LiquiLens — the Failure Radar
Free bank-filing and counterparty research; cited evidence limits; public MCP needs no API key.
| Endpoint | https://api.liquilens.in/mcp (streamable-http) |
|---|---|
| Registry version | 1.8.1 |
| Now | 26 tools · grade B (83) · pin ts_f40dc901dad605c7d17c22210ef103e9 · protocol 2025-06-18 |
| First / last listed | 2026-11-09 01:45 UTC / 2026-11-09 01:45 UTC |
| Grade over time | 2026-11-09: B (83), 26 tools |
Is this your server? Own a server? ToolFit hosted watch re-checks it every 24 h ($0.25 per 30 days) or 6 h ($0.60) and sends you an HMAC-signed webhook when its tools or grade change: POST https://api.youraitools.co/toolfit/v1/watch. To opt out, see About & opt-out.
Tools: bank_asset_quality_review bank_credit_land_stress bank_npa_reconciliation banking_specialisation_coverage corporate_transmission_board crypto_exposure_board crypto_regime_board evidence_europe evidence_india evidence_institution evidence_markets evidence_us failure_radar_board failure_radar_institution forward_odds household_credit_board institution_evidence_monitor institution_research_coverage institution_review_packet latest_article lending_geography rbi_supervisory_tape research_network stablecoin_rails_board universe_search verify_published_record
bank_asset_quality_review | Cited bank/SFB/UCB NPA, PCR and capital evidence. Keep provisional updates and periods separate. No score, credit or execution authority. params: slug*, as_of, include_history |
bank_credit_land_stress | Loan quality, NPA bridge, state NPA and housing loans vs peer block, geo context. Exact IDs; district is not measured lending exposure. full:true for cells. No score. params: slug*, district_id, as_of, full |
bank_npa_reconciliation | Reconcile NPA movements; keep recoveries, write-offs, sales and upgrades distinct. Inputs are not authenticated. params: statement* |
banking_specialisation_coverage | Bank/SFB/UCB coverage, stale/missing evidence and separate census counts. No rating. params: sector, as_of |
corporate_transmission_board | Answers ONE question: US firm funding stress? For households use household_credit_board. CP/credit lines/real economy; gaps in cannot_see. Seiche excluded from signals. Display-only, no score/tier. full:true adds methods. params: full |
crypto_exposure_board | Cited bank/crypto amounts, stablecoin/venue links and Undertow run-risk context. REST has detail. No institution score or investment advice. params: none |
crypto_regime_board | BTC/ETH change points, log-SR, shifts and counts; disclosed bank exposure context. REST has paths. No institution score or investment advice. params: none |
evidence_europe | Seven cited European retrospective case files through unrecalibrated Indian lenses. Named case studies, not a cohort: no European recall percentage to quote. params: slug |
evidence_india | 48-institution Indian construction-PIT crisis diagnostic, including misses and false alarms. Publication clocks where present, else a +60-day filing-lag proxy; overwritten amendments are unreconstructable. evidence_institution returns a full replay. params: none |
evidence_institution | A sourced Indian construction-PIT quarterly replay, lens alert timing and hit/miss/false-alarm verdict. Slugs from evidence_india. Filing-availability proxies do not establish a validated backtest. params: slug* |
evidence_markets | Historical evidence: India (48-institution construction-PIT diagnostic), US (industry-wide current-amended vintage), Europe (named cases, no cohort claim). Start here; details in evidence_india, evidence_us or evidence_europe. params: none |
evidence_us | 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; not an individual-bank verdict. params: include_trajectories |
failure_radar_board | 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. params: none |
failure_radar_institution | One Indian lender dossier: quarterly PDs and drivers, PCA/SAF headroom, funding, forensic and listed-market evidence. Slugs from failure_radar_board. Uncovered institutions remain absent, never scored from memory. params: slug* |
forward_odds | Counted Markov transitions and empirical 5/20-day reach odds, 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. params: none |
household_credit_board | Answers ONE question: US household credit stress? For firms use corporate_transmission_board. Delinquency, charge-offs, revolving credit; unscored debt service. Gaps in cannot_see. No score/tier. full:true adds history. params: full |
institution_evidence_monitor | 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. params: slug, as_of, include_history, slugs |
institution_research_coverage | Search Indian dossiers, RBI rows or NAFSCOB co-op census. Overlapping populations; listing grants no coverage or score. params: scope, q, limit, offset |
institution_review_packet | 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. params: institution* |
latest_article | Today's exact full-text LiquiLens editorial: current institution-risk analysis when the evidence moved, else a labelled historical replay. Quote it with its evidence clock and passing publication receipt, without regenerating facts. params: none |
lending_geography | Co-op operating areas and dated district environment. IDs: in-dccb-, in-stcb-, in-dist-, in-state-. No score. params: id*, offset |
rbi_supervisory_tape | RBI penalties, licence cancellations and directions, newest first with source URLs; missing snapshots stay explicit. params: none |
research_network | Palimpsest sources, Seiche funding, Undertow liquidity and NarcoScope metadata. Rights retained; no identity, score or eligibility changes. params: topic, offset, limit |
stablecoin_rails_board | Paged peg/run evidence; partial data is never CALM. Follow pagination.next_offset. Full receipts on REST. Display-only, not investment advice. params: offset, limit |
universe_search | Search the RBI NBFC register. Supply q or a filter; a filter without q browses that slice. Registration does not establish creditworthiness. params: q, classification, layer, limit |
verify_published_record | Check ledger hash chains, enabled signatures and anchors; retain failures. Record integrity, not economic accuracy. params: stream |
Entries describe changes in tool definitions. They are not statements about a server, its quality or its author. The grade measures how the tool definitions fit model providers (token cost, schema compatibility, confusable names) as scored by the ToolFit engine at the time of the listing. JSON: append .json. Opt-out: how or hello@youraitools.co.