Skip to main content
Glama
818,103 tools. Updated 2026-11-21 21:27

"CCC" matching MCP tools:

  • Enumerate every ACC and BIM 360 project the authenticated APS app can see by walking all accessible hubs and their project lists. When to use: The agent needs to discover project IDs before calling any other tool (e.g. the user says 'show me my projects' or 'find issues in the Tower project' and no project_id is known yet). Also useful to confirm hub membership for a project. When NOT to use: Do not call this repeatedly in a loop — cache the result; if the user already supplied a project_id starting with 'b.', skip discovery. APS scopes: data:read account:read. No write scope needed. Rate limits: APS default ~50 req/min per app per endpoint; BIM 360 hubs endpoints are pageable (limit 200). This tool fans out 1 hubs call + N project calls (one per hub) so call it sparingly on tenants with many hubs. Errors: 401 (APS token expired — refresh and retry once); 403 (app not provisioned in the BIM 360/ACC account — ask user to have an account admin add the APS client_id); 404 (rare, indicates hub deleted mid-call); 429 (rate limit — back off 60s); 5xx (ACC upstream — retry with jitter). Side effects: None. Read-only and idempotent.
    ConnectorNo auth
  • Upload a file from a public source URL into an ACC project folder. Runs the full four-step APS Data Management flow: top-folder discovery → storage object creation → OSS PUT of bytes → first-version item creation. When to use: The user wants to push a document/photo/model into ACC Docs — e.g. 'upload this site photo to the Tower project Photos folder' or an automation needs to archive an exported report into Project Files. When NOT to use: Do not use for files already in ACC; do not use for files behind auth-gated URLs (fetch step is an unauthenticated GET). For very large files (>100MB), prefer the chunked/signed-S3 upload flow, not this single-PUT implementation. APS scopes: data:read data:write data:create account:read. Rate limits: APS Data Management ~50 req/min per endpoint; OSS upload bandwidth typically 100 MB/min per app. This tool issues 3–5 APS calls per upload, so budget accordingly. Errors: 401 (APS token expired — refresh); 403 (user lacks folder write permission — ask account admin to grant 'Edit' on folder); 404 (project_id not found or folder_path does not match any top folder — verify 'b.' prefix, hub membership, and folder name); 422 (invalid file_name or conflicting version); 429 (rate limit — back off 60s); 5xx (ACC/OSS upstream — retry with jitter BUT be cautious: storage object may already be created so reuse, do not re-create). Also: if source file_url returns non-2xx, the tool throws before touching ACC. Side effects: Creates a storage object, uploads bytes, and creates a versioned item in the target folder. NOT idempotent — a retry may create a duplicate item with a new version. Surface the returned item_id to the user to avoid re-uploads.
    ConnectorNo auth
  • Finds people by current company, title, country (ISO-2) or location and returns name, title, company and profile link, up to 25 results. Use to identify who to contact at a company. Work emails are not included: call apione_email_find for each person you want. Give at least one filter. Set count to cap spend. Not for details on one named person (use apione_people_enrich). Cost: 3 credits per result returned, so a full page of 25 results costs 75. No results, no charge.
    ConnectorNo auth
  • Upload a CAD file (STL, 3MF, OBJ, STEP) from an https URL or base64 content (filename required for base64). MCP requests are limited to 4 MB, so base64 works for files up to about 3 MB; use a URL or get_upload_url for larger files. no_controlled_data must be true: confirms the file has no CUI/ITAR/export-controlled data. Returns a part with status 'pending'; poll get_part until 'ready' (usually seconds), or pass wait_seconds.
    ConnectorNo auth
  • Query CDC WONDER for national US mortality statistics — deaths, population, and crude and age-adjusted death rates with their 95% confidence intervals — from one of five mortality databases, final and provisional, underlying-cause and multiple-cause, together covering 1999 through the current year. Break results out by year, month, age group, sex, race, Hispanic origin, or underlying cause of death — ICD-10 chapter or sub-chapter, CDC's 113-cause list, its 15 leading causes, or injury intent — and filter by ICD-10 cause of death, sex, age group, or year range; on a multiple-cause database, mcd_icd10 matches a cause listed anywhere on the death certificate rather than only the one certified as underlying. WONDER is a separate CDC system from the Socrata datasets the other cdc_* tools query. Data is national only — sub-national (state/county) breakdowns are not available through the API (CDC vital-statistics policy). Where this server stages tables (cdc_dataframe_query is listed), a first page that leaves rows past it also stages the whole table, which cdc_dataframe_query ranks, compares, or pages with SQL without another WONDER request. CDC rejects requests made less than 15 seconds apart across all five databases, so calls are spaced automatically: calls made while another is running wait their turn and run one after another, each queued call adding about 16 seconds plus its own query time before it returns. A request WONDER has not finished answering within 20 seconds fails as a retryable upstream_error, so one call queued behind another returns within about 56 seconds.
    ConnectorNo auth
  • Create a new ACC issue (field observation, coordination clash, safety, quality, etc.) in the target project via the APS Construction Issues API. When to use: The user wants to log a new issue — e.g. 'open a high-priority issue about the leaking valve on level 3' or a downstream agent detected a defect during a model review and needs to record it for the project team. When NOT to use: Do not use to modify an existing issue (use acc_update_issue) and do not use for RFIs (use acc_create_rfi). APS scopes: data:read data:write account:read. Rate limits: ACC Issues API limited to ~100 req/min per app; APS default ~50 req/min per endpoint — batch creations with backoff. Errors: 401 (APS token expired — refresh); 403 (user lacks 'Create Issues' permission on the project or scope insufficient — surface to user); 404 (project_id not found — verify the 'b.' prefix and that the project belongs to a hub the app can see via acc_list_projects); 422 (validation — required field like title/description missing or priority enum invalid); 429 (rate limit — retry after 60s); 5xx (ACC upstream — retry with jitter, do not double-create). Side effects: Creates a persistent issue record visible to all project members. NOT idempotent — a retry on a 5xx may create duplicates; dedupe by title before retrying.
    ConnectorNo auth

Matching MCP Servers

  • A
    license
    A
    quality
    B
    maintenance
    Stop treating AI like a chatbot. Turn ChatGPT into a team of AI agents that can plan, code, test, and review your local projects. ccc-mcp brings multi-agent workflows, evidence-based reviews, and cross-chat task recovery to your own codebase.
    43
    73 PyPI
    5
    MIT
  • A
    license
    Not graded
    quality
    D
    maintenance
    Consulta o Cadastro Centralizado de Contribuinte (CCC) do Sintegra a partir de CPF ou CNPJ, inscrição estadual e UF, integrando-se a clientes MCP via HTTP.
    MIT

Matching MCP Connectors

  • Looks up the centralized taxpayer registry (CCC) in Sintegra for a person or company from the CPF or

  • Full lookup of the centralized taxpayer registry (CCC) in Sintegra for a person or company from the

  • Calculate the cash conversion cycle (CCC): DSO + DIO - DPO — the net number of days cash is tied up between paying suppliers and collecting from customers. Formula: CCC = Days Sales Outstanding + Days Inventory Outstanding - Days Payables Outstanding. WHEN TO USE: Use as the definitive working-capital efficiency measure: a shorter (or negative) CCC means less capital trapped in operations. WHEN NOT TO USE: Do NOT use unless all three components are computed on a consistent 365-day basis and comparable periods. BEHAVIOUR: pure deterministic calculation — no side effects, no network or storage access; idempotent and non-destructive; identical inputs always produce identical outputs. Division by zero or non-finite inputs returns an explicit error instead of a number. RETURNS: JSON object { cash_conversion_cycle_days: number (e.g. 57.7 days; negative = operating on supplier cash), inputs }. PARAMETERS: dso (required): Days sales outstanding, e.g. 45.6. dio (required): Days inventory outstanding, e.g. 60.8. dpo (required): Days payables outstanding, e.g. 48.7.
    ConnectorNo auth
  • 全上場企業(約3,700社)の財務データからスクリーニングします。条件に合致する銘柄を返します。 使い分け: - 「バリュー株を探して」「成長株を探して」「高配当株を探して」「業績回復株を探して」など、 定型の投資フレームで漠然と探したい場合は screen_by_framework が向いています。 - このツール(screen_stocks)は、指標と数値を細かく組み合わせて指定したい場合に使います。 例: 「ROE>=20% かつ 自己資本比率>=60% かつ PER<=15」など。 カバレッジ: 東証プライム / スタンダード / グロースの事業会社 約3,700社(名証・札証・福証だけに上場している会社は含まない)。 データソース: 全銘柄の最新 annual.json を集約した edinet-summary.json(日次更新)。 利用可能な指標(全一覧): 引数 metric には英語キーを渡してください。 「キー=日本語名(単位)」の形式です。日本語名で指定しても内部で英語キーに正規化されますが、原則は英語キーを渡してください。 本番 summary の数値項目をすべて載せています。この一覧に無い指標は使えません。 [収益性(%)] roe=ROE(自己資本利益率), roa=ROA(総資産利益率), roic=ROIC(投下資本利益率), operatingMargin=営業利益率(金融業は経常利益率で代替。marginBasis参照), netProfitMargin=純利益率, grossProfitMargin=売上総利益率, ebitdaMargin=EBITDAマージン, operatingCFMargin=営業CFマージン, fcfMargin=FCFマージン(簡易FCF=営業CF+投資CF ÷売上高・%。金融業は screen では null), sgaRatio=販管費率(販管費÷売上高・%), rdRatio=研究開発費率(研究開発費÷売上高・%), effectiveTaxRate=実効税率(%) [安全性] equityRatio=自己資本比率, tangibleEquityRatio=有形純資産比率(%), currentRatio=流動比率, debtToEquityRatio=D/Eレシオ, netDebtToEbitda=ネットD/EBITDA倍率, interestCoverageRatio=インタレスト・カバレッジ・レシオ(営業利益÷支払利息・倍), retainedEarningsRatio=利益剰余金比率(利益剰余金÷総資産・%), goodwillRatio=のれん比率(のれん÷総資産・%), netCashRatio=ネットキャッシュ比率(ネットキャッシュ÷時価総額・倍。% ではない。優先株・種類株・資本性金融商品がある会社はその請求権を引いたネットキャッシュ), ncToAssets=NC/総資産(ネットキャッシュ÷総資産・%), ncToEquity=NC/自己資本(ネットキャッシュ÷自己資本・%) [還元] payoutRatio=配当性向, doe=DOE(株主資本配当率), totalReturnRatio=総還元性向, totalShareholderReturn=総還元額(配当+自社株買い・円), dividendYield=配当利回り, forecastDividendYield=予想配当利回り(%。会社予想の年間配当 ÷ 決算時株価。株価は有報の決算時の PER×EPS から復元した値で、市場の現在株価ではない), forecastOrdinaryDividendYield=普通配当の予想配当利回り(%。会社予想の年間配当から特別配当・記念配当を除いた額 ÷ 決算時株価), dividendPerShare=1株配当, ordinaryDividendYield=普通配当の配当利回り, ordinaryDividendPerShare=普通配当(1株配当から特別配当・記念配当を除いた額), specialDividendPerShare=特別配当・記念配当(1株), dividendInterim=1株中間配当(円), dividendYearEnd=1株期末配当(円) [効率・CF] assetTurnover=総資産回転率, cashConversionCycle=CCC(現金化速度), operatingCFToDebt=営業CF対有利子負債, capexRatio=設備投資比率(設備投資÷売上高・%), accrualRatio=アクルーアル比率((純利益−営業CF)÷総資産・%), salesPerEmployee=従業員1人あたり売上高(円), operatingIncomePerEmployee=従業員1人あたり営業利益(円) [割安・バリュエーション] per=PER(株価収益率), pbr=PBR(株価純資産倍率), psr=PSR(株価売上高倍率), evToEbitda=EV/EBITDA, pegRatio=PEG(前年比)(PER÷前年比のEPS成長率。PER>0かつ成長率>0の会社のみ・倍。6軸の実力PEGとは別の指標), ncav=NCAV(流動資産−負債合計・円), ncavRatio=NCAV比率(NCAV÷時価総額・倍。1以上でグレアム基準), fcfYield=簡易FCF利回り(簡易FCF=営業CF+投資CF ÷時価総額・%。金融業は営業CFに預り金等が入るため null。土地・事業・有価証券の売却入金で一時的に跳ねるので、極端に高い会社は投資CFの中身を確認し、oneOffSuspected も見ること。get_dcf_valuation の modelInputs.baseFcfYield は5年平均FCFで別の値), earningsYield=益回り(100÷PER・%), marketEv=EV(時価総額÷親会社の取り分(非支配株主の分を足し戻す)+優先株などの請求権+有利子負債−現金・円。EV/EBITDA の分子と同じ値。EBITDA が0以下の会社にも出る。理論企業価値 enterpriseValue とは別), marketCap=時価総額, eps=EPS(1株利益), bps=BPS(1株純資産), tsrCurrent=TSR(株主総利回り・5年間の累積倍率) [規模・絶対値] netSales=売上高, operatingIncome=営業利益, ordinaryIncome=経常利益(IFRS・米国基準は税引前利益), netIncome=当期純利益, totalAssets=総資産, equity=自己資本, tangibleEquity=有形純資産(円), currentAssets=流動資産(円), totalLiabilities=負債合計(円), investmentSecurities=投資有価証券(円), netCash=ネットキャッシュ, netDebt=ネット有利子負債, interestBearingDebt=有利子負債, ebitda=EBITDA, cashFlowFromOperations=営業キャッシュフロー(円), fcf=簡易フリーキャッシュフロー(営業CF+投資CF) [成長性(%)・連続年数] salesGrowth=売上成長率, operatingIncomeGrowth=営業利益成長率(%), netIncomeGrowth=純利益成長率(%), epsGrowth=EPS成長率, salesCagr3y=売上高CAGR(3年・%), operatingIncomeCagr3y=営業利益CAGR(3年・%), netIncomeCagr3y=純利益CAGR(3年・%), epsCagr3y=EPS CAGR(3年・分割調整後・%), salesPerEmployeeGrowth=従業員1人あたり売上高の成長率(%), operatingIncomePerEmployeeGrowth=従業員1人あたり営業利益の成長率(%), consecutiveSalesGrowthYears=連続増収年数, consecutiveOpGrowthYears=連続増益年数, consecutiveDividendGrowthYears=連続増配年数, totalYears=収録している決算年数 [前期・過去の値(ROAの推移を含む)] prevNetSales=前期の売上高, prevOperatingIncome=前期の営業利益, prevOrdinaryIncome=前期の経常利益(IFRS・米国基準は税引前利益), prevNetIncome=前期の純利益, prevEps=前期のEPS, prevRoe=前期のROE, prevRoa=前期のROA, prev2Roa=2期前のROA, roaChange3y=ROAの3年変化(最新期 − 3期前、%ポイント。マイナス=低下。4期が12か月×3で並ぶ会社だけ), consecutiveRoaDeclineYears=ROAの連続低下年数(最新期から遡って、前期よりROAが下がった期の連続数。0=低下していない), prevOperatingMargin=前期の営業利益率, prevEquityRatio=前期の自己資本比率 [株式・株主] sharesOutstanding=発行済株式数, treasuryShares=自己株式数, issuedSharesTotal=発行済株式総数(議決権ベース), shareCountChange5y=株数の5年変化率(自己株式を除く発行済株式数・分割調整後・%。マイナス=自社株買い・消却で減少、プラス=増資・新株予約権等で増加), shareCountChange10y=株数の10年変化率(自己株式を除く発行済株式数・分割調整後・%。マイナス=減少、プラス=増加), foreignShareholdingRatio=外国人持株比率, institutionalShareholdingRatio=機関投資家持株比率, auditFeesTotal=監査報酬合計(円) [独自スコア(0-100)] scoreTotal=総合スコア, scoreValuation=割安度スコア, scoreProfitability=稼ぐ力スコア, scoreGrowth=成長性スコア, scoreSafety=安全性スコア, scoreShareholderReturn=還元力スコア, scoreMoat=事業独占力スコア, scoreValuationCoverage=割安度スコアの算出できた指標の割合(0-1。1未満は一部欠測), scoreSafetyCoverage=安全性スコアの算出できた指標の割合(0-1) [実力(一過性の損益を除いた試算)] normalizedEps=実力EPS(一過性損益を除いた試算), normalizedPer=実力PER(一過性損益を除いた試算), normalizedRoe=実力ROE(一過性損益を除いた試算), normalizedRoa=実力ROA(一過性損益を除いた試算), normalizedPayoutRatio=実力配当性向(一過性損益を除いた試算), normalizedTotalReturnRatio=実力総還元性向(一過性損益を除いた試算), normalizedOperatingMargin=実力営業利益率(一過性損益を除いた試算), normalizedNetIncome=実力純利益(一過性損益を除いた試算) [理想株価モデル] alphaPct=α値(%), upperAlphaPct=上値α値(%), idealPriceLow=理想株価(下値), idealPriceMid=理想株価(中央値), idealPriceHigh=理想株価(上値), pseudoPrice=擬似現在株価, pseudoPriceAgeMonths=擬似株価の基準日からの経過月数, assetValue=資産価値(1株あたり・円), businessValue=事業価値(1株あたり・円), growthValue=成長価値(1株あたり・円), dividendValue=配当価値(1株あたり・円), excessCashValue=超過現金価値(1株あたり・円), epsAnchor=採用EPS(アンカー), forecastEps=予想EPS, effectiveMultiple=実効倍率(キャップ後) ※ 金額は円、%と書いた比率は 15.2=15.2%、「倍」は倍率。foreignShareholdingRatio / institutionalShareholdingRatio だけ 0-1 表記(下記)。 ※ fields に指定するだけで条件にせず値を見ることもできます。verdict(5段階判定)は専用パラメータで指定します。 使用例: 「総合スコア80以上×割安以下」= conditions: [{metric: "scoreTotal", operator: ">=", value: 80}] + verdict: ["超割安", "割安"] 注意: - 会計基準が異なる銘柄(IFRS / USGAAP)は数値の比較に留意(特に営業利益・有利子負債)。 - USGAAP 連結 XBRL 不開示銘柄(オリックス等)は interestBearingDebt = null。 - 【重要】foreignShareholdingRatio / institutionalShareholdingRatio は 0-1 表記です (例: 22.8% の場合は 0.228 として保存されています)。roe や equityRatio 等の他の指標は % 表記(例: 15.2 = 15.2%)なので単位が異なります。「外国人持株比率30%以上」を条件にする場合、 value: 30 ではなく value: 0.3 を指定してください。value: 30 を指定すると、 エラーにはならず該当銘柄が0件(または比較演算子によっては意図せず全件)になります。 - institutionalShareholdingRatio は金融機関(信託銀行・保険会社等)のみの比率で、 証券会社・事業法人(政策保有株主)を含まない狭い定義です。 - 条件に使った指標が null の銘柄は自動的に除外されます(例: 保険業は netSales が null)。 - 金融業(銀行・証券・保険・その他金融)は営業CFに預り金等が入るため、fcfYield(FCF利回り)・fcf・fcfMargin は「対象外」で、値は null のまま行に notApplicable: [指標名] を付けます。FCF系の条件は金融業なら満たす扱い(値が取れていない欠損の会社は満たさない)、並べ替えは「値がある会社 → 対象外 → 欠損」の順です(Webのランキングと同じ)。 - fcfYield(簡易FCF=営業CF+投資CF)は土地・事業・有価証券の売却の入金で一時的に跳ねます。利回りが極端に高い会社(100%超など)は投資CFの中身を確認し、上位を見るときは oneOffSuspected も見てください。 - shareCountChange5y / shareCountChange10y(株数の5年・10年変化率、%)は、自己株式を除く発行済株式数を株式分割・併合で調整して比べた値です。 マイナス=自社株買い・消却で株数が減った、プラス=増資・新株予約権の行使・株式交換などで増えた(希薄化)。例: 自社株買いで株数を減らしている会社は conditions: [{metric: "shareCountChange5y", operator: "<=", value: -5}]。 5年(10年)前の年度が無い・決算期変更をまたぐ・分割調整できない会社は null(条件に使うと除外)。10年前の年度は自己株式数の記載が無いため、多くの会社で 純資産÷BPS から株数を推定しています。 - operator「==」は厳密一致のため小数値の指標ではほぼヒットしません。範囲指定は >= と <= を組み合わせてください。 - ヒット数が limit を超えた場合は結果ヘッダーに総ヒット数が表示されます。切れている場合は offset で続きを取得できます(例: limit=100, offset=100 で101〜200件目)。 - 単一銘柄の詳細は get_edinet_financial_data、開示は get_timely_disclosures。 - scores / verdict / alphaPct はラジ株ナビ独自算出値(日次バッチ更新)。 - 【重要】dividendYield / dividendPerShare は有報の「当期確定実績」ベースです。 来期の会社予想配当ではありません。分母も市場株価ではなく擬似株価(PER×EPS)です。 記念配当・特別配当を含む年度では実績利回りが跳ね上がり、来期予想とは大きく乖離します (例: 7463 アドヴァンは実績100円で利回り10.89%だが、来期予想は40円)。 dividendYield / dividendPerShare / payoutRatio は特別配当・記念配当を含む合計です。特別配当・記念配当を除いた値は ordinaryDividendPerShare(普通配当)・ordinaryDividendYield(普通配当の配当利回り)、除いた額は specialDividendPerShare です (有報の配当に関する注記・配当政策の節・期末配当の注記から決めた値。get_edinet_financial_data の annualSpecialDividend・ get_ideal_price の配当価値と同じ値。特別配当を決められない年度は ordinaryDividendPerShare が合計、specialDividendPerShare が null)。 consecutiveDividendGrowthYears(連続増配年数)は普通配当で数えます。 - salesGrowth / operatingIncomeGrowth / netIncomeGrowth / epsGrowth などの前期比(%)は、前期・今期とも黒字(売上は前期が正)の会社だけ値を持ちます。 前期が赤字・0 の会社(黒字転換・赤字縮小など)と、今期が赤字・0 の会社(赤字転落・損益ゼロ)は null で、条件に当たりません(マイナスの前期で割った率は向きが逆に読めるため)。 これらの会社の言葉(黒字転換・赤字転落・赤字縮小・赤字拡大・赤字継続・損益ゼロ)は、成長率の列を返す行に growthWords(例: {"operatingIncomeGrowth": "黒字転換"})として添えます。 言葉で絞り込むときは growthWords 引数を使います(例: 営業利益が黒字転換した会社 = growthWords: [{metric: "operatingIncomeGrowth", words: ["黒字転換"]}])。 - consecutiveSalesGrowthYears / consecutiveOpGrowthYears / consecutiveDividendGrowthYears(連続増収・増益・増配の期数)は、 有報の提出前は最新の決算短信(通期)の年度を含めて数えます(銘柄ページの「N期連続」と同じ値)。 これらを返す行には growthStreakBasis(数えた最新の年度 fiscalYearEnd・出どころ source=yuho(有報)か tanshin_annual(決算短信)・ disclosedDate・tdnetId)を添えます。有報の年度だけで数えた数が違う会社は growthStreakYuhoOnly(sales・op・dps)も添えます。 - ROA の推移: roa(最新期)・prevRoa(前期)・prev2Roa(2期前)・roaChange3y(最新期 − 3期前、%ポイント。マイナス=低下)・consecutiveRoaDeclineYears(最新期から遡って前期よりROAが下がった期の連続数。0=低下していない)。 例: ROAが3期連続で低下 = conditions: [{metric: "consecutiveRoaDeclineYears", operator: ">=", value: 3}]。年度の ROA(純利益 ÷ 期末総資産)の列を使い、比べる期が12か月×N で並ばない会社(決算期変更・年度の抜け)は null(条件に使うと除外)。 - forecastDividendYield(予想配当利回り、%)= 会社予想の年間配当(特別配当・記念配当を含む合計)÷ 決算時株価。株価は有報の決算時の PER×EPS から復元した擬似株価で、市場の現在株価ではありません(J-Quants・Yahoo の株価は使っていません)。 forecastOrdinaryDividendYield(普通配当の予想配当利回り、%)は、同じ株価で、会社予想の年間配当から特別配当・記念配当を除いた額を割った値です。行の forecastDividendYieldBasis に特別配当の額(forecastSpecialDividendPerShare)と出どころ(specialDividendSource: stated=短信の注記・修正開示に額あり / undetermined=額を読めない(このとき普通配当の利回りは null)/ not-stated=記載なし(含まれないことの確認ではない))を添えます。 dividendYield(実績)と同じ株価・同じ式で、分子だけが「来期の会社予想の年間配当」です。予想 PER と同じく、最新の有報の次の期を対象にした予想があるときだけ値を持ち、 有報より新しい通期短信が出ていて有報待ちの会社・予想配当が未定の会社・無配予想・予想の対象期が変則の会社は null(条件に使うと除外)。 高配当スクリーニングの結果は実績ベースの値です。個別銘柄の来期予想は get_earnings_forecast または get_edinet_financial_data の companyForecast で確認できます。 - verdict フィルタは決算時点の擬似現価(pseudoPrice)ベースの理想株価モデル判定であり、 市場株価との比較ではありません。verdict 指定時は各行に pseudoPriceFiscalYearEnd (判定の基準となった決算期末日)を併記します。割安/割高はこの基準日時点の判定です。 verdictBasisType="asset_floor" の行は、理論株価の中央値が下支え(資産価値の7割)に張り付いており、判定(割高・超割高だけ)は 資産価値の7割との比較で決まっています。利益から見るとさらに割高寄りです。下支えの会社で割安・超割安・適正になる会社、 金融4業種、有報より新しい決算短信が出ていて有報待ちの会社は verdict が無い(判定を出していない)ため、verdict フィルタには掛かりません。 - 【重要】sort.metric に alphaPct(α値)または upperAlphaPct を指定した場合、擬似現価の 鮮度(pseudoPriceFreshness)で並び替えを補正します。stale(決算から7-12ヶ月経過)/ obsolete(13ヶ月超)の銘柄は、α値がどれだけ高くても同ランク内の下位に降格されます (除外はされません。件数・フィルタ結果は変わらず並び順だけが変わります)。 3月決算企業が9月前後にほぼ全社該当する aging(4-6ヶ月)は降格しません。 この場合、各行に pseudoPriceFreshness / pseudoPriceAgeMonths を併記します(順位が低い理由が鮮度のことがあります)。 - sector(業種)・market(市場)・verdict(5段階判定)は指標ではないので、トップレベルの sector / market / verdict 引数で指定してください。conditions に {metric: "sector", operator: "==", value: "情報・通信業"} のように入れても受け付け、トップレベルの指定として扱います(応答の interpretedAs に記載。トップレベルの指定と食い違うときはエラー)。fields に sector / market を入れても受け付け、指標ではなく表示する列として扱います(絞り込みにはなりません。応答の interpretedAs に記載)。oneOffSuspected は指標ではなく、conditions には入れられません(除くには excludeFlagged: true)。 - 応答が大きいとき: compact=true にすると、返す列を code・companyName・条件/並べ替え/fields の指標だけに絞り(業種・市場・決算期・長い注記を省略)、応答を小さくできます。毎日の一覧用途向け。 - excludeFlagged=true にすると、一過性の疑い(oneOffSuspected)・擬似株価が13ヶ月超古い(obsolete)・配当性向が500%超の銘柄を結果から除き、除いた件数を理由別にヘッダーに表示します(stale は除かない)。 - goingConcern="exclude" で継続企業の前提に関する注記がある会社(最新の書類で注記あり)を除き、"only" で注記がある会社だけにします。最新の書類は有報・半期/四半期報告書・決算短信のうち期末日が最も新しいもの(get_stock_analysis の goingConcernLatest と同じ値)。注記がある会社の行には goingConcern: "present" と goingConcernAsOf(書類の期末日)を常に添えます。読んだ書類が無い・読み取れない会社は exclude では残し、only では除き、その社数をヘッダーに出します(「注記なし」とは扱いません)。 - oneOffSuspected: true の銘柄は特別損益で純利益・EPS・PER・理論株価・スコアが嵩上げされている可能性があります。 特別損益は get_edinet_financial_data で確認できます。 実力の値([実力] の指標・basis): - 実力の値は、特別損益・事業の売却益・減損などの一過性の損益を除いて試算した値です。一過性の損益が無い会社は公表の値と同じです。 - normalizedEps・normalizedPer・normalizedRoe・normalizedRoa・normalizedPayoutRatio・normalizedTotalReturnRatio・normalizedOperatingMargin・normalizedNetIncome は conditions・sort・fields にそのまま使えます(一過性の損益が無い会社は公表と同じ値。全社で比べられます)。 - 既定(basis 省略・reported)で、conditions に実力の値がある指標(per・roe・roa・eps・payoutRatio・totalReturnRatio・operatingMargin・netIncome)を 使い、結果に一過性の損益で公表と実力が違う会社が含まれるときは、応答の最後に、該当の社数と例(公表→実力)と「実力の値で絞り直しますか?」という問いかけが付きます。 - basis="normalized" は、conditions と sort のそれらの指標を実力の欄に置き換えて判定・並べ替えし、結果に公表と実力を並べて差の主な理由(normalizedReasons)を添えます。 応答の metricLabels は英語キー→日本語指標名の対訳です。利用者向けには日本語名(例: roe→「ROE(自己資本利益率)」)のほうが伝わりやすくなります。 データ品質・値の異常・不具合に触れる場合も同様で、フィールド名を示すときは「発行済株式数(sharesOutstanding)」のように日本語を主・英語キーを括弧内にすると読みやすくなります。 (出力は { metricLabels, results } 形式。銘柄配列は results に入ります) ※ 本データは情報提供を目的とし、投資助言・推奨ではありません。
    ConnectorOAuth
  • Find states, counties, congressional districts (cd), census places, CBSAs (metro areas), and tribal areas by case-insensitive literal name substring in the 2021 FCC geography lookup. Keep ambiguous matches distinct and choose the geography_type and geography_id to pass to fcc_get_coverage_summary. Include a location qualifier in name to narrow results; names do not establish exhaustive state membership. Always queries live FCC Open Data, even with the Form 477 mirror enabled, and needs no BDC credentials. Follow nextOffset until absent; no total match count is computed.
    ConnectorNo auth
  • What did a web page say on a given date? Finds the archived capture of a URL nearest that date across the Internet Archive Wayback Machine, Common Crawl and Arquivo.pt, reads it, and returns the readable text (HTML stripped) with the capture timestamp, a link to the archived copy, and the GAP between the date asked for and the capture actually used (e.g. "Captured 1.5 day(s) before the requested date"). One call replaces the find-capture, fetch-record, parse-HTML chain. If no archive holds a capture within max_gap_days (default 30) it answers status "no_capture" and names the nearest capture before and after the date with their gaps, so a distant capture is never passed off as the page on that date. Every archive's outcome is listed in sources[]; one that timed out or errored says so with its upstream status, and if all of them failed the answer is error "archives_unavailable", not no_capture. Captures are immutable and cached by capture id; served_from says whether the text came from cache or upstream. Use archive_compare to see what changed between two dates.
    ConnectorNo auth
  • Claygent-style per-row research: answer ONE question about ONE company and return a JSON object matching your output_schema, with every field wrapped in its own evidence, {value, evidence_url, quote, status}. status is NEVER self-reported by the model: "found" means this code independently verified the model's quote is a VERBATIM substring of text actually fetched; "inferred" means a value was given but the quote could not be verified; "not_established" means no source answered the field, and its value is always null, never guessed, never a blended score. Sources: "web" fetches the company's own site (entity.domain required, homepage, /about, /leadership) via fetch_url; "catalog" checks entity_profile (SEC EDGAR; resolved:false for a private company is expected, not a failure); "both" (default) tries both. max_cost (USD, default 0.02, max 0.50) scales how many pages are fetched and refuses up front if it is too small to pay for even one extraction call (floor $0.002), never silently overspends. A row where every source comes back empty costs nothing: every field is mechanically not_established with NO model call made. For a boolean/derived field (e.g. "does this company sell to healthcare"), the quote only has to SUPPORT the value, a descriptive sentence about customers/products counts, the source need not state the answer verbatim. leadership_page_status ("fetched"|"not_found"|"not_attempted", plus leadership_note) says plainly whether a leadership/team page was actually read, so a named-person field (head_of_sales) coming back not_established is distinguishable from "this company just doesn't publish one" vs. "we never checked". model_output_empty:true means the model returned nothing usable (a transport/budget problem), every field is not_established for THAT reason, never read as 20 individual "no" judgments. Use with a fixed question + schema across many rows for "Claygent over N companies with a hard cost cap" (composes with batch callers). For picking from a fixed label list instead of extracting open fields, use classify_row (cheaper, one model call).
    ConnectorNo auth
  • Tell the Pipeworx team something is broken, missing, or needs to exist. Use when a tool returns wrong/stale data (bug), when a tool you wish existed isn't in the catalog (feature/data_gap), or when something worked surprisingly well (praise). ONLY for tools served by this Pipeworx connection, if the tool came from a different MCP server in your client (another vendor's Gmail, Splunk, Slack, etc. connector), we cannot fix it and reporting it here only delays you; file it with that server instead. Not sure? Pipeworx tool names are the ones this connection lists. Describe the issue in terms of Pipeworx tools/packs, don't paste the end-user's prompt. Filing without an account returns a `claim_token`; pass it back later as pipeworx_feedback({claim_token:"pwfb_..."}) to read whether it was fixed and what changed. The team reads digests daily and signal directly affects roadmap. Rate-limited to 5 per identifier per day. Free; doesn't count against your tool-call quota.
    ConnectorNo auth
  • What did a web page say on a given date? Finds the archived capture of a URL nearest that date across the Internet Archive Wayback Machine, Common Crawl and Arquivo.pt, reads it, and returns the readable text (HTML stripped) with the capture timestamp, a link to the archived copy, and the GAP between the date asked for and the capture actually used (e.g. "Captured 1.5 day(s) before the requested date"). One call replaces the find-capture, fetch-record, parse-HTML chain. If no archive holds a capture within max_gap_days (default 30) it answers status "no_capture" and names the nearest capture before and after the date with their gaps, so a distant capture is never passed off as the page on that date. Every archive's outcome is listed in sources[]; one that timed out or errored says so with its upstream status, and if all of them failed the answer is error "archives_unavailable", not no_capture. Captures are immutable and cached by capture id; served_from says whether the text came from cache or upstream. Use archive_compare to see what changed between two dates.
    ConnectorNo auth
  • Claygent-style per-row research: answer ONE question about ONE company and return a JSON object matching your output_schema, with every field wrapped in its own evidence, {value, evidence_url, quote, status}. status is NEVER self-reported by the model: "found" means this code independently verified the model's quote is a VERBATIM substring of text actually fetched; "inferred" means a value was given but the quote could not be verified; "not_established" means no source answered the field, and its value is always null, never guessed, never a blended score. Sources: "web" fetches the company's own site (entity.domain required, homepage, /about, /leadership) via fetch_url; "catalog" checks entity_profile (SEC EDGAR; resolved:false for a private company is expected, not a failure); "both" (default) tries both. max_cost (USD, default 0.02, max 0.50) scales how many pages are fetched and refuses up front if it is too small to pay for even one extraction call (floor $0.002), never silently overspends. A row where every source comes back empty costs nothing: every field is mechanically not_established with NO model call made. For a boolean/derived field (e.g. "does this company sell to healthcare"), the quote only has to SUPPORT the value, a descriptive sentence about customers/products counts, the source need not state the answer verbatim. leadership_page_status ("fetched"|"not_found"|"not_attempted", plus leadership_note) says plainly whether a leadership/team page was actually read, so a named-person field (head_of_sales) coming back not_established is distinguishable from "this company just doesn't publish one" vs. "we never checked". model_output_empty:true means the model returned nothing usable (a transport/budget problem), every field is not_established for THAT reason, never read as 20 individual "no" judgments. Use with a fixed question + schema across many rows for "Claygent over N companies with a hard cost cap" (composes with batch callers). For picking from a fixed label list instead of extracting open fields, use classify_row (cheaper, one model call).
    ConnectorNo auth
  • Tell the Pipeworx team something is broken, missing, or needs to exist. Use when a tool returns wrong/stale data (bug), when a tool you wish existed isn't in the catalog (feature/data_gap), or when something worked surprisingly well (praise). ONLY for tools served by this Pipeworx connection, if the tool came from a different MCP server in your client (another vendor's Gmail, Splunk, Slack, etc. connector), we cannot fix it and reporting it here only delays you; file it with that server instead. Not sure? Pipeworx tool names are the ones this connection lists. Describe the issue in terms of Pipeworx tools/packs, don't paste the end-user's prompt. Filing without an account returns a `claim_token`; pass it back later as pipeworx_feedback({claim_token:"pwfb_..."}) to read whether it was fixed and what changed. The team reads digests daily and signal directly affects roadmap. Rate-limited to 5 per identifier per day. Free; doesn't count against your tool-call quota.
    ConnectorNo auth
  • What did a web page say on a given date? Finds the archived capture of a URL nearest that date across the Internet Archive Wayback Machine, Common Crawl and Arquivo.pt, reads it, and returns the readable text (HTML stripped) with the capture timestamp, a link to the archived copy, and the GAP between the date asked for and the capture actually used (e.g. "Captured 1.5 day(s) before the requested date"). One call replaces the find-capture, fetch-record, parse-HTML chain. If no archive holds a capture within max_gap_days (default 30) it answers status "no_capture" and names the nearest capture before and after the date with their gaps, so a distant capture is never passed off as the page on that date. Every archive's outcome is listed in sources[]; one that timed out or errored says so with its upstream status, and if all of them failed the answer is error "archives_unavailable", not no_capture. Captures are immutable and cached by capture id; served_from says whether the text came from cache or upstream. Use archive_compare to see what changed between two dates.
    ConnectorNo auth
  • Claygent-style per-row research: answer ONE question about ONE company and return a JSON object matching your output_schema, with every field wrapped in its own evidence, {value, evidence_url, quote, status}. status is NEVER self-reported by the model: "found" means this code independently verified the model's quote is a VERBATIM substring of text actually fetched; "inferred" means a value was given but the quote could not be verified; "not_established" means no source answered the field, and its value is always null, never guessed, never a blended score. Sources: "web" fetches the company's own site (entity.domain required, homepage, /about, /leadership) via fetch_url; "catalog" checks entity_profile (SEC EDGAR; resolved:false for a private company is expected, not a failure); "both" (default) tries both. max_cost (USD, default 0.02, max 0.50) scales how many pages are fetched and refuses up front if it is too small to pay for even one extraction call (floor $0.002), never silently overspends. A row where every source comes back empty costs nothing: every field is mechanically not_established with NO model call made. For a boolean/derived field (e.g. "does this company sell to healthcare"), the quote only has to SUPPORT the value, a descriptive sentence about customers/products counts, the source need not state the answer verbatim. leadership_page_status ("fetched"|"not_found"|"not_attempted", plus leadership_note) says plainly whether a leadership/team page was actually read, so a named-person field (head_of_sales) coming back not_established is distinguishable from "this company just doesn't publish one" vs. "we never checked". model_output_empty:true means the model returned nothing usable (a transport/budget problem), every field is not_established for THAT reason, never read as 20 individual "no" judgments. Use with a fixed question + schema across many rows for "Claygent over N companies with a hard cost cap" (composes with batch callers). For picking from a fixed label list instead of extracting open fields, use classify_row (cheaper, one model call).
    ConnectorNo auth
  • Tell the Pipeworx team something is broken, missing, or needs to exist. Use when a tool returns wrong/stale data (bug), when a tool you wish existed isn't in the catalog (feature/data_gap), or when something worked surprisingly well (praise). ONLY for tools served by this Pipeworx connection, if the tool came from a different MCP server in your client (another vendor's Gmail, Splunk, Slack, etc. connector), we cannot fix it and reporting it here only delays you; file it with that server instead. Not sure? Pipeworx tool names are the ones this connection lists. Describe the issue in terms of Pipeworx tools/packs, don't paste the end-user's prompt. Filing without an account returns a `claim_token`; pass it back later as pipeworx_feedback({claim_token:"pwfb_..."}) to read whether it was fixed and what changed. The team reads digests daily and signal directly affects roadmap. Rate-limited to 5 per identifier per day. Free; doesn't count against your tool-call quota.
    ConnectorNo auth
  • The same 15-minute crypto "up or down" window priced on polymarket.com, Polymarket US and Kalshi, side by side, with whether each pair is actually the same contract. Pass asset (btc | eth | sol | xrp | bnb) and window ("current" default, "next", "previous", or the window START as ISO such as 2026-10-27T14:15:00Z, on a 15-minute boundary). Per venue: question, Up bid / ask / mid / last, spread_pp, quote_state, volume WITH ITS UNIT, open interest, liquidity, settlement source, comparison basis, when it settles. THE VENUES ARE NOT ONE CONTRACT. Kalshi and Polymarket US settle on CF Benchmarks' BRTI (60-second average at the end against the same at the start): the same bet, so a gap between them is a real disagreement. polymarket.com settles on a Chainlink 60-second TWAP, end against start: same comparison shape, different feed, so a gap against either is partly the contract. `pairs[]` gives equivalent ("true"|"false"|"unclear"|"not_comparable") from resolution_diff for every pair, material_differences, mid_diff_pp (a minus b, in percentage points) and read_as in words. Measured over 30 days of settled windows the Chainlink and BRTI feeds settle a window differently about 1.2-1.8% of the time, almost entirely windows that ended near the threshold (see updown_divergence_rate). `net_spread` is computed only for the pair that is equivalent: the gap in mid terms and at top of book (buy Up where cheaper at the ask, Down where Up is dearer at 1 minus the bid) after BOTH venues' taker fees, each fee carrying its verified-as-of date. Top-of-book size is shown where the venue publishes it (Polymarket US); the Kalshi figure is not in its market payload, so read its order book before sizing. A venue with no market for the window is {status:"not_listed", reason}; one that could not be read is {status:"unavailable", refusal} -- never an empty object, and never the same thing. A one-sided book (typical Polymarket US just before a window is decided) has quote_state "bid_only", a null mid, and the last trade stands in labelled price_basis "last". Quotes are read venue by venue (cached up to 60 seconds), so a gap of a couple of points on a moving window is inside the skew. Only the 15m horizon is offered: it is the one where all three list the same up/down question. For the settled history of how often the venues disagreed, call updown_divergence_rate.
    ConnectorNo auth
  • The same 15-minute crypto "up or down" window priced on polymarket.com, Polymarket US and Kalshi, side by side, with whether each pair is actually the same contract. Pass asset (btc | eth | sol | xrp | bnb) and window ("current" default, "next", "previous", or the window START as ISO such as 2026-10-27T14:15:00Z, on a 15-minute boundary). Per venue: question, Up bid / ask / mid / last, spread_pp, quote_state, volume WITH ITS UNIT, open interest, liquidity, settlement source, comparison basis, when it settles. THE VENUES ARE NOT ONE CONTRACT. Kalshi and Polymarket US settle on CF Benchmarks' BRTI (60-second average at the end against the same at the start): the same bet, so a gap between them is a real disagreement. polymarket.com settles on a Chainlink 60-second TWAP, end against start: same comparison shape, different feed, so a gap against either is partly the contract. `pairs[]` gives equivalent ("true"|"false"|"unclear"|"not_comparable") from resolution_diff for every pair, material_differences, mid_diff_pp (a minus b, in percentage points) and read_as in words. Measured over 30 days of settled windows the Chainlink and BRTI feeds settle a window differently about 1.2-1.8% of the time, almost entirely windows that ended near the threshold (see updown_divergence_rate). `net_spread` is computed only for the pair that is equivalent: the gap in mid terms and at top of book (buy Up where cheaper at the ask, Down where Up is dearer at 1 minus the bid) after BOTH venues' taker fees, each fee carrying its verified-as-of date. Top-of-book size is shown where the venue publishes it (Polymarket US); the Kalshi figure is not in its market payload, so read its order book before sizing. A venue with no market for the window is {status:"not_listed", reason}; one that could not be read is {status:"unavailable", refusal} -- never an empty object, and never the same thing. A one-sided book (typical Polymarket US just before a window is decided) has quote_state "bid_only", a null mid, and the last trade stands in labelled price_basis "last". Quotes are read venue by venue (cached up to 60 seconds), so a gap of a couple of points on a moving window is inside the skew. Only the 15m horizon is offered: it is the one where all three list the same up/down question. For the settled history of how often the venues disagreed, call updown_divergence_rate.
    ConnectorNo auth
  • The same 15-minute crypto "up or down" window priced on polymarket.com, Polymarket US and Kalshi, side by side, with whether each pair is actually the same contract. Pass asset (btc | eth | sol | xrp | bnb) and window ("current" default, "next", "previous", or the window START as ISO such as 2026-10-27T14:15:00Z, on a 15-minute boundary). Per venue: question, Up bid / ask / mid / last, spread_pp, quote_state, volume WITH ITS UNIT, open interest, liquidity, settlement source, comparison basis, when it settles. THE VENUES ARE NOT ONE CONTRACT. Kalshi and Polymarket US settle on CF Benchmarks' BRTI (60-second average at the end against the same at the start): the same bet, so a gap between them is a real disagreement. polymarket.com settles on a Chainlink 60-second TWAP, end against start: same comparison shape, different feed, so a gap against either is partly the contract. `pairs[]` gives equivalent ("true"|"false"|"unclear"|"not_comparable") from resolution_diff for every pair, material_differences, mid_diff_pp (a minus b, in percentage points) and read_as in words. Measured over 30 days of settled windows the Chainlink and BRTI feeds settle a window differently about 1.2-1.8% of the time, almost entirely windows that ended near the threshold (see updown_divergence_rate). `net_spread` is computed only for the pair that is equivalent: the gap in mid terms and at top of book (buy Up where cheaper at the ask, Down where Up is dearer at 1 minus the bid) after BOTH venues' taker fees, each fee carrying its verified-as-of date. Top-of-book size is shown where the venue publishes it (Polymarket US); the Kalshi figure is not in its market payload, so read its order book before sizing. A venue with no market for the window is {status:"not_listed", reason}; one that could not be read is {status:"unavailable", refusal} -- never an empty object, and never the same thing. A one-sided book (typical Polymarket US just before a window is decided) has quote_state "bid_only", a null mid, and the last trade stands in labelled price_basis "last". Quotes are read venue by venue (cached up to 60 seconds), so a gap of a couple of points on a moving window is inside the skew. Only the 15m horizon is offered: it is the one where all three list the same up/down question. For the settled history of how often the venues disagreed, call updown_divergence_rate.
    ConnectorNo auth