mcp
Add to Cursor

Autonomath: common questions

Is Autonomath MCP server safe?
With care: it is graded C, so read the findings first (57/100). Read the Autonomath safety report
How do I install Autonomath?
It runs on your machine. Copy the Claude Code, Cursor, VS Code or Claude Desktop config from the install section.
Does Autonomath need an API key?
Not as far as the registry entry and our scan can tell: no credentials are declared or required.
Is Autonomath maintained?
The latest release is v0.5.0.
What can I use instead of Autonomath?
Servers from other publishers that do the same job: Norman Finance — AI Bookkeeping, Accounting & Taxes MCP server, three.ws Tutor MCP server and Bcra MCP server.
How does Autonomath compare with other Finance MCP servers?
safety score 57/100 (higher than 15% of 1,761 Finance servers); tools 100 (the typical Finance server has 8); tools that change things 1% (typical: 0%. Fewer write tools means less an agent can break). Full comparison.

Alternatives to Autonomath

Same job from other publishers: the closest match first, then the best rated.

  • Norman Finance — AI Bookkeeping, Accounting & Taxes
    Bookkeeping, invoices and tax workflows for European businesses, including Polish KPiR and JPK.
    A
  • three.ws Tutor
    Read a Pay-As-You-Learn tutoring session's itemized tab and close it for an attested invoice.
    A
  • Bcra
    BCRA — Argentine Central Bank public data (exchange rates, inflation, reserves)
    A
  • E Arveldaja
    Estonian e-arveldaja (RIK e-Financials) accounting — invoices, bank import, reports.
    B
  • OpenAccountants
    Open-source AI accounting skills verified by licensed accountants (tax, VAT, payroll).
    B