LiquiLens — the Failure Radar
Measured conclusion: Deep-tested. L2 outcome: tools_ok.
Free bank-filing and counterparty research; cited evidence limits; public MCP needs no API key.
| Author | io.github.beepboop2025 |
|---|---|
| Access | remote |
| Publisher key required | No |
| Measured state | Deep-tested |
| L1 liveness | alive |
| L1 latency | 419 ms |
| Last measured | 2026-10-24 |
Add to your agent
Copy this into your MCP client config:
{
"mcpServers": {
"LiquiLens — the Failure Radar": {
"url": "https://api.liquilens.in/mcp",
"transport": "streamable-http"
}
}
}
Measured tools (24)
bank_asset_quality_reviewread-onlyCited 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.
Parameters:
slug(required) — stringas_of— string — End-of-day cutoff; not future.include_history— boolean
Hints: read-only yes · destructive not declared · idempotent yes · open-world no
bank_npa_reconciliationread-onlyReconcile supplied NPA movements; keep recoveries/write-offs/sales/upgrades distinct. Arithmetic, not input authentication.
Parameters:
statement(required) — object
Hints: read-only yes · destructive not declared · idempotent yes · open-world no
banking_specialisation_coverageread-onlyBank/SFB/UCB coverage with stale and missing evidence. Research, not a census or rating.
Parameters:
as_of— string — End-of-day cutoff; not future.sector— string
Hints: read-only yes · destructive not declared · idempotent yes · open-world no
corporate_transmission_boardread-onlyAnswers 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.
Parameters:
full— boolean — also return method_note, thresholds and per-leg basis prose (larger payload); default false
Hints: read-only yes · destructive not declared · idempotent yes · open-world no
crypto_exposure_boardread-onlyRead 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.
Hints: read-only yes · destructive not declared · idempotent yes · open-world no
crypto_regime_boardread-onlyRead 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.
Hints: read-only yes · destructive not declared · idempotent yes · open-world no
evidence_europeread-onlyRead 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.
Parameters:
slug— string — optional kebab-case case-file slug, e.g. 'credit-suisse'; omit for all seven summaries
Hints: read-only yes · destructive not declared · idempotent yes · open-world no
evidence_indiaread-onlyRead 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.
Hints: read-only yes · destructive not declared · idempotent yes · open-world no
evidence_institutionread-onlyRead 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.
Parameters:
slug(required) — string — kebab-case slug of a replayed institution, e.g. 'dhfl' or 'global-trust-bank'
Hints: read-only yes · destructive not declared · idempotent yes · open-world no
evidence_marketsread-onlyHistorical 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.
Hints: read-only yes · destructive not declared · idempotent yes · open-world no
evidence_usread-onlyRead 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.
Parameters:
include_trajectories— boolean — also return per-quarter score series for the marquee replays (large payload); default false
Hints: read-only yes · destructive not declared · idempotent yes · open-world no
failure_radar_boardread-onlyVetted 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.
Hints: read-only yes · destructive not declared · idempotent yes · open-world no
failure_radar_institutionread-onlyRead 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.
Parameters:
slug(required) — string — kebab-case institution slug from a failure_radar_board row, e.g. 'esaf-sfb'
Hints: read-only yes · destructive not declared · idempotent yes · open-world no
forward_oddsread-onlyRead 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.
Hints: read-only yes · destructive not declared · idempotent yes · open-world no
household_credit_boardread-onlyAnswers 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.
Parameters:
full— boolean — also return method_note, thresholds, labels and full sparklines (larger payload); default false
Hints: read-only yes · destructive not declared · idempotent yes · open-world no
institution_evidence_monitorread-onlyBank/NBFC evidence, gaps and review alerts. slug: one record; slugs: watchlist; neither: all tracked. End-of-day as_of. No scoring or delivery authority.
Parameters:
slug— stringas_of— stringslugs— arrayinclude_history— boolean
Hints: read-only yes · destructive not declared · idempotent yes · open-world no
institution_research_coverageread-onlySearch Indian dossiers or RBI rows. Overlapping populations; registry presence grants no financial coverage or score.
Parameters:
q— stringlimit— integerscope— stringoffset— integer
Hints: read-only yes · destructive not declared · idempotent yes · open-world no
institution_review_packetread-onlyCited 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.
Parameters:
institution(required) — string — exact Failure Radar slug or full institution name
Hints: read-only yes · destructive not declared · idempotent yes · open-world no
latest_articleread-onlyRead 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.
Hints: read-only yes · destructive not declared · idempotent yes · open-world no
rbi_supervisory_taperead-onlyRead 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.
Hints: read-only yes · destructive not declared · idempotent yes · open-world no
research_networkread-onlyRoute 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.
Parameters:
limit— integertopic— stringoffset— integer
Hints: read-only yes · destructive not declared · idempotent yes · open-world no
stablecoin_rails_boardread-onlyPaged peg/run evidence; partial data is never CALM. Follow pagination.next_offset. Full receipts on REST. Display-only, not investment advice.
Parameters:
limit— integeroffset— integer
Hints: read-only yes · destructive not declared · idempotent yes · open-world no
universe_searchread-onlySearch 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.
Parameters:
q— string — case-insensitive substring of the registered name or CINlayer— string — Scale Based Regulation layer filterlimit— integer — maximum rows to return (default 20, capped at 50)classification— string — exact RBI classification as it appears in the register, e.g. 'MFI' or 'HFC'
Hints: read-only yes · destructive not declared · idempotent yes · open-world no
verify_published_recordread-onlyVerify 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.
Parameters:
stream— string — ledger stream name to verify (default 'mfi_watchlist')
Hints: read-only yes · destructive not declared · idempotent yes · open-world no
Measured by MCPYP probing. Untested fields are omitted, never estimated. Listing is always free; MCPYP never proxies calls or stores user tokens.