io.github.beepboop2025/seiche

Est-ce que io.github.beepboop2025/seiche est sûr ?

Au dernier audit MCP Hub, le serveur MCP « io.github.beepboop2025/seiche » est classé « Non encore testé ». Référencé dans l'annuaire. Seul le pentest comportemental fait foi, et il n'a pas encore été exécuté sur ce serveur. Le verdict est réévalué en continu ; consultez la fiche pour l'état à jour.

Méthode : MCP Hub analyse la description de chaque outil (couche 1) et, pour le verdict fort, exécute le serveur dans une micro-VM isolée avec leurres et réseau bloqué (couche 2). On publie des noms et des compteurs, jamais le contenu brut renvoyé par un outil.

Les 16 outils

• crypto_stress_record≈ 344 tokens

  Labelled crypto stress episodes (Black Thursday 2020, Terra, FTX, the SVB/USDC weekend, the Oct-2025 liquidation cascade, the Ethena unwind) replayed with causal truncation but final/current-vintage inputs against the dollar-funding board. External wrecks show transmission; crypto-native wrecks show the board correctly staying quiet. Use for any 'does TradFi funding stress reach crypto' question, grounded in the record.

  Paramètres, retour & exemple (0)

  Exemple d'appel

  {"name": "crypto_stress_record", "arguments": {}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"ok": true, "reason": "texte", "status": "texte", "reading": "texte", "category": "texte"}}

• data_health≈ 322 tokens

  Freshness, provenance, and fault status for every underlying series (FRED, NY Fed, OFR, Treasury). Call this to confirm the board is current before relying on a reading.

  Paramètres, retour & exemple (0)

  Exemple d'appel

  {"name": "data_health", "arguments": {}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"ok": true, "faults": [], "reason": "texte", "status": "texte", "reading": "texte", "version": "texte", "category": "texte", "provenance": {}, "generated_at": "texte"}}

• funding_stress_now≈ 470 tokens

  The live money-market funding-stress reading: a 0-100 composite index, the regime (CALM/EROSION/STRAIN/STRESS), per-component decomposition, the market-stress 'Tell', and any data faults. Ask this whenever an analysis touches US dollar funding, repo, reserves, the Fed's balance sheet, or liquidity conditions.

  Paramètres, retour & exemple (0)

  Exemple d'appel

  {"name": "funding_stress_now", "arguments": {}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"ok": true, "tell": {}, "as_of": "texte", "proof": {}, "faults": [], "reason": "texte", "schema": "texte", "status": "texte", "reading": "texte", "version": "texte", "category": "texte", "delivery": {}}}

• fx_materials_passage≈ 536 tokens

  The live upstream FX and physical-material pressure read versus funding already priced in SOFR and commercial paper, with the Passage's discovery/holdout ledger, de-clustered analogs, dollar-system context and settlement scenarios. Use for currency weakness, commodity working capital, FX settlement, or whether trade-flow cash pressure is reaching money markets. Context only; an earned link is stable association, not causation.

  Paramètres, retour & exemple (0)

  Exemple d'appel

  {"name": "fx_materials_passage", "arguments": {}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"ok": true, "as_of": "texte", "reason": "texte", "schema": "texte", "status": "texte", "analogs": {}, "caveats": [], "leaders": {}, "passage": {}, "reading": "texte", "sources": [], "category": "texte"}}

• gift_city_context≈ 414 tokens

  Read dated USD/INR funding, separate ECB and CBUAE VAT FX references, and CFTC COMEX gold positioning. Cache-only research with source clocks; no executable prices or regulatory eligibility determination.

  Paramètres, retour & exemple (0)

  Exemple d'appel

  {"name": "gift_city_context", "arguments": {}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"ok": true, "gold": {}, "forex": {}, "reason": "texte", "schema": "texte", "status": "texte", "funding": [], "sources": [], "category": "texte", "eligibility": {}, "methodology": [], "context_only": true}}

• gold_inventory_carry≈ 602 tokens

  Calculate fine gold, simple financing cost and INR per fine gram from explicit decimal-string assumptions. All inputs are caller supplied, no quote is verified, and inputs are not persisted.

  Paramètres, retour & exemple (8)

  Paramètres

  • days · integer · requis
  • fees_usd · string · requis
  • fineness · string · requis
  • day_count · integer · optionnel · 360 | 365
  • quantity_kg · string · requis
  • fx_inr_per_usd · string · requis
  • annual_rate_pct · string · requis
  • price_usd_per_oz · string · requis

  Exemple d'appel

  {"name": "gold_inventory_carry", "arguments": {"days": 1, "fees_usd": "texte", "fineness": "texte", "quantity_kg": "texte", "fx_inr_per_usd": "texte", "annual_rate_pct": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"ok": true, "inputs": {}, "reason": "texte", "schema": "texte", "status": "texte", "outputs": {}, "category": "texte", "persisted": true, "assumptions": [], "eligibility": {}, "context_only": true}}

• historical_analogs≈ 397 tokens

  The historical days most similar to today's funding conditions, and how often those analogs led to a stress event, plus a novelty flag for whether today has any close precedent. Use to ground a 'what usually happens from here' question in real history.

  Paramètres, retour & exemple (0)

  Exemple d'appel

  {"name": "historical_analogs", "arguments": {}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"ok": true, "as_of": "texte", "reason": "texte", "status": "texte", "novelty": {}, "reading": "texte", "category": "texte", "event_odds": {}, "horizon_bd": 1, "forward_fan": [], "hindcast_skill": {}, "nearest_analogs": []}}

• institutional_flows≈ 393 tokens

  Hedge-fund / pension / sovereign positioning nowcast from public prints: the Treasury basis-trade size proxy (CFTC leveraged-fund net short, with a funding-fragility flag), asset-manager duration demand, foreign-official custody flows (H.4.1), a mixed-frequency fused positioning index with uncertainty bands, and how self-exciting stress events currently are (Hawkes branching ratio). Weekly cadence, point-in-time. Ask this when a question involves hedge fund leverage, the basis trade, pension duration bids, or sovereigns buying/selling Treasuries. Built from free public data.

  Paramètres, retour & exemple (0)

  Exemple d'appel

  {"name": "institutional_flows", "arguments": {}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"ok": true, "as_of": "texte", "reason": "texte", "status": "texte", "reading": "texte", "category": "texte"}}

• latest_article≈ 398 tokens

  The latest available full-text Seiche editorial, which may predate today. Returns the canonical headline, dek, Markdown, publication date, evidence clock, generation mode and passing publication receipt. Report its publication and evidence dates; do not describe an older edition as today's analysis. Use funding_stress_now for current funding conditions, and quote the article without regenerating facts.

  Paramètres, retour & exemple (0)

  Exemple d'appel

  {"name": "latest_article", "arguments": {}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"id": "texte", "ok": true, "url": "texte", "title": "texte", "reason": "texte", "status": "texte", "summary": "texte", "category": "texte", "content_text": "texte", "_liquidity_lab": {}, "date_published": "texte"}}

• market_workbench≈ 636 tokens

  Read cached official FX reference histories and same-date currency crosses, with native units, provenance, age and observed-interval changes. Inspect owner-accepted Palimpsest China annual economic series and revision-aware history beside the CNY reference. Daily fixings, annual context and licensed gaps remain distinct. No collection, model fitting, executable quotes or scoring.

  Paramètres, retour & exemple (5)

  Paramètres

  • base · string · optionnel · AUD | BRL | CAD | CHF | CNY | CZK | DKK | EUR
  • days · integer · optionnel
  • quote · string · optionnel · AUD | BRL | CAD | CHF | CNY | CZK | DKK | EUR
  • provider · string · optionnel · h10 | ecb
  • china_series · string · optionnel

  Exemple d'appel

  {"name": "market_workbench", "arguments": {"base": "AUD", "days": 1, "quote": "AUD", "provider": "h10", "china_series": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"ok": true, "china": {}, "forex": {}, "reason": "texte", "schema": "texte", "status": "texte", "category": "texte", "selection": {}, "eligibility": {}, "context_only": true, "generated_at": "texte", "money_markets": {}}}

• money_market_context≈ 1446 tokens

  Use section='countries' for the public-source country catalog, or add country='JP' (a supported ISO alpha-2 code; UK is an alias for GB) for dated policy, funding, liquidity and sovereign references. Country coverage is partial and monthly references are explicitly separate from daily curves. Granular, descriptive USD money-market context from the already assembled desk: policy corridor and overnight spreads; SOFR/TGCR/BGCR distributions and tails; repo-segment rates and volumes; CP-Treasury spreads; bills and cash curve; liquidity buffers and Fed facilities; and MMF repo plumbing. Use section='india' for the India funding, RBI liquidity, policy and sovereign-curve desk from a bounded canonical observation read. It keeps benchmark identities, date alignment, curve movements and mechanism hypotheses separate. India defaults to view='full' for compatibility; prefer view='summary' for findings, constraints and an exact metric ID catalog, then view='metric' with metric_id for one complete evidence card. These India-only views are independent reads, not a pinned snapshot or pagination. Otherwise use optional `section` to request a compact summary, one named USD desk section, diagnostics, sources, methodology, or all context. Diagnostics count funding persistence, compare secured/unsecured benchmarks and show calendar cohorts with sample limits, without changing any score. Returns exact-date alignment, native-cadence changes, empirical own-history statistics, freshness, coverage, formulas, sources, and caveats as applicable. Chart history is always omitted. USD reads only an already completed cached or persisted snapshot; it never triggers collection or engine recomputation, while freshness is re-evaluated at response time. Context only: no causal, predictive, probability, or trade claim.

  Paramètres, retour & exemple (4)

  Paramètres

  • view · string · optionnel · full | summary | metric
    India only: legacy full desk, compact findings/catalog, or one exact metric card.
  • country · string · optionnel
    Country code for section=countries only. Omit to list supported countries; UK aliases GB.
  • section · string · optionnel · summary | india | countries | diagnostics | policy_corridor | secured_distributions | repo_segments | unsecured_funding
    Projection to return; defaults to the compact desk summary.
  • metric_id · string · optionnel
    Exact ID from the India summary metric_catalog; required only for view=metric.

  Exemple d'appel

  {"name": "money_market_context", "arguments": {"view": "full", "country": "texte", "section": "summary", "metric_id": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"ok": true, "asof": "texte", "india": {}, "reason": "texte", "regime": {}, "schema": "texte", "status": "texte", "caveats": [], "sources": [], "category": "texte", "coverage": {}, "formulas": []}}

• oil_funding_context≈ 586 tokens

  Observed WTI/Brent, commercial-paper and SOFR−IORB evidence; Ballast's WTI/Henry Hub CFTC positioning, gross mark-displacement proxy, paying-side concentration and EIA inventory ledger; live Cushing stocks and the Brent−WTI spread kept separate from dated capacity, benchmark and chokepoint references; the change-on-change oil/CP association; plus explicitly scenario-only cargo-credit, margin and India cash arithmetic. Use when a question asks how oil or energy futures can transmit cash pressure into dollar funding. Ballast is not an observed margin call; dated structure is not live transit data; nothing here is a forecast, trade signal, or Seiche composite input.

  Paramètres, retour & exemple (0)

  Exemple d'appel

  {"name": "oil_funding_context", "arguments": {}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"ok": true, "oil": {}, "as_of": "texte", "india": {}, "reason": "texte", "schema": "texte", "status": "texte", "ballast": {}, "caveats": [], "funding": {}, "reading": "texte", "sources": []}}

• proof_backtest≈ 376 tokens

  The backtest scoreboard, stated honestly: recall and precision with 95% confidence intervals over labelled funding events, an orthogonal robustness test, every named episode (hits and misses), and the caveats. Use to judge how much to trust the readings.

  Paramètres, retour & exemple (0)

  Exemple d'appel

  {"name": "proof_backtest", "arguments": {}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"ok": true, "as_of": "texte", "reason": "texte", "sample": {}, "status": "texte", "caveats": [], "reading": "texte", "category": "texte", "episodes": [], "orthogonal": {}, "event_capture": {}, "historical_evidence": {}}}

• research_network≈ 540 tokens

  Explore every Palimpsest dataset by topic, with source clocks, rights, freshness and pagination. Includes Seiche's separately completed funding context and explicit research steps into institution filings, exit liquidity and NarcoScope's granular global data. Source metadata and funding interpretations stay distinct. No source collection, score changes, causal joins or trading authority.

  Paramètres, retour & exemple (3)

  Paramètres

  • limit · integer · optionnel
  • topic · string · optionnel · all | china | regions | information_controls | model_evaluations | funding | institutions | liquidity
  • offset · integer · optionnel

  Exemple d'appel

  {"name": "research_network", "arguments": {"limit": 1, "topic": "all", "offset": 1}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"ok": true, "reason": "texte", "schema": "texte", "source": {}, "status": "texte", "category": "texte", "datasets": [], "selection": {}, "next_steps": [], "context_only": true, "funding_context": {}}}

• trade_safety_risk_context≈ 1573 tokens

  A deterministic, bounded projection of the last completed Seiche board: funding regime, 0-100 stress index, coverage, source staleness counts, snapshot clock, and conservative evidence clock. It repeats the rights check and never collects, fits, calls a network source, reads a notary ledger, or contacts a broker. This is metadata-only derived context, not order-bound, non-executable, never real-money eligible, and it does not evaluate stream attestations or treat them as per-order authority.

  Paramètres, retour & exemple (0)

  Exemple d'appel

  {"name": "trade_safety_risk_context", "arguments": {}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"ok": true, "state": "context_only", "clocks": {}, "reason": "texte", "regime": "texte", "schema": "texte", "status": "available", "category": "texte", "staleness": {}, "disclaimer": "texte", "executable": "texte", "source_url": "texte"}}

• world_markets_context≈ 2236 tokens

  Unified, chartless context for broad financial-market questions. It projects only completed/public state into money_markets, forex, macro-capital transmission, China macro evidence, official references, methodology, or a compact summary. Every response carries snapshot/as-of clocks, canonical Seiche citation URLs, and explicit observed, derived, structural, restricted, and unavailable boundaries. The China structural catalog is unsigned; only status=restricted represents a verified Seiche owner-attested revision; both states keep NBS values, raw evidence, and history withheld. A separately operator-accepted economic_context may publish licensed World Bank WDI values with annual/structural freshness, distinct release, Palimpsest collection, and Seiche acceptance clocks. Those values are context only and never a live print, score, gauge, forecast, or signal. The sources selector is reference-only; use all when verified China context and its NBS source linkage must appear together. Coverage is curated and partial rather than exhaustive or uniformly live. It never triggers collection, repository history reads, or model fitting. Its named-field whitelist omits chart and history arrays for data minimization; that is not a per-record licensing audit. Capital coverage is limited to public positioning proxies, Treasury primary-market absorption, market stress, official liquidity and global dollar credit—not a security master, issuer-data service or consolidated tape. Use Undertow instead when the question is specifically about executable depth, liquidity-provider concentration, or position-sized exit cost.

  Paramètres, retour & exemple (1)

  Paramètres

  • section · string · optionnel · summary | money_markets | forex | capital_markets | china_macro | sources | methodology | all
    Projection to return; defaults to the compact cross-market summary.

  Exemple d'appel

  {"name": "world_markets_context", "arguments": {"section": "summary"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"ok": true, "as_of": "texte", "forex": {}, "scope": {}, "clocks": {}, "reason": "texte", "schema": "texte", "status": "observed", "sources": [], "summary": {}, "category": "texte", "citation": {}}}

C'est votre serveur ?

Revendiquez-le sur l'espace créateur (preuve GitHub, domaine ou npm) pour afficher le badge « propriétaire vérifié » et lancer un pentest comportemental à la demande afin d'obtenir le badge « Vérifié ».

Créer un compte / revendiquer →

Source

https://api.seiche.info/mcp