io.github.beepboop2025/liquilens

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

Au dernier audit MCP Hub, le serveur MCP « io.github.beepboop2025/liquilens » 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 24 outils

• bank_asset_quality_review≈ 189 tokens

  Cited NPA changes, PCR definitions and capital scope for banks/SFBs/UCBs, plus separately dated provisional business updates when accepted. Keep each period and provisional status explicit. No score, credit or execution authority.

  Paramètres, retour & exemple (3)

  Paramètres

  • slug · string · requis
  • as_of · string · optionnel
    End-of-day cutoff; not future.
  • include_history · boolean · optionnel

  Exemple d'appel

  {"name": "bank_asset_quality_review", "arguments": {"slug": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• bank_npa_reconciliation≈ 411 tokens

  Reconcile supplied NPA movements; keep recoveries/write-offs/sales/upgrades distinct. Arithmetic, not input authentication.

  Paramètres, retour & exemple (1)

  Paramètres

  • statement · object · requis

  Exemple d'appel

  {"name": "bank_npa_reconciliation", "arguments": {"statement": {}}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• banking_specialisation_coverage≈ 144 tokens

  Bank/SFB/UCB coverage with stale and missing evidence. Research, not a census or rating.

  Paramètres, retour & exemple (2)

  Paramètres

  • as_of · string · optionnel
    End-of-day cutoff; not future.
  • sector · string · optionnel · all | bank | sfb | ucb

  Exemple d'appel

  {"name": "banking_specialisation_coverage", "arguments": {"as_of": "texte", "sector": "all"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• corporate_transmission_board≈ 198 tokens

  Answers ONE question: is US funding stress reaching nonfinancial firms? Use household_credit_board for households. CP, bank credit lines and real-economy confirmation; cannot_see preserves gaps. Seiche context never enters regime or transmission. Display-only; no institution score or tier. full:true adds methods.

  Paramètres, retour & exemple (1)

  Paramètres

  • full · boolean · optionnel
    also return method_note, thresholds and per-leg basis prose (larger payload); default false

  Exemple d'appel

  {"name": "corporate_transmission_board", "arguments": {"full": true}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• crypto_exposure_board≈ 154 tokens

  Read the compact cited bank/crypto exposure register: disclosed quantum, stablecoin and venue links, exposure channels, Undertow run-risk cross-read and compound flags. Detailed disclosures stay on the public REST detail route. Takes no arguments; display-only, never an institution score or investment advice.

  Paramètres, retour & exemple (0)

  Exemple d'appel

  {"name": "crypto_exposure_board", "arguments": {}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• crypto_regime_board≈ 156 tokens

  Read the compact BTC/ETH Crypto Regime board: current change-point state, log-SR statistic, last shift, observation count and the display-only cross-read against disclosed bank exposure. Time-series paths stay on the public REST detail route. Takes no arguments; feeds no institution score and is not investment advice.

  Paramètres, retour & exemple (0)

  Exemple d'appel

  {"name": "crypto_regime_board", "arguments": {}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• evidence_europe≈ 178 tokens

  Read seven cited European retrospective case files through unrecalibrated Indian lenses. Named case studies, not a cohort: no European recall percentage to quote. Omit slug for summaries, or supply a returned slug for a full quarterly case file.

  Paramètres, retour & exemple (1)

  Paramètres

  • slug · string · optionnel
    optional kebab-case case-file slug, e.g. 'credit-suisse'; omit for all seven summaries

  Exemple d'appel

  {"name": "evidence_europe", "arguments": {"slug": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• evidence_india≈ 154 tokens

  Read the 48-institution Indian construction-PIT crisis diagnostic, including misses and false alarms. Uses publication clocks where present and a +60-day filing-lag proxy otherwise; overwritten amendments are unreconstructable. evidence_institution returns a full replay.

  Paramètres, retour & exemple (0)

  Exemple d'appel

  {"name": "evidence_india", "arguments": {}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• evidence_institution≈ 173 tokens

  Read a sourced Indian construction-PIT quarterly replay, lens alert timing and hit/miss/false-alarm verdict. Use evidence_india for exact slugs. Filing-availability proxies do not establish a validated backtest.

  Paramètres, retour & exemple (1)

  Paramètres

  • slug · string · requis
    kebab-case slug of a replayed institution, e.g. 'dhfl' or 'global-trust-bank'

  Exemple d'appel

  {"name": "evidence_institution", "arguments": {"slug": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• evidence_markets≈ 138 tokens

  Historical evidence: India (48-institution construction-PIT diagnostic), US (industry-wide current-amended vintage), Europe (named cases, no cohort claim). Start here, then evidence_india, evidence_us or evidence_europe for details.

  Paramètres, retour & exemple (0)

  Exemple d'appel

  {"name": "evidence_markets", "arguments": {}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• evidence_us≈ 203 tokens

  Read US bank current-amended-vintage diagnostics and named replays, including misses. Not a validated point-in-time backtest. Report the quarterly top-decile budgeted watchlist beside recall, uncertainty and lead times; it is not an individual-bank verdict. include_trajectories:true adds histories.

  Paramètres, retour & exemple (1)

  Paramètres

  • include_trajectories · boolean · optionnel
    also return per-quarter score series for the marquee replays (large payload); default false

  Exemple d'appel

  {"name": "evidence_us", "arguments": {"include_trajectories": true}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• failure_radar_board≈ 124 tokens

  Vetted Indian lender PDs, PCA/SAF and funding. market_dd requires tier authority; diagnostic clocks/refusals stay in market_dd_evidence. Slugs for failure_radar_institution. Research, not a rating.

  Paramètres, retour & exemple (0)

  Exemple d'appel

  {"name": "failure_radar_board", "arguments": {}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• failure_radar_institution≈ 172 tokens

  Read one Indian lender dossier: quarterly PDs and drivers, PCA/SAF headroom, funding, forensic and listed-market evidence. Discover slugs with failure_radar_board. Uncovered institutions remain absent, never scored from memory.

  Paramètres, retour & exemple (1)

  Paramètres

  • slug · string · requis
    kebab-case institution slug from a failure_radar_board row, e.g. 'esaf-sfb'

  Exemple d'appel

  {"name": "failure_radar_institution", "arguments": {"slug": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• forward_odds≈ 137 tokens

  Read counted Markov transitions and empirical 5/20-day reach odds. Odds are withheld until 60 observed days; counts stay visible and absence is never precision. Historical frequencies are not calibrated forecasts. Display-only, never a state driver.

  Paramètres, retour & exemple (0)

  Exemple d'appel

  {"name": "forward_odds", "arguments": {}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• household_credit_board≈ 191 tokens

  Answers ONE question: is stress reaching US household credit? Use corporate_transmission_board for firms. Delinquency, charge-offs, revolving credit and unscored debt-service context; gaps stay in cannot_see. Display-only; no institution score or watchlist tier. full:true adds methods and histories.

  Paramètres, retour & exemple (1)

  Paramètres

  • full · boolean · optionnel
    also return method_note, thresholds, labels and full sparklines (larger payload); default false

  Exemple d'appel

  {"name": "household_credit_board", "arguments": {"full": true}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• institution_evidence_monitor≈ 186 tokens

  Bank/NBFC evidence, gaps and review alerts. slug: one record; slugs: watchlist; neither: all tracked. End-of-day as_of. No scoring or delivery authority.

  Paramètres, retour & exemple (4)

  Paramètres

  • slug · string · optionnel
  • as_of · string · optionnel
  • slugs · array · optionnel
  • include_history · boolean · optionnel

  Exemple d'appel

  {"name": "institution_evidence_monitor", "arguments": {"slug": "texte", "as_of": "texte", "slugs": [], "include_history": true}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• institution_research_coverage≈ 162 tokens

  Search Indian dossiers or RBI rows. Overlapping populations; registry presence grants no financial coverage or score.

  Paramètres, retour & exemple (4)

  Paramètres

  • q · string · optionnel
  • limit · integer · optionnel
  • scope · string · optionnel · dossiers | rbi_registry
  • offset · integer · optionnel

  Exemple d'appel

  {"name": "institution_research_coverage", "arguments": {"q": "texte", "limit": 1, "scope": "dossiers", "offset": 1}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• institution_review_packet≈ 164 tokens

  Cited human review packet for an exact slug or unique normalized full name. No fuzzy match or new score; stale/dark gaps retained. Content hash detects alteration, not attestation or publication-time proof.

  Paramètres, retour & exemple (1)

  Paramètres

  • institution · string · requis
    exact Failure Radar slug or full institution name

  Exemple d'appel

  {"name": "institution_review_packet", "arguments": {"institution": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• latest_article≈ 146 tokens

  Read today's exact full-text LiquiLens editorial: current institution-risk analysis when the evidence moved, or a labelled historical replay when it did not. Returns the canonical headline, dek, Markdown, evidence clock and passing publication receipt; quote it without regenerating facts.

  Paramètres, retour & exemple (0)

  Exemple d'appel

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

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• rbi_supervisory_tape≈ 162 tokens

  Read the latest RBI enforcement and supervisory actions — monetary penalties, licence cancellations and supervisory directions — parsed from rbi.org.in press releases, newest first, each item carrying the RBI's own source URL. Takes no arguments. When no tape snapshot exists on the deployment, says so in a stated note instead of returning silent emptiness.

  Paramètres, retour & exemple (0)

  Exemple d'appel

  {"name": "rbi_supervisory_tape", "arguments": {}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• research_network≈ 198 tokens

  Route to Palimpsest sources, Seiche funding, Undertow exit liquidity and NarcoScope data. Set limit for full metadata. Rights remain attached; no identity, score or eligibility changes.

  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": "…"}]}

• stablecoin_rails_board≈ 134 tokens

  Paged peg/run evidence; partial data is never CALM. Follow pagination.next_offset. Full receipts on REST. Display-only, not investment advice.

  Paramètres, retour & exemple (2)

  Paramètres

  • limit · integer · optionnel
  • offset · integer · optionnel

  Exemple d'appel

  {"name": "stablecoin_rails_board", "arguments": {"limit": 1, "offset": 1}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• universe_search≈ 253 tokens

  Search the RBI NBFC register by name/CIN substring, classification or regulation layer. Returns official register rows. Supply q or a filter; a filter without q browses that slice. Registration does not establish creditworthiness.

  Paramètres, retour & exemple (4)

  Paramètres

  • q · string · optionnel
    case-insensitive substring of the registered name or CIN
  • layer · string · optionnel · Upper | Middle | Base
    Scale Based Regulation layer filter
  • limit · integer · optionnel
    maximum rows to return (default 20, capped at 50)
  • classification · string · optionnel
    exact RBI classification as it appears in the register, e.g. 'MFI' or 'HFC'

  Exemple d'appel

  {"name": "universe_search", "arguments": {"q": "texte", "layer": "Upper", "limit": 1, "classification": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• verify_published_record≈ 162 tokens

  Verify a ledger stream by recomputing hash-chain commitments and checking enabled signatures and anchors. Returns the actual verifier verdict, including failures. Verifies record integrity, not economic accuracy.

  Paramètres, retour & exemple (1)

  Paramètres

  • stream · string · optionnel
    ledger stream name to verify (default 'mfi_watchlist')

  Exemple d'appel

  {"name": "verify_published_record", "arguments": {"stream": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

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.liquilens.in/mcp